Skills in this repository
SkillsMP has collected 229 skills from coco-research/coco. Open a skill to review its source and details.
coco-research/cocoShowing 40 of 229 collected skills.
Install, update, version-check, or uninstall the Coco open-source AI workflow framework via bin/coco.js. Use when setting up Coco on a machine, checking out the pinned release tag into an existing clone, checking the installed version, or removing it. npx…
Build and validate .arch/index.json — a committed map from each architectural component of this repository to the real directories and files that implement it, pinned to a git commit, with every path verified to exist. Also detects structural drift between…
Your climate and energy brain trust. 25 named personas across 7 cells covering energy transition, carbon markets, climate modeling, sustainability, grid infrastructure, environmental policy, and ESG.
Data & Analytics Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.
Your education and edtech brain trust. 25 named personas across 7 cells covering learning science, curriculum design, AI tutoring, higher-ed strategy, edtech platforms, assessment, and workforce development.
Your software-engineering brain trust. Named personas across 11 cells covering cloud architecture, reliability/SRE/observability, data and storage, security, FinOps, languages and runtimes, systems programming, web and frontend…
Your finance brain trust and decision partner. Named personas across 7 cells: valuation/corporate finance, investing, accounting/FP&A, macro, fintech, behavioral, and capital markets/M&A/private. Markets/quant/derivatives are reserved for…
Sales, GTM & Marketing Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.
Your healthcare and life sciences brain trust. 25 named personas across 7 cells covering drug discovery, medtech, biotech strategy, health policy, genomics, clinical trials, and healthcare economics.
Your legal, IP, and regulatory brain trust. 31 named personas across 7 cells covering patent strategy, tech licensing, regulatory litigation, AI governance, open-source compliance, privacy law, and antitrust.
Your product + design brain trust and decision partner. Named personas across 8 cells spanning product strategy, discovery/research, growth/metrics, design foundations/usability, design leadership/craft, UX/content, design systems, and a…
Risk & Compliance (GRC) Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.
Strategy Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.
Trading Super Intelligence Team. Named real-world personas across 8 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.
Use when the user says run the rest autonomously, overnight, or hands-off through the remaining phases. Runs discuss, plan, execute per phase, pausing only for user decisions, then milestone audit, complete, and cleanup.
Use when working with this machine's local LLM setup (LM Studio + mlx-dspark) -- checking status, changing context window, diagnosing a reasoning hang or dead request, understanding RAM/speed tradeoffs, or wiring a new script to the local inference endpoint.
Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt engineering, or AI cost control. Treats prompts as code and validates every model output.
Use when designing a new REST or GraphQL API, reviewing an API spec before implementation, setting team API standards, or migrating REST to GraphQL. Covers resources, HTTP semantics, pagination, error handling, and pitfalls.
Use when implementing, reviewing, or debugging Apple Liquid Glass: iOS 26+ adoption, Regular vs Clear variants, tinting, scroll edge effects, or an iOS-native redesign review.
Use when the agent must open a URL, fill a form, click through a flow, screenshot a page, or extract data from a live page. Covers two providers (agent-browser local CLI, agentic-browser cloud) and the shared @e ref workflow.
Use when the user invokes /coco or /coco!, says catch me up, or asks what needs attention, a project status, their todos, decisions or people. Renders the PM dashboard and routes each subcommand to its platform tool or a PM skill.
Use after every code change, after writing tests, or before marking a task complete, and when the user says verify, quality gate, or audit code. Runs a 7-category mechanical check for TDZ, import, dead code, and mock leakage bugs.
Use when linked docs drift, when a source file changes and downstream PRDs, decks, or notes must follow, or when a .sync-report.md exists. Diffs the proposed edits, applies them only after approval, and never overwrites a target file.
Use when adding server-side API routes to an Expo Router app (+api.ts files) for secrets, database access, third-party proxies, webhooks, CORS, or EAS Hosting deploys. Covers file routing, env vars, and Cloudflare Workers limits.
Use when asked to generate tests for a file, module or component, to raise coverage, or to bootstrap a suite for untested code. Detects the project's test framework and conventions first, then writes unit, integration and edge-case tests.
Use when the user asks for an incident response plan, IRP, escalation matrix or incident playbook. Writes an offline HTML plan with severities, escalation contacts and comms; DR restores service, IRP runs the incident.
Use when the user sends or generates an image, screenshot, video, audio or file and wants it saved, or asks to find past media (that diagram, the mockup from last week). Ingests and searches with local ChromaDB embeddings.
Use when implementing GPT chat, streaming, function calling, embeddings for RAG, images, audio or batch jobs, or troubleshooting 429 rate limits and API or TypeScript errors. Stateless OpenAI patterns that prevent 16 documented errors.
Use when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and doc-sync config.
Use when the user says I want to add X, implement Y, create a task for Z, or plan this feature. Writes a task file plus a PRD under .agent/, links them, and waits for approval before any implementation starts.
Use when designing, building or reviewing UI/UX for a web or mobile app: picking styles, color palettes, typography, layout, animation or charts, or checking accessibility and touch targets. Priority-ranked rules ordered by impact.
Use when facing architectural decisions, complex trade-offs, strategic technology choices, or scaling and migration questions that deserve more than a quick answer. Lays out options with trade-offs, then a recommendation.
Use when starting any task, before invoking any other skill or GSD command, to route between Superpowers skills and GSD commands from project state and task scope. Fires first when both systems are installed.
Use when the user asks to refresh CLAUDE.local.md, regenerate project context, or after a brain-update session flush. Rewrites only the sentinel-delimited auto-generated section from the brain DB, preserving manual behavior rules.
Use when setting up project memory in a new folder or on the first brain:init in a project. Creates project_brain.db, registers the project, and bootstraps it from CLAUDE.local.md, memory files, docs, and emails; safe to re-run.
Use when project files changed since the last brain scan, CLAUDE.local.md was updated, or a periodic refresh is due. Rescans incrementally, writes new entities, decisions, and documents; needs project_brain.db (run /brain-init first).
Use when the user says brain, project knowledge, what do we know about, open tasks, or recent decisions, or runs /brain or /brain-update. SQLite project_brain.db tracker for entities, relationships, tasks, threads, decisions, events.
Use when the user asks for a knowledge article, wiki page, or entity summary from the brain, or wants to search, list, or review merges across brain DB articles. Generates Wikipedia-style articles from entities, decisions, and emails.
Use when the user says 'cognee recall', 'search memory', 'what do we know about', 'find related', or 'graph search'. Runs semantic, graph, and lexical search across the Cognee knowledge graph and injects results as agent context.
Use when the user says 'cognee', asks about knowledge graph or graph memory, wants to switch memory backends, or needs a status check, dataset init, or graph view. Covers Cognee endpoints plus the Brain fallback.