抓取 GitHub 上 star 涨得最快的项目（Trending 榜），打分标注是否与研究方向相关， 生成 Obsidian 笔记到 GitHubTrending 文件夹。默认周榜。 触发词："GitHub 周榜"、"star 涨得最快"、"过去一周 GitHub 热门"、"GitHub trending"、 "看看这周 GitHub 上火了什么"、"GitHub 日榜"、"GitHub 月榜"

Plan, capture, edit, and visually QA short product demo recordings for docs, releases, and integration walkthroughs. Use when recording or replacing browser/app videos such as n8n or Node-RED flows; not for general-purpose video production.

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

Answer questions about the GM Farcaster podcast archive (Farcaster, Base, and the wider crypto-social ecosystem) using the paid Warpee Knowledge API. Use this when the user asks what the GM Farcaster hosts or guests have said on a topic, wants an episode summary, asks about casts featured on the show, mentions of a person/project, or episode metadata (dates, hosts, guests). Each query is a paid x402 request (~$0.005 USDC on Base).

Migrate an existing Django auth API from dj-rest-auth to django-modern-rest, moving account flows onto django-allauth headless and rebuilding the transport layer with dmr controllers and auth classes. Use when replacing dj_rest_auth login/logout/registration/password/MFA/social views and their DRF serializers.

Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.

Create a GitHub pull request from current working changes. Handles all git states - uncommitted changes, no branch, unpushed commits, etc. Analyzes diffs and changesets to generate a PR with filled-in template. Opens the PR in the browser when done. Use when the user asks to create a PR, open a PR, submit changes, or push for review.

Implement @data-client Managers for global/background side effects - websocket, SSE, polling, real-time updates, subscriptions, logging, analytics, metrics/timing, error reporting (Sentry), toast notifications, refetch on window focus or network reconnect, cross-tab sync (BroadcastChannel), offline persistence (localStorage/IndexedDB), auth logout on 401, middleware, intercepting Controller actions, DataProvider managers prop, redux-style action handling. Use when adding cross-cutting store behavior, reacting to dispatched actions, or handling external event streams.

Migrate workloads from Microsoft Azure to AWS. Triggers on: migrate from Azure, Azure to AWS, move off Azure, migrate AKS to EKS, migrate App Service or Azure VMs to AWS compute, migrate Azure SQL or Azure Database to RDS, migrate Cosmos DB to DynamoDB, migrate Azure OpenAI to Bedrock, move Azure AI or agentic workloads to AWS, estimate AWS costs for my Azure infrastructure, what-if workshop. Runs a 6-phase process: discover Azure resources from Terraform, the live `az` CLI, app code, and billing exports, then clarify, design, estimate costs, optionally reprice scenarios, generate artifacts, and collect feedback. Clarify gates Design, Estimate, and Generate; Generate is opt-in at the post-Estimate decision gate. Bicep/ARM discovery is not yet implemented; a Bicep/ARM-only workspace halts. Do not use for: GCP migrations (see gcp-to-aws), Heroku migrations (see heroku-to-aws), general AWS architecture advice (see architect-for-startups), AWS-to-Azure reverse migration, or Azure-to-Azure refactoring.

Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my review", "fetch GitHub review requests", or "check team review queue".

Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Generate structured PR descriptions from diffs, add review checklists, risk assessments, and test coverage summaries. Use when the user says "write a PR description", "improve this PR", "summarize my changes", "PR review", "pull request", or asks to document a diff for reviewers.

Execute a strict Red-Green-Refactor TDD cycle for one requirement at a time while applying KISS and DRY. Use when the user provides a business rule, acceptance criterion, bug fix, or feature requirement and wants test-first development, behavioral tests, failing tests first, TDD, red-green-refactor, or high-quality code. Works for unit, integration, UI component, API, and CLI tests across stacks.

Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq, spatial data, clinical diagnosis, or workflows that require the original hosted CIBERSORT web service.

Generates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake (syllabus input format + course audience + year range) plus a grouping forcing-options checkpoint before any search runs — so the reading list matches the course's level and recency need. Parses the syllabus to extract topics and learning outcomes, searches Consensus for recent peer-reviewed papers per topic, and produces a professionally formatted .docx with clickable Consensus links, plain-language summaries calibrated to audience level, and Bloom-higher-order discussion questions tied to course learning goals. Use when the user uploads a syllabus, course outline, or curriculum document and wants supplementary readings (e.g., 'create a reading list from this syllabus', 'find recent papers for my course') — even casual mentions with a syllabus attached should trigger this skill.

Use when reviewing a specific inbound deal before close — when sales has asked for a discount that exceeds AE authority, when the customer has redlined the MSA, when per-deal economics (margin after discount, multi-year payment shape, indemnity exposure) need to be quantified, or when discount approval needs to be routed to a named human approver (Sales Director, VP Sales, CFO, CRO, General Counsel). Covers deal review, discount approval routing, per-deal margin scoring, deal exception handling, MSA redline triage, contract landmine detection (uncapped indemnity, MFN, perpetual license-back, missing DPA), and named-approver chain assembly. NEVER auto-approves — every output is a numeric scorecard plus a routing recommendation to a named human.