workflows

Clay tables — sweep a table for errored rows and report grouped by root cause (not a specific record). Use when the user asks "what's erroring in {table}?", "show failed rows", or "is {action} failing?".

Clay workflow alerts — use when the user wants to create, inspect, edit, enable, disable, or delete a workflow alert rule, or subscribe themselves to its email notifications.

Keep Clay up to date. Use when the user asks to update or upgrade Clay, the plugin, or the `clay` CLI; when `clay update` reports the CLI is pinned / managed by the plugin; or to check whether a newer version is available. The plugin and CLI update independently; migrate older plugin-managed installs through setup.

Clay tables — explain one cell by walking a column backward through its dependencies and run-gate to the origin or root cause. Use when the user asks "where did this value come from?", "why did {action} error?", "why didn't {action} run?", or "why is this value empty?".

Clay tables — locate a record by identifier and snapshot its state: which table(s) hold it and each cell's status. Use when the user has an id and asks "trace {id}", "where is {id}?", "what enrichments ran for this lead?", or "is this record done?".

Clay tables — check the row-capacity ceiling when imports stall, before assuming a run/config/enrichment problem. Use when the user asks "why aren't new rows being added?", "why is the import stuck?", or "is this table full?".

Clay tables — analyze what a table does: reconstruct the column DAG, stage it, and narrate the workflow encoded in its columns. Use when the user asks "what does this table do?", "explain the {table} workflow", "walk me through this table", or "what's set up here?".

Clay workflows — build enrichment steps and map their results back to Audiences in an existing audience enrichment workflow. Use while editing an audience enrichment workflow or migrating an Audience-backed bulk enrichment table into a workflow.

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。