alexzhu0

deck-to-agent-kb

Use when converting slide decks, PPT notes, exported screenshots, or mixed enterprise presentation material into an agent-queryable knowledge base with evidence, risks, actions, and answer boundaries.

Code & Development Listed

agent-skill-lint-review

Use when reviewing an agent Skill or SKILL.md draft before publishing to check trigger clarity, scope, safety boundaries, progressive disclosure, validation, and publish readiness.

agent-trace-debugger

Use when summarizing AI-agent traces, JSONL logs, tool-call transcripts, retries, or execution histories into a failure timeline, root-cause candidates, and retry recommendations.

devtool-launch-pack

Use when preparing a small AI developer tool or agent utility repository for public launch with README clarity, GitHub topics, release notes, launch copy, and first issue ideas.

eval-case-miner

Use when converting bugs, user complaints, support tickets, logs, bad model outputs, or incident notes into reusable evaluation cases with inputs, expected behavior, assertions, and tags.

llm-cost-risk-review

Use when reviewing prompts, context bundles, agent workflows, or LLM product flows for token cost, latency risk, context bloat, repeated instructions, and budget guardrails.

mcp-server-evaluator

Use when comparing MCP servers, tool connectors, plugin capabilities, or agent integrations by capability, auth needs, trust boundary, maintenance risk, and integration fit.

meeting-to-action-brief

Use when turning meeting notes, transcripts, chat summaries, or call fragments into a concise action brief with decisions, owners, deadlines, blockers, evidence, and follow-up prompts.

prompt-drift-review

Use when reviewing changes to prompts, system instructions, AGENTS.md files, safety policies, agent rules, or workflow instructions for behavior drift and missing regression checks.

repo-to-agent-context

Use before coding-agent implementation work to compress a repository into a concise context brief covering project purpose, layout, entrypoints, dependencies, tests, risks, and first commands.

agent-handoff-brief

Use when handing work from one AI agent, developer, or session to another by summarizing current state, files touched, decisions made, blockers, verification, and next safe actions.

API & Backend Listed

api-doc-to-tool-spec

Use when converting API documentation, endpoint notes, OpenAPI snippets, or integration docs into an agent-ready tool specification with capabilities, inputs, auth, examples, and operational risks.

architecture-rfc-review

Use when reviewing architecture RFCs, system design docs, diagrams, proposals, or technical decision records for tradeoffs, missing constraints, risk, and decision readiness.

Data & Documents Listed

bug-report-to-repro

Use when converting bug reports, user complaints, screenshots, logs, or QA notes into a reproducible case with environment, steps, expected behavior, actual behavior, and missing evidence.

changelog-to-upgrade-plan

Use when reviewing changelogs, release notes, migration guides, or dependency announcements to create a practical upgrade plan with impact, tests, rollback, and owner-ready tasks.

competitive-research-brief

Use when summarizing competitor research, product pages, feature comparisons, sales notes, or market observations into a concise brief with positioning, gaps, claims, and watch items.

customer-call-to-prd

Use when converting customer call notes, interview transcripts, sales discovery notes, or PM research fragments into a concise PRD with user problems, requirements, non-goals, and risks.

API & Backend Listed

database-migration-risk-review

Use when reviewing schema migrations, SQL changes, data backfills, index changes, or rollout plans for data loss risk, locking, rollback gaps, validation checks, and production safety.

Code & Development Listed

dependency-upgrade-risk-review

Use when reviewing dependency upgrades, package-lock diffs, SDK version changes, release notes, or migration guides for breaking changes, security impact, tests, and rollout risk.

messy-notes-to-decision-log

Use when turning rough notes, chat dumps, meeting fragments, scratch documents, or mixed planning material into a decision log with evidence, owners, dates, and unresolved questions.

privacy-data-flow-map

Use when mapping product flows, event tracking, forms, integrations, or agent workflows into a privacy data-flow map covering collected data, purpose, retention, sharing, consent, and risk.

prompt-to-eval-rubric

Use when converting prompts, system instructions, assistant behaviors, or policy requirements into eval rubrics with scoring criteria, test cases, assertions, and failure modes.

repo-launch-readiness-review

Use when reviewing a small repository before public launch for README clarity, examples, license, metadata, validation commands, issue hygiene, release notes, and obvious trust gaps.

roadmap-to-release-plan

Use when converting roadmap notes, feature lists, planning docs, or backlog themes into a release plan with milestones, scope, dependencies, rollout phases, and validation checks.

security-review-checklist

Use when reviewing feature specs, tool integrations, agent workflows, API changes, or launch plans for security concerns such as auth, secrets, data exposure, abuse paths, and approval gates.

support-ticket-to-eval

Use when turning support tickets, user complaints, helpdesk transcripts, or failed assistant responses into reusable eval cases with expected behavior, assertions, and failure modes.

telemetry-to-product-insights

Use when reviewing product telemetry, funnel notes, event exports, dashboard screenshots, or metric summaries to produce grounded insights, hypotheses, experiments, and data caveats.

tool-permission-audit

Use when auditing AI-agent tool permissions, command policies, connector access, GitHub actions, file-system scopes, or automation rules for risk, approval gates, and least-privilege controls.

workflow-automation-scout

Use when reviewing repeated manual processes, team workflows, operational checklists, or task logs to identify automation candidates, required inputs, ROI, risks, and human approval points.