catalog

Write and maintain architecture docs — the documents that say what each system is, where it runs, what it depends on, and the real names of things (cloud projects, clusters, namespaces, hostnames, buckets). The heart of it is an interview that pins down what each system name actually means before anything is written. Use when asked to write, extend or improve architecture documentation, to document a system, or to fill a gap the `architecture` skill could not answer.

Answer questions about how the organisation's own systems are built and run — what a system is, who owns it, where it runs, what it depends on and what depends on it, and the real names of things (clusters, hostnames, queues, buckets, repos) — from architecture docs, the catalog and past incidents. Use whenever a question is about a specific system or piece of infrastructure: "what is X", "what breaks if X goes down", "where does X run", "do we have docs on X", or grounding a component before debugging it.

Review the health of your incident.io agent estate — plugins, skills, connections — and say what to fix, without fixing anything itself. Use whenever anyone asks whether their incident.io setup is healthy, what's degraded, or what to improve, in any phrasing — one-off or as a recurring review. Every finding routes to the thing that fixes it.

Set up, explain and troubleshoot incident.io extensions: the plugins of skills and the connectors (MCP servers, HTTP APIs) that give incident.io's agents an organisation's own knowledge and tools. Use whenever you're working with incident.io plugins, skills, connectors or the extension_ tools in any way, including why one isn't working: a skill that never loads, a change that wasn't picked up, a sync error, a connector tool investigations won't call, whether a skill is used or helping. Not for questions about the organisation's own systems, which the architecture skill answers.

Reading and changing incidents in incident.io: status, severity, roles, fields, updates, channel messages and the AI investigation. Use whenever you're working with an incident in any way, even a single read or change. Load it before the first incident, update, follow-up or investigation tool call: the tools accept changes the organisation's rules then reject, and this skill says what to check first. Not for fleet-wide statistics, runbooks or who is on call.

Who is on call in incident.io and how they get paged: schedules, rotas and shifts, overrides, cover requests, escalation paths, and pages (escalations). Use whenever you're working with any of these in any way, including plain reads ("who's on call tonight?", "when am I next on?") and paging ("page Ava", "ack my page", "has anyone acked?"). Load it before the first schedule, escalation or cover-request tool call: the tools return raw shifts and levels, and this skill says how to read them.

Work with an incident's postmortem document — the write-up a team produces after an incident. Use when the conversation is about a postmortem, post-incident review, debrief or retro document: finding it, creating one, reading it, changing its text, or reviewing it against what actually happened. Covers rewriting a section, fixing a claim, adding a timeline entry or a learning, and also judging whether its claims hold up, what is missing, and what should become a follow-up. Not for general questions about an incident, which is the incidents skill.

Create and improve the skills in your own plugins — the ones incident.io's agents and your coding agents load. Use whenever you're writing, editing, or reviewing a skill in any way: creating one, improving one from usage feedback or a review brief, or asking what makes a good skill.

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。