bulk

Diagnose existing Spotify Ads Pixel, Conversions API (CAPI), and dataset implementations when events are missing, stale, duplicated, unexpectedly high or low, not deduplicated, attached to the wrong account, or present in diagnostics but absent from campaign reporting. Use for Pixel/CAPI troubleshooting, event-delivery audits, token/connection mismatches, source comparison, or measurement incident triage. Prefer read-only checks and never create test conversions without explicit confirmation.

Configure Spotify Ads API credentials via OAuth 2.0 with PKCE or a direct token. Sets up authentication, ad account, and execution preferences.

Quick performance overview of all active Spotify ad campaigns — impressions, spend, reach, clicks, and pacing at a glance.

Default write workflow for Spotify Ads API campaigns, ad sets, and ads. Stage new entities or changes to published entities as drafts, validate them, and publish only after explicit confirmation. Use for create, change, update, adjust, fix, pause, resume, archive, creative, tracking, or other campaign-hierarchy writes even when the user does not say draft.

Export Spotify Ads API campaign data to CSV — full campaign hierarchies with ad sets, ads, targeting, budgets, and performance metrics for offline review, campaign analysis, or budget reconciliation.

Turn advertiser or third-party media plans from spreadsheets, CSVs, PDFs, documents, presentations, or text into a source-traceable Spotify Ads implementation plan, enrich and forecast it with live Ads API data when available, resolve or explicitly defer gaps, obtain review approval, and then create a validated draft campaign hierarchy. Use for media plans, planning grids, insertion-order worksheets, or cross-channel plans that need to become Spotify drafts. Never publish.

Pull Spotify Ads API reporting data — aggregate metrics, audience insights, or async CSV reports.

Check Spotify Ads API campaign health — pacing, delivery issues, budget burn rate, stalled campaigns, and underpacing alerts. Use for one-shot health checks or recurring monitoring when the host supports scheduled automations.

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。