ryan-brosas
UserGlobal skill catalog and configuration baseline for AI coding agent CLIs (pi, Claude Code, Codex, OpenCode, Gemini): skills, templates, gates, and policy.
Categories
Indexed Skills (50)
app-experience-mapping
Use when mapping an app's user journeys, touchpoints, channels, and service seams before building, shipping, or changing it, to define hypotheses and measurable outcomes.
black-box-experience-review
Use when reviewing an app as a black box for observable experience failures across journeys, seams, states, and recovery before shipping or after changes.
cdp
Use when the user wants to automate, script, or inspect a Chromium-based browser through the DevTools Protocol. Runs JS snippets through the browser-harness-js CLI against a persistent CDP session: session, targets, and globals survive across calls; attach to a running browser or launch one with --remote-debugging-port.
aeo-affiliate-skills-foundation
Use when porting agent skill-collection machinery from aeo-affiliate-skills — CLI-supervised localhost daemons with three-tier liveness reuse, idle self-shutdown lifecycle, TTL cache key namespacing, wide-page client-side filter adapters, markdown-corpus→registry generation coupled to invariant tests, executable documentation vocabulary contracts, pattern-grep skill eval harnesses, and agent-facing self-install bootstrap skills.
aeo-elmo-foundation
Use when building AI-visibility (AEO/GEO) tracking: multi-provider answer-engine adapters, citation extraction from raw LLM/scraper payloads, mention-based Share of Voice, history-metered per-target scheduling with failure backoff + maintenance self-healing, and encrypted credential storage.
affine-foundation
Use when porting CRDT sync loops, offline-first storage ladders, or block-editor data layers — AFFiNE local-first collaboration stack: Yjs sync engine (DocEngine/SyncPeer), reactive block store (stash/pop, flat Y.Map proxies, schema globs), and production doc-sync job kernel with clock-map dedup.
agency-swarm-foundation
Use when porting multi-agent orchestration machinery from agency-swarm: synchronous send-message bus, per-agent tool concurrency guards, flow-wiring validation, runtime subagent registries, flat thread stores with pair-scoped history, guardrail retry loops, handoff reminders, deferred OAuth MCP activation, loop-affine proxies, fake-id stream normalization.
agent-s-foundation
Use when porting screenshot-driven computer-use agents — grounding-model coordinate generation, eval-based grounded-action execution, code-agent delegation with step budgets, behavior-narrator trajectory annotation, or Best-of-N comparative judging.
agentic-seo-skill-foundation
Use when porting deterministic SEO/AEO/GEO audit machinery — SSRF-safe fetchers, robots/llms.txt evaluation, JSON-LD schema validation and generation, snippet-format scanning, E-E-A-T/freshness/citation content scoring, GSC decay/striking-distance tracking, AI-crawler policy matrices, authenticated GitHub repository-trust audits (provider fallback, rate-limit-aware retries, release/file-inventory scoring), the standalone-script runtime plane (non-raising fetch envelope, stdlib dotenv ladder, CLI output contract), or the orchestration pattern of an 88-script evidence layer under an LLM-first router.
agno-foundation
Use when building or porting an agent framework runtime — the single-agent run loop with retries/cancellation/HITL pauses/approvals and conversation time-travel (continue/fork/regenerate), model provider fallback and retry-with-guidance, OR the multi-agent layer: a supervisor/team-leader loop over member agents, an autonomous shared-task-list mode, tool routing for the leader model, cooperative run cancellation with cancel-before-start support, and HITL pause propagation from members to teams. Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.
ai-foundation
Use when building LLM abstractions or chat/agent UIs: agent step loops with approval replay, typed output envelopes, history round-tripping, tool-drift fingerprints, stream shims, useChat/useObject hook state machines, RSC streamable value/UI protocols, and schema normalization.
aider-foundation
Use when building AI pair-programming harnesses: token-bounded repository context, repairable edits, explicit file and consent gates, plan-to-edit handoff, diagnostic feedback, provider policy, and scoped Git safety.
airflow-foundation
Use when porting Airflow scheduler and triggerer foundation — HA task queueing, executor reconciliation, retry/timeout ladders, orphan adoption, deferred-task lifecycle.
aliasvault-foundation
Use when porting AliasVault's E2E-encrypted vault patterns — SRP wire-format auth, LWW merge-to-SQL core, append-only vault revisions, and zero-knowledge client planes.
analytics-foundation
Use when porting or debugging privacy-analytics engine internals — ClickHouse query planning with table partitioning and subquery joins, session metric sign arithmetic, timeSlots smearing, goal array-index joins, filter-to-SQL compilation, batched RowBinary ingestion, per-user serialization, comparison-period arithmetic, or tracker engagement protocol.
appflowy-foundation
Use when porting AppFlowy's offline-first sync kernels — assembling CRDT objects with disk persistence and cloud sync, routing typed events across an FFI boundary, running QoS background task queues, reconnecting realtime sockets, or implementing a local server that satisfies cloud traits without a backend.
autogen-foundation
Use when porting multi-agent orchestration machinery from Microsoft AutoGen (Python): single-queue envelope runtime, topic/subscription message bus, intervention hooks at dequeue time, group-chat supervisor loops (round-robin, LLM selector, swarm handoff, DAG graph flow), FIFO ordered delivery, termination algebra, run/stream lifecycle, bounded agent tool-call loops, RPC cancellation/failure ladders, name-keyed team checkpointing, middle-out token-budget contexts, mutate-and-report memory injection, subprocess executor timeout/cancel exit codes, grpc worker/host registration handshake with request-id correlation and disconnect cleanup, streamed tool-call workbenches, and pluggable model-context recall strategies.
awaithumans-foundation
Use when building human-in-the-loop (HITL) async agent workflows: long-poll reconnect loop, schema-driven form inference, magic-link action tokens, HKDF key separation, and idempotent task lifecycle.
awesome-guidelines
Use when a practices leaf or question points at a specific awesome-guidelines style capsule or learning note - archived cold library; the ingestion pipeline is retired, so load only to read a cited capsule.
baserow-foundation
Use when porting Baserow's dynamic-schema kernel: per-user-table Postgres DDL, runtime Django model generation, versioned model caching, link-row twin relations, and MVCC-safe reads beside live ALTERs.
billion-context-pi-foundation
Use when building long-context agent delegation and context management: per-turn context transforms, message-range compression, async subagent delegation, watchdogs, tool guardrails.
biome-foundation
Use when building linters/formatters/language tooling: lossless CSTs with green/red splits, flat formatter IRs with best-fitting printing, rule engines with lazy diagnostics and positional suppressions, and event-stream parser drivers with buffered lookahead, speculative disambiguation, and marker-surgery recovery.
browser-harness-foundation
Use when building browser automation tooling: a CDP daemon that attaches to a real browser, high-level page helpers, action recording, and video composition — plus the IPC/auth/telemetry/self-heal plumbing around such a daemon.
browser-harness-js-foundation
Use when building a thin CDP/WebSocket bridge for browser agents: persistent eval daemon, target routing, a11y-tree compression and locators, consent-gated privacy-scrubbed action recording, hash-sealed evidence videos, and zero-dependency skill CLIs.
browser-use-foundation
Use when building an LLM-driven browser agent: event-bus sessions, watchdog self-healing, DOM serialization to stable indices, schema-enforced action registries with secret redaction, and cache-friendly prompt assembly.
bruno-foundation
Use when building API-client cores: TLS agent caching with LRU eviction, OAuth2 grant ladders + encrypted token vaults, PAC/system proxy resolution, cookie-jar wrappers, WebSocket connection FSMs, sandboxed expression interpolation.
camel-foundation
Use when porting CAMEL-AI multi-agent workforce orchestration foundation — supervisor decomposition, task bus, coordinator routing, agent pooling, quality gates.
cap-foundation
Use when building a screen-recording pipeline: multi-track studio recording actor (pause/resume segmented), crash-safe fragmented MP4 recovery with manifest ladders, browser MediaRecorder spooling, streaming multipart upload with uncertain-completion semantics, getDisplayMedia retry ladders, and VFR-safe duration/sync invariants.
celery-foundation
Use when building a distributed task queue or job worker: at-least-once ack/reject semantics across early/late modes, retry ladders (manual Task.retry, autoretry wrapper, exponential backoff with full jitter), prefork pool with event-loop time limits, bootstep blueprint startup/shutdown graphs, broker reconnect loops, ETA/countdown timers, beat's reentrant heap scheduler with crontab DST math, gossip worker elections, and mailbox-based remote control.
changedetection-foundation
Use when building watch/recheck schedulers, polite pollers, or any multi-worker job fleet — reusable contracts from changedetection.io (Apache-2.0): epoch-priority recheck queue, claim-then-defer UUID mutex, ticker scheduler gate ladder, timezone-pinned schedule windows, per-worker event-loop fleet with health self-repair, quiescence protocol, and memory-hygiene cleanup.
chatwoot-foundation
Use when porting Chatwoot-style multi-tenant SaaS mechanics — account-scoped event fanout to per-account webhook subscriptions, HMAC-signed outbound webhook delivery with retry classification, Redis round-robin agent assignment with row-lock race discipline, API-token tenant resolution with bot endpoint allowlists, bit-packed feature flags, and editor-markdown webhook payload hygiene.
chroma-foundation
Use when porting Chroma embedded vector database internals — HNSW segment engine, layered brute-force batches, SQL metadata filter planner, SQLite WAL queue, and the Rust MaxScore/SPANN/HNSW-provider engine.
cline-foundation
Use when porting Cline's agentic-runtime core — context compaction (trigger budget, overflow-recovery ladder, safe cuts, no-LLM fold), compaction state projection with prefix hashes, runtime safety (loop detection, mistake tracker), pending-prompt steer/queue gate, local hub-daemon transport plane (discovery record, mkdir-lock mutex, ensure/retire ladders, WS envelope, subscription refcounts), claim-once env sentinels with supervised-child restart/adoption, hub command router (authority/drain gates, degraded replies), monotonic shutdown coordination, disk-truth cron reconciliation, agenda task persistence kernel (run-admission gates, exactly-once terminals, crash triage, revision+content-hash CAS), strict/tolerant Markdown intent grammars, location containment, todo-tool scope gate, workspace file-index TTL worker, @mention budget matching, ACP stdio bridge (stdio hygiene, fail-closed permissions, streaming/replay, session lifecycle, config options). Source code and direct tests are ground truth.
codebase-memory-mcp-foundation
Use when porting codebase-memory-mcp's C internals: SQLite graph store pragmas/integrity/quarantine, atomic publish pipeline, incremental closure routing, MCP server surface (TOON, profiles, cancellation), daemon rendezvous/version-cohort IPC, watcher/supervisor resilience, or the foundation allocator/lock/log primitives.
codedb-foundation
Use when building or porting codedb-style code-intelligence search engines — typo-substring trigram indexes with bloom pruning, inverted word indexes with BM25+ ranking, content-defined n-gram indexes, mmap zero-copy persistence, deterministic call/import graphs, generation-safe result caches, and tiered recall ladders for agent context tools. Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.
android-coding-practices
Use when authoring or reviewing Android apps, ribot/xmartlabs resource naming, component factories, Java/Kotlin conventions, MVP/Jetpack layering, and lint/detekt/tests in CI.
angular-coding-practices
Use when authoring or reviewing Angular apps, kebab-case files, feature folders, inject(), readonly inputs, protected template members, class/style bindings, selector prefixes, and angular-eslint verification.
api-and-interface-design
Use when designing or reviewing REST/GraphQL APIs, SDK interfaces, or public module boundaries; choose contracts, failure semantics, and compatibility from consumer needs and project conventions.
arduino-coding-practices
Use when authoring or reviewing Arduino libraries/sketches, camelCase read/write/begin API,.h/.cpp structure, setup/loop lifecycle, Stream-aware serial, keywords/examples, and arduino-cli compile verify.
brainstorming
Use when a rough idea needs clarification before implementation, resolve ambiguous direction by grounding in what exists, framing the problem, exploring real alternatives, and deciding.
cloudflare
Use when deploying to or configuring ANY Cloudflare service, Workers, Pages, KV, D1, R2, AI, Tunnel, WAF. MUST load before writing Cloudflare Workers code, wrangler configs, or infrastructure-as-code for Cloudflare.
code-cleanup
Use when behavior works but the diff is noisy, repetitive, over-complicated, or AI-shaped - lock behavior first, simplify the changed code, and re-verify without expanding scope.
code-discipline
Use when implementing, reviewing, or committing code, general code-discipline principles (scope, verification, type-safety, tests, context-gathering) farmed from high-quality repos.
code-review-and-quality
Use when reviewing code or PRs before merge, after subagent work, or when a review is requested. Bloat Review mode hunts over-engineering only, with a delete-list and tagged findings.
codebase-memory
Use when navigating, indexing, tracing, or comparing local and inspiration repositories through the Codebase Memory MCP knowledge graph.
coderabbit-review
Use when CodeRabbit CLI review is explicitly requested; scope the external review, inspect current CLI capabilities, and validate findings without replacing the project’s PR workflow.
agent-code-quality-gate
Use when a coding agent claims implementation work is complete - an operational gate over scope, duplication, behavior tests, verification evidence, and regressions.
c-coding-practices
Use when authoring or reviewing C, snake_case naming, header guards, no data in headers, Yoda comparisons, safe macros, initialize-all, and checked error returns.
clojure-coding-practices
Use when authoring or reviewing Clojure, 2-space layout, gathered parens, sorted ns requires, lisp-case naming,?/! conventions, threading idioms, keyword maps, ex-info errors, and clj-kondo/cljfmt in CI.
api-design-practices
Use when an existing caller selects this legacy HTTP/JSON API entry; forward to the canonical API owner without introducing a second policy.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.