Skills directory · page 37

Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.

Generate a structural architecture overview of a codebase: languages, package map, entry points, dependency graph, and hotspots. One call for the big picture.

Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.

Three-tier documentation lookup for any symbol — hover → offline toolchain doc → source definition. Use when hover text is absent, insufficient, or the symbol is in an unindexed dependency.

End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.

Find and run the tests that cover a source file. Use after editing a file to discover exactly which test files and test functions need to run — without running the entire test suite.

Use when the user asks to generate images via the Luma AI API (Dream Machine / Photon); collects a prompt and options interactively, then calls the API using the bundled script. Requires LUMA_API_KEY — will prompt the user if missing.

Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI. Trigger on intents such as "evaluate my agent", "test my agent", "run my evals", "create eval prompts", "add multi-turn tests", "tune evaluator thresholds", "why is my agent failing", or "set up eval environment variables".

Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, AgentApplication routing, and MSAL-based auth. Triggers: "Microsoft 365 Agents SDK", "Microsoft.Agents", "AddAgentApplicationOptions", "AgentApplication", "AddAgentAspNetAuthentication", "Copilot Studio client", "IAgentHttpAdapter".

Microsoft 365 Agents SDK for Python. Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based auth. Triggers: "Microsoft 365 Agents SDK", "microsoft_agents", "AgentApplication", "start_agent_process", "TurnContext", "Copilot Studio client", "CloudAdapter".

Microsoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication routing, Express hosting, streaming responses, and Copilot Studio client integration. Triggers: "Microsoft 365 Agents SDK", "@microsoft/agents-hosting", "AgentApplication", "startServer", "streamingResponse", "Copilot Studio client", "@microsoft/agents-copilotstudio-client".

Inspect and operate the independent Microsoft 365 Copilot desktop app through local CDP: discover exact model labels, read the active conversation, or send an explicitly authorized prompt and capture a newly completed reply. Use for the desktop app's Chat or actual Code surface, not a browser PWA, Teams, Cowork, or a chat request that merely asks for code.

Buy a company or sell yours: diligence, valuation, terms, integration. Use whenever M&A or an exit comes up.

Mac apps that open at login in the menu bar only, one window, template icon, versioned installs. Use for any macOS app.

Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the user says their Mac disk or storage is full or nearly full, gets a "startup disk almost full" / low-storage warning, asks to free up space, clean/clear caches, remove junk, delete leftover files from apps they uninstalled, or find what's eating their disk — in any language (e.g. English "my mac is out of space", "free up disk", "clear caches", "what's taking up my storage"; Georgian "ქეში გაასუფთავე", "მეხსიერება გადამევსო", "ადგილი აღარ მაქვს"). Surveys usage first, auto-clears only pure caches, moves anything riskier to the Trash (restorable), asks before anything expensive, logs every deletion, and reports what was freed. Do NOT use for cloud storage, RAM/memory-pressure, or a single named app's own in-app cache button.

Read and organise the owner's mailbox through mail, a WireCat CLI — sync mail over IMAP into the shared store, search it, read an email whole with its attachments' text and follow its thread; mark, move, copy, delete to Trash and undo, keep the owner's mail rules, write drafts, and send, reply and forward over SMTP, with JSON answers. Use when a task needs the owner's mail. It never asks for or prints a password, and over MCP it mails only the owner unless the owner allows more.

Guides agents through integrating transactional email sending via Mailtrap's Email API, including sandbox testing, domain verification, and API authentication. Use when implementing email-sending features, debugging delivery issues, or setting up safe dev/staging email testing.

Keep Paperclip stories and their downstream catalog aligned with the feature map and production UI. Use to reconcile story drift, classify prototypes, update fixtures, or maintain feature coverage.

Keep a project's verification skill and product/agent access maps aligned with current source and real evidence. Use for /maintain-verification-skill, auditing the verify skill, or reconciling feature and agent access coverage.

Use to bring exactly the source files a PR/branch touches up to the deterministic-refactor compliance conditions (typed, overrides marked, typed test doubles), so a future refactor over them is verifiable. Scoped to the diff — grows compliance monotonically, no repo-wide migration.

Apply concrete design-engineering details that make interfaces feel polished. Use when reviewing or improving UI spacing, typography, borders, shadows, motion, hit areas, icons, text wrapping, and interaction states.

Use BEFORE renaming a symbol/attribute (Python or TypeScript) to make its blast radius verifiable — type the code that might reference it (untyped params/vars that could hold the class, classes with matching attribute names, overrides not marked as such) so the post-rename type-check gate is sound.

Inspect, audit, and clean up your local Claude Code projects under ~/.claude. Use this whenever the user wants to see which projects Claude Code has tracked on this machine, get statistics about a project (session count, project-local skills/agents/commands/MCPs/plugins, disk usage, token usage, estimated cost), or remove/clean up a project's traces from ~/.claude. Trigger on phrases like "manage my claude projects", "list my claude code projects", "how many sessions / how much have I spent on project X", "token usage for this project", "delete this project from claude", "remove project X from ~/.claude", "clean up old claude projects", "which projects are taking up disk space", or any request to audit or purge local Claude Code project data — even when the user names a path or project instead of saying "project".

Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys or endpoints, troubleshooting plugin connection issues, or verifying the observability pipeline is running.

Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control

Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.

Builds reusable Manim explainers for technical concepts, diagrams, system diagrams, and product demos, handing off to the broader ECC video stack when needed. Use when the user wants clear animated explanations rather than a generic talking-head explainer script.

Cria o Manual de Copy completo de um cliente de consultoria a partir do diagnóstico existente. Gera o documento estruturado em 18 seções cobrindo arquétipo, posicionamento, persona, JTBD, SWOT, objeções, CVBA, banco de copy por canal e checklist de aprovação. Use quando o projeto tiver diagnóstico aprovado e for hora de produzir o manual de referência de comunicação do cliente.

Create or revise professional Brazilian Portuguese HTML manuals de identidade visual (MIV/brandbook) for clients from brand sources such as PDFs, presentations, logos, websites, social profiles, existing copy manuals, and prior project files. Use when the user asks for Manual_MIVev, manual de identidade, MIV, brandbook, guia de marca, identidade visual, logo usage, brand applications, or how to apply/not apply a brand in HTML deliverables.

Cria o Manual de Tráfego Pago completo de um cliente de consultoria em HTML com imagens, ensinando alguém sem experiência prévia a montar as primeiras campanhas em Meta Ads e Google Ads. Gera documento estruturado em 15 seções cobrindo pré-requisitos técnicos, estrutura de conta (com diagramas), orçamento por fase, segmentação (com funil visual), arquitetura de campanhas, mockups de criativo, rastreamento, cadência de otimização, KPIs e checklist de lançamento. Use quando o cliente tiver Manual de Copy pronto (ou diagnóstico + ICP definidos) e for hora de operacionalizar a aquisição paga.

Writes or restructures project documentation in Markdown — READMEs, guides, references, runbooks, architecture notes — organised around what the reader is trying to do. Use this whenever the user asks for a README, docs, a guide, a runbook, or says their documentation is out of date, missing, or unhelpful, and also after building something substantial that nobody else could pick up without a written explanation.

Writes or restructures project documentation in Markdown — READMEs, guides, references, runbooks, architecture notes — organised around what the reader is trying to do. Use this whenever the user asks for a README, docs, a guide, a runbook, or says their documentation is out of date, missing, or unhelpful, and also after building something substantial that nobody else could pick up without a written explanation.

Use when the user wants a markdown file turned into a single-file interactive HTML page (document, code review or slide deck). Classifies it with doctype_classifier.py and routes to md-document, md-review or md-slides.

Markdown linting for this workspace: MD029 list numbering, MD040 code block language tags, MD051 anchor links, and the closing-fence mistake that breaks HTML generation. Use when: writing or editing any .md file, running markdownlint-cli2, fixing MD029/MD040/MD051 errors, generating HTML or PDF from markdown. Do NOT use for: the general documentation standard (use the documentation skill) — this is the linter-specific subset.

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user needs market sizing, competitor comparisons, fund research, technology scans, or research to inform business decisions.

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

Use for market sizing (TAM, SAM, SOM both top-down and bottom-up), survey sample sizes or segment scoring. Runs market_sizer.py, sample_size_planner.py and segmentation_scorer.py and never returns one unsourced number.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Identify 3-5 potential customer segments with demographics, JTBD, and product fit analysis. Use when exploring market segments, identifying target audiences, evaluating new markets, or learning how to segment a market.

Estimate market size using TAM, SAM, and SOM with top-down and bottom-up approaches. Use when sizing a market opportunity, estimating addressable market, preparing for investor pitches, or evaluating market entry.

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

Use at the start of any marketing project, or when ICP, positioning or brand voice are missing, before other marketing skills. Writes the shared context file the other skills read and validates it with context_validator.py.

Use when planning demand generation, paid acquisition across Google, LinkedIn and Meta, or a marketing budget, before allocating spend. Computes blended and per-channel CAC with calculate_cac.py and sets MQL to SQL handoffs.

Multi-channel demand generation, paid media optimization, SEO strategy, and partnership programs for Series A+ startups. Includes CAC calculator, channel playbooks, HubSpot integration, and international expansion tactics. Use when planning demand generation campaigns, optimizing paid media, building SEO strategies, establishing partnerships, or when user mentions demand gen, paid ads, LinkedIn ads, Google ads, CAC, acquisition, lead generation, or pipeline generation.

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category.

Use when asked for marketing or growth ideas for a SaaS or software product. Picks from 139 tactics by stage, budget and channel instead of a generic list.

Generate 5 creative, cost-effective marketing ideas with channels, messaging, and engagement rationale. Use when brainstorming marketing campaigns, planning product promotion, or looking for creative marketing tactics.

Use when a marketing request spans several skills (a campaign across content, SEO, CRO and channels) or it is unclear which skill fits. Routes and sequences the work and tracks it with campaign_tracker.py.