win-loss-review

Guide for developing monday.com platform API tools in the agent-toolkit package. Use when creating, modifying, or debugging tools in packages/agent-toolkit/src/core/tools/platform-api-tools/, working with GraphQL queries, or adding new MCP tools to the toolkit.

Analyze CRM activity data — rep performance, call and email volume, team activity breakdowns, and engagement stats. Use when someone says "how many calls did the team make", "show me rep activity", "who's the most active rep", "activity breakdown this week", "how is the team performing", "what's our outreach volume", "compare rep activity", "call stats", "email volume by rep", "activity report", or "team engagement stats". For team, rep or account-wide totals; not for one item's activity history (use log-activity) or sequence performance (use run-sequence).

Set up, view, and manage automations on monday CRM boards using natural language — no block IDs or technical knowledge required. Use when someone says "set up an automation", "automate this", "when a deal is won notify me", "remind me when a date passes", "move deals automatically", "what automations do I have", "turn off automation", "create a workflow", "automate my pipeline", or "set up a rule". Not for multi-step email or outreach sequences (use run-sequence).

Prioritized CRM briefing for today — what needs attention now across deals, contacts, accounts or leads, with tasks due today, deals closing or slipping, contacts going cold, and a summary of recent meetings and activity. Works on any monday CRM setup, or with no board at all. Use when someone says 'morning briefing', 'daily brief', 'what's on my plate today', 'catch me up on my deals', 'what needs my attention', 'anything urgent in my deals', 'what should I focus on today', 'start my day', or 'daily standup prep'. Not for period forecasts or commit-vs-best-case views (use forecast).

Check your CRM board's health and clean up messy data — run a scored health check (missing fields, stalled deals, abandoned columns, automation gaps) as a report, or fix data in bulk (phone formats, missing emails, country codes, unowned deals, stale dates). Use when someone says "clean my CRM", "fix my data", "normalize my phone numbers", "fill in missing owners", "run a board health check", "audit my CRM board", "what's broken in my CRM", "what are the data gaps on my board", "board is messy", or "clean up before my kickoff call".

Build a forecast dashboard in monday — committed, best-case, and pipeline views by close month, rendered as real dashboard widgets. Use when someone says "build me a forecast", "show me Q2 pipeline", "Salesforce-style forecast", "forecast dashboard", "commit vs best-case", "what's our number this quarter", "how are we tracking to quota", "weighted pipeline", "deal rollup", "Clari-style", "pipeline by month", "pipeline summary", or "what's in commit". For views by period; not for today's priorities or what needs attention now (use daily-briefing).

Log one call, meeting or note that the user describes onto a single CRM item's timeline, read that item's activity history, or add a correction. Use when someone says "log my call with", "add a note to the deal", "record this meeting with", "log a meeting with", "track a call with", "I just spoke with", "I just had a call with", "note on the account", "what activities happened on this deal", "what's the activity history for", "correct the activity I logged", or "add to my note on". Not for turning recorded Notetaker meetings or pasted transcripts into deal recaps (use meeting-to-deal), and not for team or rep activity totals (use activity-insights).

Turn recorded monday Notetaker meetings (or a pasted transcript) into deal recaps — key points, commitments and next steps posted as updates on the matching CRM deals (confirmed per your mode), with optional stage edits and new contacts for unknown attendees. Use when someone says "log my recorded meetings to deals", "sync notetaker", "update CRM from my recorded calls", "add notes from my Notetaker meetings", "update my deals from this transcript", "what did I commit to in meetings", or "what did I promise in yesterday's calls". Not for dictating a single call or note onto one item (use log-activity).

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。