gathering-architecture-requirements

Execution skill. Use when configuring an application calendar — choosing calendar type, fiscal year, date range, and time dimensions.

Planning skill. Supply chain use cases: demand planning, inventory management, procurement planning, S&OP alignment. Each use case has inline guidance.

Planning skill. Sales performance use cases: quota planning, commission calculations, territory assignment, attainment tracking, pipeline coverage. Each use case has inline guidance.

Planning skill. FP&A use cases: budget/expense planning, revenue forecasting, P&L reporting, multi-currency, financial consolidation. Each use case has inline guidance; load sub-files only for advanced patterns.

Execution skill. Use when sharing metrics or lists between Pigment Applications via Libraries and cross-Application formula references.

Execution skill. Use when investigating slow inputs, slow calculations, or timeouts with the Performance Insights tools (performance_profile_change, performance_profile_change_scope_details, performance_slowest_changes, performance_changes_statistics, get_top_blocks_by_performance). Covers which tool to call, the includeAllExecutions default, reading change profiles (X/Y scope, contention, impacted viewed data), drilling into the scoped dimensions of some executions, locating the bottleneck, and comparing timings before/after a fix. Always profile before formula changes; never optimize from assumptions.

Execution skill. Use when writing PREVIOUS, PREVIOUSOF, or PREVIOUSBASE formulas, configuring iterative calculation cycles, or debugging circular dependency errors.

Execution skill. Use when naming or organizing Pigment Applications, folders, and blocks so models stay navigable, formula-safe, and consistent across teams.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

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

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。