Design and run promptfoo evaluations for LLM behavior regressions or comparisons across prompts, agent rules, and models. Use for repeatable behavioral cases with explicit assertions, not ordinary unit tests or static configuration checks.

Maintain or create PROJECT_STATUS.md files at the repository root with the canonical structure (Executive Summary, Completed Components, In Progress, Next Steps, Known Issues, Notes). Use when starting or finishing work on a project, when the user asks to update or create PROJECT_STATUS.md, when a session involves significant changes that should be reflected in the project status file, or when reviewing project state before committing.

Designs software features collaboratively through visual scenarios and iterative refinement. Use when designing features, tools, UIs, workflows, or any system before implementation.

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

Submit, amend, and review Gerrit changes using git-review CLI. Use when asked to submit a patchset, download a change, rebase a change request, check CR status, or manage code reviews in Gerrit.

How to chart a metrics view with the create_chart tool, which chart type fits which question, and the pitfalls that produce misleading charts

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

用於多步驟 AI 代理工作的持久化檔案規劃。將 task_plan.md、findings.md 與 progress.md 保存在磁碟上，生命週期鉤子會注入選定的專案規劃內容。自動恢復只讀取專案規劃檔案；只有明確執行 session-catchup.py --metadata 才會檢查本機同一專案的代理工作階段中繼資料，--replay 則會輸出有界且以 nonce 框定的摘錄。選用的閘門模式只會在主機支援時要求繼續，而且絕不執行 Markdown 中宣告的命令。此技能沒有網路上傳路徑。適用於研究或需要超過 5 次工具呼叫的工作。觸發詞：任務規劃、專案計畫、制定計畫、分解任務、多步驟規劃、進度追蹤、檔案規劃、幫我規劃、拆解專案

Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it. Use when launching a session that should work in its own worktree.

Recommend the best Cult UI components for a described need, with docs links and install commands.

When the user wants to plan, implement, or optimize referral program strategy. Also use when the user mentions "referral program," "referral marketing," "user referral," "refer-a-friend," "word-of-mouth growth," "referral rewards," "referral tracking," "referral code," "referral incentives," or "viral loop." For referral landing copy, use landing-page-generator.

When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student plan," "for students," ".edu discount," "academic pricing," "student verification," "SheerID," "UNiDAYS," or "education program." For startup pricing page, use startups-page-generator.

When the user wants to plan, implement, or optimize affiliate marketing strategy. Also use when the user mentions "affiliate marketing," "affiliate program strategy," "CPS model," "affiliate recruitment," "commission structure," "affiliate partners," "affiliate network," "affiliate tracking," "affiliate commission," or "partner marketing." For affiliate page, use affiliate-page-generator.

Receive and verify AgentMail webhooks (email inboxes for AI agents). Use when setting up AgentMail webhook handlers, debugging Svix signature verification (svix-id, svix-timestamp, svix-signature, whsec_ secret), deduplicating on event_id, or handling events like message.received, message.sent, message.delivered, message.bounced, message.complained, message.rejected, message.opened, message.security.review, domain.verified and calendar.event.starting.

Use when defining company values, turning them into behaviors, assessing culture health or designing rituals. Treats culture as operating behavior, not posters.

Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and writes a build sheet with build_sheet_builder.py, checked by primitives_validator.py; no API key needed.