debug-replay

Deep-dives into specific AI agent sessions or failure patterns to explain why something went wrong. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when investigating a specific session ID, debugging agent failures, understanding why quality is low, tracing tool errors, or when monitor-ai-quality surfaces an issue that needs root cause analysis.

Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.

Monitors AI agent health across quality, cost, performance, and errors. Only use when the user has Amplitude Agent Analytics instrumented in their project. Use when the user asks "how are our AI agents doing", "AI quality check", "agent health", "AI errors", "agent performance", "LLM cost", or wants a proactive health report on their AI/LLM features.

Lists projects for an employee-accessible organization or writes organization/project AI context with `manage_amp_context`; use `get_amplitude_context` for reads.

Investigates live product issues against Amplitude data — "is X firing today", "did the release break Y", "which users are affected by Z". Covers the verify-then-query loop, query_amplitude_data parameterization, and its common failure modes. Use for incident analysis, instrumentation checks, and affected-user discovery.

Creates, edits, and archives Amplitude Guides and Surveys through `run_amp`, including step content blocks, buttons, and survey questions. Use before changing a guide's or survey's copy, steps, questions, buttons, targeting, or settings.

Given a change_brief YAML (output from diff-intake), generates an exhaustive list of candidate analytics events to instrument. Takes the perspective of an engineer with a PM mindset — surfaces everything worth considering so a PM can decide what actually matters. Use this as step 2 of the analytics instrumentation workflow, immediately after diff-intake produces a change_brief. Trigger whenever a user has a change_brief YAML and wants to know what analytics events to add, or asks "what should I track for this PR", "what events should I instrument", "generate event candidates", or any request to surface analytics coverage gaps for a code change.

Discovers product opportunities by analyzing Amplitude analytics, experiments, session replays, and customer feedback. Synthesizes evidence into prioritized, actionable opportunities with RICE scoring. Use when the user asks to "find opportunities", "what should we build", "where are we losing users", "product gaps", or wants a data-driven backlog of improvements.

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.

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。

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.