iamdemetris
UserA curated library of senior grade Agent Skills and subagents for Claude Code and OpenAI Codex. 70 skills, 30 dispatchable subagents, designed for multi agent orchestration.
Categories
Indexed Skills (48)
api-contract-designer
Use when designing an API, writing a contract, choosing REST vs GraphQL vs gRPC, authoring OpenAPI / swagger / GraphQL SDL / proto, defining endpoints, request and response shapes, error codes, idempotency keys, pagination, webhooks, SDK surface, or stating a versioning policy. Triggers on API, contract, endpoint, REST, GraphQL, gRPC, OpenAPI, swagger, proto, schema first, idempotent, cursor pagination, breaking change, error code, webhook, SDK. Produces the contract artifact (OpenAPI spec, GraphQL schema, or proto), an error code table, a versioning policy, and a breaking change checklist before any code is written. Do not invoke for pure implementation work (route the request to senior-backend-engineer) or for system level protocol selection across services (route to staff-software-architect).
data-modeler
Use when designing or reviewing a database schema, ERD, table, column, index, foreign key, or identifier strategy; when choosing between relational, document, or column oriented stores; when normalizing, denormalizing, picking types (money, UUID, ULID, UUIDv7, enums), planning partitions or sharding, or defining soft delete and lifecycle policy. Triggers: schema, ERD, model, normalize, denormalize, index, foreign key, FK, cardinality, table, column, type, identifier, ULID, UUID, lifecycle, soft delete, partition, sharding, document store, NoSQL, DynamoDB. Produces forward and rollback DDL, a Mermaid ERD, an access pattern table, and a justified indexing plan. Antitrigger: do not invoke for writing application queries or migration runner code; hand off to `senior-backend-engineer` and `migration-planner`.
dependency-auditor
Use when reviewing dependencies, lockfile diffs, CVE alerts, supply chain risk, SBOM generation, npm audit, pip-audit, dependabot or renovate PRs, version bumps, postinstall scripts, transitive packages, or package manifests like package.json, requirements.txt, Cargo.toml, go.sum, pom.xml, Gemfile.lock. Produces a dependency audit report, an SBOM (CycloneDX or SPDX), a remediation plan with owners and due dates, a CI policy proposal, and a risk score rubric. Defensive only: own repos, authorized audits, and CI security hardening. Do not invoke for offensive supply chain work, malware authoring, or attacks on third party registries. Hand severity classification on critical CVEs and org wide policy to `principal-security-engineer`, CI enforcement to `senior-devops-sre`, and active exploitation to `incident-commander`.
migration-planner
Use for migration, replatform, schema change, backfill, dual write, shadow read, cutover, rollback, kill switch, expand contract, big bang, online migration, blue green, framework upgrade, cloud migration, zero downtime change. Produces a phased runbook, dual write plan, shadow read and backfill spec, cutover checklist, kill switch wiring, and a post migration cleanup ticket. Sequences destructive changes so production keeps working at every step, each phase ships independently, and every step is reversible until the cutover. Do not invoke for small in place changes that fit one deploy with no data reshape and no consumer coordination; that is a normal change, not a migration.
postmortem-author
Use when the team needs a postmortem, RCA, root cause analysis, incident writeup, blameless review, lessons learned doc, sev review, or action item list after an outage. Triggers on "what went wrong", "what went right", "retro after incident", "draft the postmortem", "publish the writeup", and "track the followups". Produces a Google SRE style postmortem document, a tracked action item table grouped by prevent or detect or mitigate, a two paragraph executive summary for stakeholders, a UTC timeline anchored to evidence links, and a "where we got lucky" section. Do not invoke during the live incident; route active firefighting to `incident-commander` and bring this skill in once the incident is resolved and the channel has stabilized.
senior-code-reviewer
Use when reviewing a pull request, diff, patch, or code change; when leaving PR comments, requesting changes, approving, or considering LGTM; when triaging review feedback, labeling severity (blocking, strong suggestion, nit), or rewriting a vague review into a useful one. Covers diff reading, context gathering, test review, API surface review, error path review, observability review, and summary composition. Triggers: review, PR, pull request, diff, patch, lgtm, looks good to me, nit, blocking, request changes, approve, code review, review comments, reviewer, second pair of eyes. Produces PR review summaries, severity labeled inline comments, follow up issue stubs, and approve / request changes verdicts. Not for live debugging of a failing build, see `senior-debugger`. Not for top down architectural design surfaced inside a PR, hand off to `staff-software-architect`. Not for restructuring the diff itself, hand off to `senior-refactorer`.
senior-debugger
Use when a bug, broken feature, error, exception, stack trace, crash, panic, NPE, segfault, undefined value, or intermittent failure needs root cause diagnosis. Use to reproduce a defect, isolate a faulty change, bisect a regression, read a stack trace, interpret logs, or answer "why doesn't this work". Triggers: bug, broken, error, exception, stack trace, traceback, crash, panic, NPE, NullPointerException, segfault, undefined, repro, reproduce, isolate, debug, heisenbug, flake, flaky, intermittent, regression, works on my machine. Produces a reliable repro, a debug log of hypotheses tested, a one paragraph root cause statement, a minimum fix description, and a regression test that would have caught it. Not for live customer impacting incidents, see `incident-commander`. Not for steady state latency or throughput work, see `senior-performance-engineer`. Not for PR review of a finished change, see `senior-code-reviewer`.
senior-performance-engineer
Use when a system is slow, when latency or throughput regresses, when memory grows unbounded, when a hot path needs profiling, when a perf budget or regression guard is needed, or when Core Web Vitals (LCP, INP, CLS) miss target. Covers baselining, profiling, flamegraph reading, allocation and GC analysis, query plans, tail latency, throughput tuning, and perf budgets in CI. Triggers: slow, latency, p50, p95, p99, throughput, RPS, hot path, profile, flamegraph, memory leak, allocations, GC, garbage collection, OOM, out of memory, regression, perf, Core Web Vitals, LCP, INP, CLS, tail latency. Produces perf investigation reports, benchmark scripts, perf budgets, regression guard tests, dashboard recommendations. Not for correctness bugs masquerading as perf issues, see `senior-debugger`. Not for infra scaling (replicas, partitioning, autoscaling), see `senior-devops-sre`.
senior-refactorer
Use when refactoring, cleaning up, extracting a method or component, renaming, moving, inlining, deduping, simplifying, restructuring, addressing a code smell, or paying down technical debt without changing observable behavior. Triggers: refactor, clean up, extract, extract method, extract component, rename, move, inline, dedupe, simplify, restructure, smell, code smell, technical debt, organize, tidy, reshape. Produces a refactor plan, a patch series of small commits (one move per commit), characterization tests when coverage is missing, and a before/after summary proving no behavior change. Not for performance work, see `senior-performance-engineer`. Not for changing behavior or adding features. Not for large structural redesigns, see `staff-software-architect`. Not for PR merge review, see `senior-code-reviewer`.
ecommerce-engineer
Use when building, reviewing, or operating online stores, storefronts, catalogs, carts, checkouts, inventory, order management, fulfillment, returns, and promotions. Covers product / variant / SKU modeling, PIM, external identifiers (GTIN, EAN, MPN), cart and checkout flows, pricing and promotion rule engines, tax (Avalara, TaxJar, Stripe Tax), shipping rates, OMS, ATP and reservations, RMA, fraud and chargeback workflows, peak readiness (Black Friday, drops, flash sales), and platform choice (Shopify, BigCommerce, commercetools, Magento, Adobe Commerce, headless on Next.js). Triggers: ecommerce, store, storefront, catalog, PIM, SKU, GTIN, cart, checkout, conversion, abandoned cart, shipping, fulfillment, OMS, inventory, ATP, returns, RMA, refund, promotion, discount, coupon, gift card, BNPL, Black Friday, fraud, chargeback, Shopify, BigCommerce, headless commerce. Produces catalog schemas, checkout sequences, order state machines. Not for regulated money movement or PCI scope, see fintech-engineer.
edtech-engineer
Use when designing, implementing, or reviewing education technology: LMS, MOOCs, K-12 classroom tools, higher ed admin, assessment and proctoring, tutoring, gradebooks, parent portals, and SIS integrations. Covers interoperability (LTI 1.3, OneRoster, xAPI, SCORM, QTI), student data privacy (FERPA, COPPA, CIPA), age gating, accessibility (WCAG 2.1 AA, captions, MathML, IEP accommodations), and classroom workflow on Chromebooks, school iPads, and locked down browsers. Triggers: edtech, education technology, LMS, Canvas, Moodle, Blackboard, Schoology, Google Classroom, K-12, higher ed, MOOC, tutoring, assessment, proctoring, grade, gradebook, SIS, LTI 1.3, OneRoster, FERPA, COPPA, age gate, student data privacy, classroom, teacher, student, parent portal, IEP. Produces data classification tables. Not for the FERPA/COPPA compliance program itself, see compliance-engineer.
engineering-team-lead
Use when planning a sprint or week, breaking an epic into tickets, sizing / estimating work, sequencing tasks across people, unblocking a stuck engineer, running a standup or retro, preparing a 1:1, writing a project update, or reprioritizing in response to a fire. Triggers: sprint, planning, tickets, breakdown, estimate, story points, standup, retro, 1:1, status update, unblock, delegate, capacity, WIP. Produces ticket breakdowns, sprint plans, status updates, retro outcomes, 1:1 agendas, project trackers. Not for technical design (use staff-software-architect) or hands on implementation (use senior-backend-engineer / senior-frontend-engineer).
fintech-engineer
Use when designing, implementing, or reviewing payments, money movement, accounts, balances, ledgers, settlement, reconciliation, KYC, AML, sanctions screening, disputes, chargebacks, FX, or regulated financial product surfaces. Covers authorization vs capture, refunds, partial refunds, refunds across days, idempotency on money endpoints, double entry posting, bank file ingestion, processor integrations, and PCI scope reduction. Triggers: fintech, payments, card processing, ACH, wire, SEPA, PayPal, Stripe, Adyen, ledger, double entry, account, balance, settlement, clearing, authorization, capture, refund, chargeback, dispute, KYC, AML, PCI DSS, PCI scope, SCA, 3DS, FX, reconciliation, bank file, ISO 20022, NACHA, OFAC, sanctions, BSA. Produces money flow diagrams, ledger schemas, idempotency designs, reconciliation jobs, PCI scope diagrams, KYC decision logs, dispute case shapes. Not for storefront checkout, see ecommerce-engineer; not for regulatory program management, see compliance-engineer.
healthcare-engineer
Use when building, integrating, or reviewing healthcare software: patient portals, clinician tools, EHR integrations, telehealth, digital therapeutics, claims and eligibility flows, or anything that touches PHI. Covers HIPAA, HITECH, 42 CFR Part 2, SaMD scope, FHIR R4, HL7 v2, DICOM, ICD-10, LOINC, SNOMED CT, NPI, Epic / Cerner / athenahealth integration, patient matching, audit trails, break glass access, and BAA inventory. Produces PHI data flow diagrams, FHIR resource maps, audit log shapes, access control matrices, BAA tracking sheets, HL7 v2 interface specs. Triggers: healthcare, HIPAA, PHI, ePHI, EHR, EMR, FHIR, HL7, DICOM, ICD-10, LOINC, SNOMED, NPI, SaMD, clinical, clinician, patient portal, Epic, Cerner, telehealth, BAA. Not for HIPAA program management, see compliance-engineer; not for general threat modeling, see principal-security-engineer.
principal-security-engineer
Use when threat modeling a system or feature, reviewing code or a design for security flaws, hardening auth / authorization / sessions / secrets, responding to a suspected vulnerability or incident, evaluating dependencies for CVEs, classifying data sensitivity, or designing security controls (CSP, CORS, rate limiting, WAF rules, audit logging, encryption at rest, encryption in transit). Triggers: security, threat model, STRIDE, OWASP, CVE, vulnerability, secret, IDOR, SSRF, XSS, CSRF, SQLi, prompt injection, supply chain, auth, authz, RBAC, encryption, secrets, compliance, SOC2, GDPR, HIPAA, PCI. Produces threat models, secure review findings, hardening plans, incident triage notes. Authorized contexts only: defensive security, pentest engagements with scope, CTF, security research. Not for AI prompt injection, jailbreak, or AI threat modeling, see senior-ai-safety-engineer. Not for routine dependency CVE or supply chain triage, see dependency-auditor.
senior-ai-agent-engineer
Use when designing, building, evaluating, or operating AI agents and agentic systems: single agent loops, planner / executor splits, orchestrator with subagents, swarms, tool using agents, ReAct style loops, and Model Context Protocol (MCP) servers. Covers tool surface design, agent state and checkpointing, step and cost budgets, termination conditions, human in the loop interrupts, multi agent topology, agent trace schemas, and layered safety gates. Triggers: agent, AI agent, autonomous agent, multi agent, orchestration, ReAct, tool use, function calling, MCP, Model Context Protocol, agent SDK, agent loop, agent state, subagent, agent trace, agent eval, human in the loop, agent budget. Produces tool definitions, agent loop skeletons, multi agent topologies, trace schemas, agent eval harnesses, safety gate plans. Not for prompt injection defense, see senior-ai-safety-engineer; not for single shot LLM calls, see senior-llm-app-engineer.
senior-ai-safety-engineer
Use when threat modeling an LLM or agent system, defending against prompt injection (direct and indirect), designing output safety pipelines, hardening tool use authorization, running an authorized red team set, classifying a system under EU AI Act / NIST AI RMF / ISO 42001, responding to an AI safety incident (jailbreak gone public, harmful output reported, system prompt leak), or evaluating training data privacy risk. Triggers: AI safety, LLM security, prompt injection, indirect prompt injection, jailbreak, output safety, content filter, moderation, model exfiltration, prompt extraction, system prompt leak, agent safety, tool safety, EU AI Act, NIST AI RMF, ISO 42001, OWASP LLM Top 10, red team AI, refusal, harmful content. Produces AI threat models, defense in depth diagrams, red team sets, output safety pipelines, tool authorization matrices, regulatory classification docs, incident response plans. Not for the agent loop itself, see senior-ai-agent-engineer.
senior-backend-engineer
Use when designing, implementing, or reviewing backend code, APIs (REST, GraphQL, gRPC), services, workers, schedulers, queues, databases, and data models. Covers endpoint design, validation, auth, pagination, idempotency, retries, rate limiting, schema design, migrations, indexing, transactions, caching, background jobs, and observability hooks. Triggers: backend, back end, API, endpoint, route, REST, GraphQL, gRPC, schema, migration, query, index, transaction, queue, worker, job, cron, cache, rate limit, idempotent, webhook. Produces endpoints, services, schemas, migrations, background jobs, API contracts. Not for UI work, see senior-frontend-engineer. Not for top down system topology, see staff-software-architect. Not for formal or public API contract design, see api-contract-designer.
senior-cv-engineer
Use when designing, training, evaluating, or shipping computer vision systems: image classification, object detection, segmentation, OCR, document AI, video understanding, action recognition, tracking, pose estimation, depth, multi camera, augmented reality, edge inference. Triggers: computer vision, CV, image classification, object detection, segmentation, OCR, document AI, video understanding, action recognition, tracking, YOLO, YOLOv8, SAM, SAM-2, CLIP, DINOv2, ViT, OpenCV, image pipeline, camera calibration, vision language, multi modal, augmented reality, ARKit, ARCore, depth estimation, pose estimation, multi camera, edge inference, ONNX, CoreML, TensorRT, NPU, quantization. Produces capture plans, annotation rubrics, sliced eval sets, calibration plots, augmentation policies, and export pipelines for the target runtime. Not for the broader ML system rigor (training pipelines, registry, drift), see `senior-ml-engineer` and `senior-mlops-engineer`. Not for the eval harness platform.
senior-data-engineer
Use when designing, building, reviewing, or operating data pipelines, warehouses, lakes, and lakehouses; batch and streaming ELT/ETL; dbt models; orchestration (Airflow, Dagster, Prefect, Mage); transformation (Spark, Flink, SQL); ingestion from Kafka, Kinesis, Pub/Sub, CDC; and storage on Snowflake, BigQuery, Redshift, Databricks, Iceberg, Delta. Triggers: data engineering, data pipeline, batch, streaming, ETL, ELT, dbt, Airflow, Dagster, Prefect, Spark, Flink, Kafka, Kinesis, Pub/Sub, warehouse, lake, lakehouse, Iceberg, Delta, Snowflake, BigQuery, Redshift, Databricks, SCD, late arriving data, data quality, Great Expectations, data contract, lineage, OpenLineage, freshness SLO, idempotency, watermark, exactly once, partition pruning, clustering, backfill. Produces data contracts, dbt models with tests, orchestrator DAGs, backfill plans, dataset cards, lineage wiring. Antitrigger: not for warehouse table modeling decisions in isolation (see `data-modeler`).
senior-data-scientist
Use when designing an experiment or A/B test, writing or reviewing an experiment proposal or analysis plan, sizing a study (power, alpha, MDE), checking an A/A test, picking a unit of randomization, choosing between A/B, multi armed bandit, switchback, or a quasi experiment (difference in differences, regression discontinuity, instrumental variable, synthetic control), analyzing results with confidence intervals and multiple testing correction, interpreting lift, defining primary and guardrail metrics, running cohort or segmentation analysis, or writing a result memo with a decision recommendation. Triggers: data scientist, experiment, A/B test, A/A test, hypothesis, p value, confidence interval, multi armed bandit, switchback, causal inference, lift, statistical power, sample size, MDE, propensity, segmentation, cohort, ATE. Not for shipping a model to production (serving, monitoring, retraining), see senior-ml-engineer; not for pipelines or warehouses, see senior-data-engineer.
senior-developer-advocate
Use when building a sample app or demo app, writing a getting started tutorial or integration guide, preparing a conference talk or workshop, running a livestream demo or office hours, scoping a hackathon, drafting an ambassador or partner relations plan, or routing community signal back to product and engineering. Covers dogfooding the product, time to first success, activation funnels, developer experience friction, and partner platform integration walkthroughs. Triggers: developer advocate, DevRel, developer relations, evangelist, community, sample app, demo app, tutorial, getting started, quickstart, integration guide, partner, ambassador, hackathon, workshop, conference talk, office hours, livestream, twitch stream, developer experience. Produces sample apps, getting started tutorials, integration guides, talk abstracts, workshop runbooks, community feedback reports. Not for authoritative API reference or canonical docs, see senior-technical-writer. Not for product roadmap or PRD ownership.
senior-devops-sre
Use when building or fixing CI/CD pipelines, designing deploy / rollback / canary / blue green strategies, configuring observability (metrics, logs, traces, alerts, SLOs, dashboards), responding to a production incident, writing a runbook, planning capacity, or hardening the platform. Triggers: deploy, deployment, pipeline, CI, CD, GitHub Actions, GitLab CI, CircleCI, Docker, rollout, rollback, canary, blue green, observability, metrics, logs, traces, Prometheus, Grafana, Datadog, alert, SLO, SLI, error budget, incident, postmortem, runbook, on call, paged. Produces pipeline configs, rollout plans, runbooks, dashboards, postmortems. Not for application code, see senior-backend-engineer / senior-frontend-engineer. Not for authoring Terraform / Pulumi / CDK modules, see terraform-expert. Not for Kubernetes manifest authoring, see kubernetes-expert.
senior-embedded-engineer
Use when designing, implementing, or reviewing firmware for microcontrollers and embedded devices, bringing up new hardware, writing peripheral drivers, designing RTOS task and ISR layouts, planning OTA update mechanisms, budgeting memory and power, hardening field deployments, or debugging timing, watchdog, and brownout issues. Covers bare metal C / C++ / Rust, FreeRTOS, Zephyr, NuttX, ARM Cortex-M, ARM Cortex-A, ESP32, STM32, RP2040, nRF52. Triggers: embedded, firmware, microcontroller, MCU, MPU, RTOS, FreeRTOS, Zephyr, NuttX, bare metal, Cortex-M, Cortex-A, ESP32, STM32, RP2040, nRF52, IoT, OTA, field upgrade, watchdog, brownout, ISR, interrupt, DMA, I2C, SPI, UART, CAN, low power, sleep, MISRA, HIL, soak test. Produces memory budgets, ISR catalogs, RTOS task lists, OTA designs, bring up checklists, telemetry budgets. Not for cloud backend that ingests device data, see senior-backend-engineer. Not for mobile companion app, see senior-mobile-engineer.
senior-eval-engineer
Use when designing an eval set or eval harness for an LLM app, agent, RAG pipeline, classifier, or generative output; building a gold set; configuring an LLM as judge with a rubric; calibrating a judge against human raters; designing slice metrics; wiring a regression suite into CI; running a vibe check with rigor; choosing between exact match, BLEU, ROUGE, BERTScore, faithfulness, groundedness, or retrieval recall at K; computing inter rater agreement (Cohen kappa, Krippendorff alpha); auditing judge drift; or reporting eval deltas vs a baseline. Triggers: eval, evaluation, LLM eval, judge, LLM as judge, gold set, holdout, regression suite, agent eval, rubric, calibration, inter rater agreement, Cohen kappa, vibe check. Produces eval task specs, gold set construction plans, judge configurations, harness run reports, regression gate policies. Not for the model itself (training, serving), see senior-ml-engineer; not for the prompt as a product, see senior-llm-app-engineer.
senior-fine-tuning-engineer
Use when scoping, justifying, running, evaluating, or operating a fine tune of an LLM or other foundation model: supervised fine tuning (SFT), direct preference optimization (DPO), RLHF or RLAIF, instruction tuning, continued pretraining, parameter efficient adapters (LoRA, QLoRA, PEFT), knowledge distillation, dataset curation, preference pair labeling, decontamination against eval, hosted fine tuning APIs (OpenAI, Anthropic, Together, Replicate), or bring your own GPU training on `Llama-3.1-70B`, `Mistral-Nemo`, Qwen, Gemma, HuggingFace base models. Triggers: fine tune, fine tuning, SFT, adapter, distillation, reward model, preference pairs, instruction dataset, base model, foundation model, Llama, Mistral, `bitsandbytes`, catastrophic forgetting. Produces fine tune justification docs, dataset cards, training configs, eval delta reports, model cards. Not for the eval harness itself, see senior-eval-engineer; not for the training platform, registry, or serving, see senior-mlops-engineer.
senior-frontend-engineer
Use when building, reviewing, or debugging user interfaces, React, Next.js, Vue, Svelte, Solid, Remix, Astro, SvelteKit, Nuxt. Covers component design, state management, routing, data fetching, forms, accessibility (a11y, WCAG, ARIA), performance (Core Web Vitals, Lighthouse, LCP, INP, CLS, bundle size), responsive layout, design system consumption, and modern CSS (Tailwind, CSS-in-JS, container queries). Triggers: frontend, front-end, UI, component, React, Next, Vue, Svelte, hook, hydration, SSR, RSC, a11y, Lighthouse, slow page, layout shift, bundle, Tailwind, shadcn. Produces components, refactors, performance fixes, a11y remediations, design system contributions. Not for visual / interaction design from scratch, see senior-ux-designer. Not for backend / API work, see senior-backend-engineer. Not for Tailwind config, theme, or plugin authoring, see tailwind-expert.
senior-game-engineer
Use when building, reviewing, profiling, or shipping games in Unity, Unreal (UE4, UE5), Godot, or a custom engine. Covers gameplay loops, real time rendering, shaders, GPU and CPU frame budgets, ECS and DOTS, physics, animation, navmesh, asset pipelines, save systems with versioning, netcode (lockstep, client server with prediction, rollback), determinism, and live ops. Triggers: game, Unity, Unreal, UE5, Godot, ECS, entity component system, DOTS, rendering, shader, GPU, frame budget, ms per frame, 60fps, 120fps, gameplay loop, save game, save system, multiplayer, lockstep, deterministic, netcode, rollback, client side prediction, server authoritative, physics, animation, navmesh, asset pipeline. Produces frame budget breakdowns, ECS component and system maps, save schema and migration plans, networking model decisions, asset pipeline specs, on target profiling reports. Not for visual or interaction design of UI screens, see senior-ux-designer. Not for general backend services, see senior-backend-engineer.
senior-llm-app-engineer
Use when designing, implementing, evaluating, shipping, or operating production LLM applications: chat, copilots, classification, structured extraction, summarization, drafting, and agentic flows. Covers prompt design under eval, structured output (JSON schema, regex, grammars), tool use and function calling, retrieval integration, model selection and version pinning, streaming UX, prompt caching, cost and latency budgets, observability on every call, rollout (shadow, canary, holdout), and prompt injection defense. Triggers: LLM, large language model, GPT, Claude, Llama, Mistral, OpenAI SDK, Anthropic SDK, prompt engineering, prompt design, function calling, tool use, agent, retrieval, RAG, embedding, eval, prompt injection, model routing, fallback, cost per call, streaming, caching, prompt cache. Produces versioned prompt files, LLM call wrappers. Not for the retrieval pipeline, see senior-rag-engineer; not for multi step agent topology, see senior-ai-agent-engineer.
senior-ml-engineer
Use when designing, training, evaluating against an existing eval set, shipping, or operating classical machine learning models in production. Covers problem framing, feature store contracts, training pipelines, offline evaluation against baselines, shadow deploys, A/B rollout, drift monitoring, retraining cadence, and batch and online inference with latency budgets. Triggers: ML, machine learning, model, training, serving, inference, feature store, embedding, fine tune, retraining, model drift, holdout, classification, regression, ranking, recommender, A/A test. Produces feature contracts, training run configs, model cards, shadow and canary plans. Not for research and experimentation, see `senior-data-scientist`. Eval harness design belongs to `senior-eval-engineer`; shipping an LLM application belongs to `senior-llm-app-engineer`.
senior-mlops-engineer
Use when operating the platform that trains, evaluates, deploys, serves, monitors, and retires ML models: building or reviewing training pipelines, model registries, feature stores, batch or online inference services, shadow and canary rollouts, drift detectors, model cards, retraining triggers, or model governance. Triggers: MLOps, model registry, feature store, training pipeline, model serving, batch inference, online inference, real time inference, model deployment, model monitoring, drift detector, shadow deployment, canary model, model card, governance, AI governance, lineage, model rollback, retraining, Tecton, Feast, MLflow, Kubeflow, Vertex AI, SageMaker, BentoML, KServe, Ray Serve, Triton, ONNX, model signing. Produces registry entries, feature contracts, rollout plans, drift configs, model cards, serving SLO sheets, retraining policies. Not for building the model itself, see senior-ml-engineer. Not for generic compute infra, see senior-devops-sre.
senior-mobile-engineer
Use when planning, building, reviewing, or shipping mobile apps across iOS and Android. Triggers: mobile, iOS, Android, native, cross platform, React Native, Expo, Flutter, Dart, Kotlin Multiplatform, KMP, Compose Multiplatform, Capacitor, Cordova, PWA, app store, App Store Connect, Google Play, Play Console, TestFlight, internal testing, push notification, APNs, FCM, deep link, universal link, App Link, offline, sync, background fetch, BGTaskScheduler, WorkManager, low end device, energy, battery, Material Design 3, Apple HIG, signing, provisioning, staged rollout, remote config, feature flag, kill switch. Produces platform decision matrices, mobile architecture sketches, push and deep link designs, offline sync strategies, and release checklists. Distinct from swift-ios-expert (iOS dialect deep dive); this skill is cross platform and decision focused across native, React Native, Flutter, and KMP. Not for visual design from scratch, see senior-ux-designer. Not for backend API design.
senior-model-router-engineer
Use when designing, building, or operating the gateway between applications and LLM or model providers: routing requests across Claude, OpenAI, Gemini, and open weights, enforcing per route SLOs, configuring provider failover, tracking cost per call site, designing prompt and semantic caches, applying per tenant rate limits, supporting BYOK (bring your own key), enforcing zero data retention (ZDR) and regional routing, or wiring gateway observability. Triggers: model router, Vercel AI Gateway, OpenRouter, LiteLLM, Portkey, model fallback, provider failover, cost routing, semantic cache, prompt cache, rate limit per tenant, BYOK, ZDR, prompt logging, multi provider, provider abstraction, model SLO, model version pinning. Produces route configs, fallback policies, tenant rate limit policies, observability event schemas, cost dashboard specs, BYOK custody plans, gateway SLO sheets. Not for the call site prompt, see senior-llm-app-engineer; not for self hosted serving, see senior-mlops-engineer.
senior-platform-engineer
Use when building or evolving an internal developer platform (IDP), designing paved roads and golden paths, shipping an internal CLI, scaffolding new services, wiring a service catalog (Backstage, Port, Roadie), standing up ephemeral preview environments per PR, building a developer portal, running user research with internal engineers, measuring time to first deploy / DX NPS / adoption, or coaching a team on product mindset for internal tooling. Triggers: platform, internal platform, IDP, internal developer platform, paved road, golden path, dev experience, DX, developer productivity, developer portal, service catalog, Backstage, Port, Roadie, internal CLI, scaffolding, ephemeral environment, preview environment, onboarding, time to first deploy, T2FD, self service. Produces internal platform PRDs, paved road designs, CLI command specs, scaffolding templates, catalog entry shapes, ephemeral env specs, adoption dashboards. Not for on call ownership or incident response, see senior-devops-sre.
senior-product-manager
Use when scoping a product or feature, writing or reviewing a PRD / one pager / spec, defining the problem and the target user, prioritizing a roadmap or backlog (RICE, ICE, MoSCoW, Kano), drafting user stories with acceptance criteria, defining success metrics / north star / activation / retention, preparing a launch plan, or making a build / cut / defer decision. Triggers: PM, product manager, PRD, spec, one pager, user story, acceptance criteria, roadmap, prioritization, RICE, ICE, KPI, OKR, north star, activation, retention, jobs to be done, JTBD, launch plan, MVP, cut line. Produces PRDs, one-pagers, user stories, prioritization matrices, launch plans, metric definitions. Not for technical breakdown into tickets, see engineering-team-lead. Not for visual design, see senior-ux-designer.
senior-qa-test-engineer
Use when designing a test strategy for a feature or service, writing or reviewing unit / integration / e2e / contract / property tests, building test infrastructure (fixtures, factories, test DBs, golden files), investigating a flaky test, raising or lowering coverage where it matters, setting test gates in CI, or planning regression coverage for a release. Triggers: test, testing, QA, coverage, unit test, integration test, e2e, end to end, Playwright, Cypress, Jest, Vitest, pytest, JUnit, mock, stub, fixture, factory, flaky, flake, regression, contract test, property test, fuzz, snapshot. Produces test plans, test code, fixture / factory libraries, flake investigations, CI gate definitions. Not for incident debugging in production, see senior-devops-sre. Not for Playwright locator, flake, or CI sharding specifics, see playwright-expert.
senior-rag-engineer
Use when designing, building, reviewing, or operating retrieval augmented generation systems: corpus parsing, chunking, embedding, indexing, retrieval (semantic, lexical, hybrid), reranking, citation, evaluation, and ingestion freshness. Covers vector stores (pgvector, Pinecone, Weaviate, Qdrant, Vespa, Milvus, Elastic kNN), embedding models (text-embedding-3, bge-large, nomic-embed, voyage, cohere), BM25 and reciprocal rank fusion, cross encoder rerankers, ColBERT, MMR, and retrieval specific evaluation. Triggers: RAG, retrieval augmented generation, retrieval, embedding, vector store, hybrid search, BM25, reranker, citation, chunking, document parsing, freshness, retrieval eval, recall, precision, NDCG, MRR. Produces parsing plans, chunking configs, vector store schemas, hybrid retrieval pipelines, retrieval eval harnesses. Not for the LLM app around retrieval, see senior-llm-app-engineer; not for eval harness rigor, see senior-eval-engineer.
senior-recommender-engineer
Use when designing, building, evaluating, or operating production ranking and recommendation systems: feed ranking, product recommendations, search ranking, content discovery, ads relevance, related items, you may also like, up next, home feed. Covers two stage retrieval plus ranking, two tower embedding retrieval, learning to rank (LTR), multi objective optimization (relevance plus engagement plus business value), diversity and MMR, exploration vs exploitation, contextual bandits, off policy evaluation (IPS, doubly robust), position bias correction, cold start strategies, and slice based monitoring. Triggers: recommender, recommendation, ranking, feed, candidate generation, CTR, watch time, engagement, recommender eval, NDCG, hit rate. Produces two stage pipeline designs, LTR specs, multi objective policies, off policy eval reports, exploration policies, cold start playbooks. Not for the training pipeline, see senior-ml-engineer; not for online experiment rigor, see senior-data-scientist.
senior-technical-writer
Use when writing or rewriting a README, API reference, user guide, tutorial, quickstart, onboarding doc, changelog, release notes, runbook prose, contributing guide, ADR / RFC polish, internal documentation, or any developer facing text. Covers structure (Diátaxis: tutorial / how to / reference / explanation), voice / tone, plain language editing, code sample authoring, screenshots vs textual diagrams, doc IA, and docs as code workflows. Triggers: docs, documentation, README, changelog, release notes, API reference, tutorial, quickstart, onboarding, runbook, CONTRIBUTING, guide, doc site, Diátaxis, plain language, rewrite, edit. Produces READMEs, API references, tutorials, changelogs, release notes, doc structure plans. Not for product copy / microcopy inside the UI, see senior-ux-designer. Canonical docs site tutorials stay here; activation and sample app driven tutorials go to senior-developer-advocate.
senior-ux-designer
Use when designing or critiquing user flows, information architecture, screen layouts, interaction patterns, microcopy, empty / error / loading states, or accessibility of a UX. Covers user research interpretation, wireframing, prototyping, usability heuristics (Nielsen, WCAG), interaction patterns (forms, search, filtering, navigation, onboarding), and design system thinking. Triggers: UX, UI design, design, wireframe, mock, flow, IA, information architecture, navigation, onboarding, empty state, error state, microcopy, usability, heuristic evaluation, persona, journey, prototype, Figma. Produces user flows, wireframes (textual / spec form), interaction specs, microcopy, heuristic-evaluation findings. Not for implementing UI code, see senior-frontend-engineer. Not for product scope / PRD, see senior-product-manager.
senior-voice-ai-engineer
Use when designing, building, evaluating, or operating production conversational voice systems: IVR, voice agents, voice assistants, agent voice fronts, voice cloning compliant products. Covers streaming STT (ASR), streaming TTS, real time pipelines over WebRTC and telephony (SIP, Twilio, Vonage, Telnyx), turn taking, barge in detection, VAD (voice activity detection), prosody and SSML, dialog state, latency budgets (time to first audio, end to end response time), telephony codecs (mu law, a law, narrow band, 8 kHz), accessibility (captions, text alternative). Triggers: voice AI, voice agent, STT, speech to text, ASR, TTS, text to speech, voice cloning, whisper, deepgram, ElevenLabs, Cartesia, Resemble, gpt-4o-realtime. Produces voice latency budgets, barge in specs, telephony integration plans, dialog state schemas, voice eval sets. Not for training or fine tuning the STT or TTS model, see senior-ml-engineer; not for the dialog LLM prompt, see senior-llm-app-engineer.
staff-software-architect
Use when designing a system, choosing a database / framework / cloud / message bus, writing an ADR or RFC, deciding build vs buy, planning capacity or scaling, reviewing an architecture diagram or proposal, sequencing a migration, or weighing technical tradeoffs at the CTO level. Triggers: architect, system design, HLD, high level design, ADR, RFC, topology, capacity, scaling, build vs buy, migration plan, tech selection, tradeoff. Produces ADRs, RFCs, system diagrams, capacity plans, migration sequences. Not for implementation or code review, hand off to senior-backend-engineer / senior-frontend-engineer.
aws-expert
Use when work touches AWS: EC2, S3, RDS, Aurora, Lambda, DynamoDB, IAM, VPC, ALB, NLB, CloudFront, ECS, EKS, Fargate, SQS, SNS, EventBridge, Step Functions, CloudFormation, Secrets Manager, KMS, CloudWatch, X-Ray, AWS Organizations, SCPs, Control Tower, Route 53, ACM, WAF, GuardDuty, IAM Identity Center, or OIDC federation for CI. Produces service selection writeups, least privilege IAM roles and policies, VPC blueprints with public, private, and isolated subnets plus VPC endpoints, ECS Fargate task definitions, Lambda skeletons with DLQ and concurrency, DynamoDB single table designs, S3 bucket configs with Block Public Access plus KMS plus lifecycle, OIDC trust policies for GitHub Actions, and cost optimization plans. Do not invoke for pure GCP, Azure, or on premises work. Hand off Terraform provisioning to `terraform-expert` and Kubernetes manifests to `kubernetes-expert`.
csharp-dotnet-expert
Use when writing, reviewing, or upgrading a C# / .NET application on .NET 8 or .NET 9 (with awareness of .NET 10 LTS). Covers ASP.NET Core minimal APIs and MVC, EF Core 9, dependency injection, `IOptions<T>` configuration, structured logging with `ILogger<T>` and Serilog, OpenTelemetry, Polly resilience, MediatR, FluentValidation, xUnit plus WebApplicationFactory plus Testcontainers, source generators, Native AOT, and modern C# (records, primary constructors, pattern matching, collection expressions, `IAsyncEnumerable`, `Span<T>`). Triggers: C#, csharp, .NET, dotnet, ASP.NET Core, minimal API, record, primary constructor, pattern match, EF Core, Entity Framework, NuGet, Serilog, OpenTelemetry, AOT, xUnit, NUnit, Moq, Polly, MediatR, `Memory`. Produces minimal API endpoints, EF Core DbContexts, migrations, hosted services. Not for language agnostic API contract design across services, see senior-backend-engineer.
django-expert
Use when writing or debugging Django and Django REST Framework: ORM querysets, migrations, signals, admin, async views, Channels, Celery / Dramatiq / RQ tasks, ASGI / WSGI deploys, settings. Covers Django 5.x idioms, `select_related` vs `prefetch_related`, N+1 hunting, `UniqueConstraint` and `CheckConstraint` on `Meta`, DRF ViewSets, serializers, permissions, `RunPython` data migrations, atomic reversible migrations, async view boundaries with `sync_to_async`, Celery `acks_late` and idempotency, bounded context per app, settings split, version upgrade checklists. Triggers: Django, DRF, ORM, queryset, select_related, prefetch_related, signals, Channels, async view, manage.py, makemigrations, Celery, Dramatiq, RQ, gunicorn, uvicorn, ASGI, WSGI. Produces models, ViewSets, serializers, migrations, tasks, settings. Not for cross language API contracts, see `senior-backend-engineer`. Not for query plans, see `postgres-expert`. Not for blank page schema, see `data-modeler`.
flutter-expert
Use for Flutter and Dart work on iOS and Android. Triggers: Flutter, Dart, widget, StatelessWidget, StatefulWidget, BuildContext, Riverpod, Bloc, Provider, GetX, signals, ChangeNotifier, ValueNotifier, FutureBuilder, StreamBuilder, RenderObject, Impeller, Skia, platform channel, MethodChannel, EventChannel, FFI, dart:ffi, pubspec.yaml, melos, flutter_test, integration_test, golden test, flutter_lints, go_router, dio, drift, isar, sqflite, flavors, l10n, slang. Produces widget skeletons with const constructors, Riverpod notifier providers, go_router configs, platform channel scaffolds (Dart plus iOS Swift plus Android Kotlin), golden test setups, and pubspec.yaml with pinned versions and analyzer rules. Anchored to Flutter 3.24 plus (Impeller default on iOS) and Dart 3 sound null safety, records, and patterns. Skip for cross platform decision (route to senior-mobile-engineer), iOS dialect deep dive (swift-ios-expert), or backend API design (senior-backend-engineer).
gcp-expert
Use when the request names GCP, Google Cloud, gcloud, GCE, GKE, Cloud Run, Cloud Functions, BigQuery, Cloud SQL, Spanner, Firestore, AlloyDB, Pub/Sub, Cloud Storage, GCS, VPC, Cloud Load Balancing, IAM, Workload Identity, Workload Identity Federation, Cloud KMS, Secret Manager, Cloud Logging, Cloud Monitoring, Cloud Trace, Cloud Build, Artifact Registry, VPC Service Controls, or Organization Policy. Produces service selection rationale, IAM and project layout, VPC and Cloud NAT topology, Workload Identity Federation trust for CI, BigQuery partition and cluster plans, Cloud Run service skeletons, GCS lifecycle and KMS configuration, and cost guardrails. Do not invoke for AWS, Azure, or non Google Cloud platforms; route those to aws-expert or the relevant cloud skill.
skill-name-here
Use when {trigger verbs}, {artifact nouns}, or {situations}. Produces {outputs}. {Antitrigger if needed, name the better fit skill}.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.