End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.

Captures the current session's repeatable process into a reusable SKILL.md skill file by interviewing the user, extracting steps from the conversation, generating YAML frontmatter, and writing structured markdown instructions. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.

Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.

Open-source pipeline: fork, sanitize, and package private projects for safe public release. Chains 3 agents (forker, sanitizer, packager). Triggers: '/opensource', 'open source this', 'make this public', 'prepare for open source'.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.

Develop or review put.io SDK repositories, API clients, and client libraries across TypeScript, Swift, Kotlin, and similar packages. Use when adding or changing namespaces, tightening request or error types, aligning SDK behavior with backend and app usage, updating SDK verification flows, or checking how an SDK repo should be documented and released.

Author, structure, and package new Tessl tiles, skills, and documentation. Use when creating new tiles, authoring new SKILL.md files, writing documentation to be ingested by Tessl, or structuring a tile.json manifest.

Configure custom AI agents (OpenClaw, OpenCode, etc.) to use Tessl by editing agent config files, setting up MCP server connections, installing skills via CLI, and validating Tessl authentication. Use when setting up a new agent, configuring MCP tools, editing mcpServers JSON or opencode.json, troubleshooting connection issues, or enabling Tessl features in an unsupported agent.

Publish, share, update, archive, and unpublish Tessl tiles in the registry. Use when distributing tiles to workspaces, making tiles public or private, managing tile lifecycle, or sharing skills with the team.

Configures and consumes the SonicJS headless CMS REST API — builds API clients, constructs query filters for content endpoints, configures CORS headers, and handles authenticated GET/POST requests with JSON payloads. Use when fetching data from SonicJS endpoints, sending HTTP requests to a SonicJS backend, integrating a frontend with a SonicJS API, creating or retrieving CMS content via fetch, managing CORS for a SonicJS deployment, or building an API client against SonicJS collections.

Configures login flows, implements role-based access control (RBAC), generates JWT tokens, and manages user accounts in SonicJS. Use when configuring login flows, role-based access, permissions, auth, session management, or creating authentication middleware.

Scaffolds new SonicJS routes, configures Drizzle ORM schemas, sets up authentication and RBAC, registers Hono.js plugins, and manages Cloudflare Workers deployment for a SonicJS edge-native headless CMS. Use when creating an API endpoint, adding a content type, configuring a database schema, deploying the CMS to Cloudflare, building or modifying a SonicJS plugin, setting up auth flows, or architecting any part of a SonicJS application backed by Cloudflare Workers, D1, R2, and HTMX.

Rapidly screens batches of 10-50+ startups from pitch events, demo days, or accelerator showcases into investment tiers. Scores startups on traction, team, market size, and differentiation; classifies into 4 priority tiers; validates top candidates via web research; generates tier rankings and shortlist comparison tables. Use for batch deal screening, startup triage, demo day prep, cohort evaluation, or dealflow prioritization.

Configures Supabase Realtime clients with worker:true to prevent background tab disconnections. Implements heartbeat monitoring and reconnection strategies. Use when fixing realtime disconnects, configuring worker-based realtime clients, implementing heartbeat resilience, or handling browser tab WebSocket stability.

Use when writing or reviewing T-SQL, creating stored procedures, designing table schemas, writing views, building migrations, defining custom types, or architecting a SQL Server application database. Also use when writing RAISERROR patterns, CHECK constraints with scalar functions, base/subtype table hierarchies, composite key designs, role-scoped views with row-level security, or idempotent DDL scripts. If you are touching SQL for an application database, use this skill.

Generates micro Flutter/Dart UI components (atoms/molecules) following Atomic Design patterns. Uses StatelessWidget for atoms and HookConsumerWidget for molecules, including form validation classes and auto-generated widget tests with mocktail mocks. Use when the user asks to create small Flutter UI components such as buttons, text fields, inputs, cards, or reusable widgets following Atomic Design principles, or when they need a Flutter atom, molecule, or micro-UI component with Riverpod integration.

Use when the goal is to demo the end-to-end Tessl workflow quickly and reliably. Always ask which workspace to publish to, create a minimal SKILL.md with valid frontmatter, create exactly one simple eval scenario in the expected Tessl format, run skill review on the skill directory, optionally apply one optimization pass, and use publish to trigger evals. Good triggers include "make a demo skill", "scaffold a Tessl skill", "generate one eval scenario", and "show the Tessl flow end to end".

List pending skills and rules on the NAS staging area. Shows what the agent has created or updated that hasn't been promoted to tiles yet. Use before running promote, or when the user asks what's on staging.

Kill a running agent container on the NAS by Telegram group JID. The orchestrator respawns a fresh container on the next message. Does NOT delete registration or group folder. Use when a container is stuck, stale, or needs a fresh start.

Promote agent-created skills and rules from NAS staging to tile GitHub repos via a full PR lifecycle — opens a PR, summons Copilot, iterates fixups until the review is clean, then merges so GHA publishes. Use when there are new items on staging, after check-staging shows pending items, or when asked to deploy skills, push to production, or publish rules to a tile repo.

Check NanoClaw system health — stuck tasks, DB size, task run failures. Uses /workspace/store/messages.db directly. Use as part of heartbeat or standalone. Triggers on "system health", "check tasks", "check database".

Session bootstrap and rolling memory updates for trusted containers. On session start, reads MEMORY.md (permanent facts), RUNBOOK.md (operational workflows), recent daily and weekly logs, and highlights.md to restore context. After non-trivial interactions, appends timestamped entries to group-local and cross-group shared daily logs. Use when starting a new session to load previous notes and remember context, or after meaningful conversations to save conversation history, persist session state, or record newly learned owner preferences.

Generate HTML presentations as self-contained single files with persistent sidebar navigation, scrollable sections, and interactive components. Use this skill when the user wants a polished visual presentation viewable in a browser. Ideal for internal decks, workshop materials, strategy frameworks, and any deliverable that should feel like a premium consulting product — not a generic AI output. Supports Metis branding (default) and client brand extraction from PPTX templates. Triggers on "html slides," "html presentation," "browser deck," or when the user explicitly asks for HTML output instead of PPTX.

Draft Statements of Work (SOWs) from client templates and Metis proposals, and review/redline Master Services Agreements (MSAs) from the Supplier perspective. Use this skill whenever a consultant asks to draft an SOW, populate a client SOW template, review contract terms, redline an MSA, do a risk analysis of a legal agreement, check for scope creep between a proposal and SOW, or prepare legal documents for a consulting engagement. Also triggers for requests involving deliverable tables, invoice schedules, IP carve-outs, indemnification review, or any mention of "SOW", "MSA", "master agreement", "statement of work", "redline", or "contract review" in the context of Metis Strategy client engagements.

Summarize any video by analyzing both audio and visuals. Downloads via yt-dlp, extracts transcript (YouTube captions or Whisper), pulls scene-detected keyframes, and produces a multimodal summary with clickable timestamped YouTube links. Use this skill whenever the user wants to summarize a YouTube video, digest a talk or tutorial, get notes from a video, extract key points from a recording, or says things like "tl;dw", "summarize this video", "what's in this video", or pastes a YouTube URL and asks for a summary. Also triggers for non-YouTube URLs that yt-dlp supports.

Control Slack via CDP or headless API tokens. Navigate channels, read/send messages, search conversations, check unreads, and manage status. Two modes: CDP (Slack desktop with --remote-debugging-port) for full UI control, or headless (xoxp/xoxb token) for data operations without Slack running. Triggers on: slack, read slack, search slack, slack unreads, send slack message, slack status, navigate slack, check slack, slack messages, go to channel, slack DM.