Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.
Designing tabletop games - from core mechanics to manufacturing, from prototyping to KickstarterUse when "board game, tabletop, card game, worker placement, deck building, area control, playtesting, rulebook, kickstarter game, game balance, asymmetric factions, euro game, ameritrash, party game, dice game, prototype, game publisher, crowdfunding game, board-games, tabletop, game-design, mechanics, playtesting, kickstarter, manufacturing, rulebook, components, balance, player-interaction" mentioned.
Use when the user already has browser automation and wants it unblocked or run in the cloud: Playwright, Puppeteer, Selenium or another driver, a headless script that gets blocked, detected, or rate limited locally, or a computer-use AI that clicks by itself and needs somewhere to click. Also for asks that name CDP, connectOverCDP, browserWSEndpoint, a remote WebDriver, a websocket browser endpoint, or Browser API. Not for building the scraper for them (use scrape), not for one page as markdown, HTML, or a screenshot (use fetch), not for a search query (use search).
Summarize lessons learned from ccbox session logs (projects/sessions/history/skills) so the agent can do better next time. Produce copy-ready instruction updates (project + global) backed by evidence, with optional skill-span context to attribute failures to specific skills. Use when asked to run /ccbox:insights, generate a "lessons learned" memo, or propose standing instructions from session history.
Interactive UI rendered inside ChatGPT or Claude — OpenAI Apps SDK apps, MCP Apps (the @modelcontextprotocol/ext-apps standard), or MCP-UI components, with a Next.js/React server. Covers the MCP tool and resource architecture, the window.openai / ui-bridge data flow, widget state, sandbox/CSP security, display modes, visual design, and directory submission. Trigger when building, reviewing, or designing such apps — even when the user only says "chat app", "ChatGPT widget", "Claude app", "render UI in chat", "window.openai", "createUIResource", "outputTemplate", or "MCP app UI" without naming a specific SDK.
Bootstrap `.chief/project.md` for a Chief-installed project by interviewing the user about their tech stack, dev commands, architecture, and key rules. Use after `/chief-install` (or any time the user wants to set up project-wide context). This is the lazy entry point for `.chief/` — it creates only `project.md`; milestones and rules are created later, on demand.
On-demand pattern extraction from a specific GitHub codebase, given a focused query — "how does shadcn/ui implement the design system", "how does opencode use effect-ts", "how does base-ui handle composition" — when no pre-distilled static rule pack exists yet. Distills the generic pattern-extraction moves — classify the query before grepping (component / composition / state / effect / error / build / routing), grep before reading whole files, treat tests and examples/ as canonical intent, follow imports outward for the public surface, follow usages inward for variants, filter boilerplate / legacy / test scaffolding to surface load-bearing code, and capture findings to /knowledge/libraries/ for reuse. Dynamic light sibling of static code-atlas skills (opencode-ts, openai-codex-rust-patterns, nextjs-ppr-patterns). Triggers on "show me how <library> implements X", "find the <pattern> in <repo>", "distill <library>", and ad-hoc /distill-<library>-style invocations.
Install, customize, switch, verify, or restore a full adaptive theme for the Codex desktop app on macOS or Windows. Use when the user wants a Codex theme beyond official color settings, wants to turn a personal image into a full-window Codex wallpaper with adaptive readability, needs the skin reapplied after a Codex update, wants to switch saved themes from the menu bar or tray, or needs a safe rollback without modifying the official app or app.asar.
Grounds visual design decisions in cognitive psychology principles — perception, attention, memory, Gestalt grouping, and visual encoding hierarchy — explaining WHY certain designs work. Covers interfaces, data visualizations, educational content, and presentations. Invoke when user mentions cognitive load, visual hierarchy, working memory, preattentive processing, Gestalt principles, encoding hierarchy, or cognitive design pyramid. For design evaluation, use `design-evaluation-audit`. For fallacy prevention, use `cognitive-fallacies-guard`. For data storytelling, use `visual-storytelling-design`.
Build evidence-oriented readiness checklists for frameworks such as SOC 2, HIPAA, PCI DSS, and GDPR, with gaps and remediation priorities. Use when the user needs an internal readiness assessment or control-mapping plan; do not use it to certify compliance or replace an auditor or counsel.
Build or transform ecommerce websites from loose company, product, or brand briefs into unconventional, brand-specific shopping experiences with original ImageGen product imagery. Use when a user asks for a crazy, wild, experimental, unconventional, anti-template, art-directed, or highly memorable online store; wants Codex to invent an ecommerce visual direction from business details; or wants a working storefront that combines creative concepting, generated product photography, responsive implementation, cart interactions, validation, and optional publishing.
Cultural tourism Douyin feed — search popular cultural tourism Douyin posts, filter the hottest content by likes, and generate a polished HTML report. Use when the user needs cultural tourism Douyin, travel guides, scenic spot popularity, cultural tourism news, or viral cultural tourism content. Trigger words: 文旅抖音, 文旅信息源, 文旅资讯, 旅游抖音, 景区视频, 文旅爆款.
Comprehensive data visualization skill covering visual execution and technical implementation. Includes perceptual foundations, chart selection, layout algorithms, and library guidance. Triggers on: charts, graphs, dashboards, 'visualize', 'plot', data presentation, D3, Recharts, Victory.
Provides comprehensive guidance for Domain-Driven Design (DDD) concepts, strategic design, tactical design, and architecture patterns. Includes DDD applicability assessment, Pattern Boundaries table (what each pattern is and is NOT), Complexity Ladder (when to adopt each level), Core Concepts quick reference with Entity/ValueObject/Aggregate patterns, full architecture landscape overview, anti-patterns with fixes, multi-language reference implementations, and complete primary source references. Use when the user asks about DDD basics, needs to understand DDD concepts, evaluates DDD applicability, or wants an introduction to domain-driven design.
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.
Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an animation", "polish the UI", "review this component".
Use when checking a radiology or medical AI study design before drafting or submission. Reviews the analysis unit, cohort logic, leakage risks, comparator, validation strategy and reporting-guideline fit. AI-vs-expert benchmarks are /design-ai-benchmarking.
Guides application developers in designing correct and performant transaction patterns for CockroachDB, covering transaction lifetime, implicit vs explicit transactions, retry handling with exponential backoff, pushing invariants into SQL, selective pessimistic locking, set-based operations, connection pooling, prepared statements, keyset pagination, follower reads, and separating business logic from database logic. Use when building applications on CockroachDB, designing transaction workflows, handling retries, optimizing application-layer database interactions, or configuring connection pools.
Provides situational playbooks for high-stakes edge cases that don't fit the standard management toolkit — produces step-by-step guidance for inappropriate team behavior, an engineer badmouthing your manager, letting someone go when circumstances are hard, manager quitting guilt, and handling layoffs (for both those leaving and those staying). Use when the user says "don't know how to handle this," "someone said something inappropriate," "engineer said something offensive," "developer talks badly about my manager," "letting someone go when their situation is hard," "I feel guilty about leaving my job," or "handling a layoff." Do NOT use for standard underperformance management (use performance-reviews) or giving direct feedback (use feedback).
Django backend patterns for recommendation services (AWS Personalize, Databricks Model Serving, internal microservices) and OpenSearch-backed search/feed endpoints. Covers fan-out orchestration (asyncio.gather, deadline propagation, partial results, async client reuse), external service protection (timeouts, circuit breakers, jittered retry, bulkheads, rate limits), OpenSearch query patterns (search_after, _source filtering, function_score, aliases, routing, bool.filter), result blending (score normalization, MMR, dedup, cold-start), Redis caching (stampede protection, model-versioned keys, two-tier, negative), resilience (partial-response envelope, stale-on-error, graceful degradation), async (sync_to_async, async ORM, uvicorn, contextvars, disconnect cancellation), and DRF response shape (cursor pagination, ETag, throttling). Use when building, reviewing, or refactoring such a Django backend. Triggers even without explicit "scale" cues. Includes 5 scaffolding templates.
Use this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — without rewriting the data-plane in DOCA-native form: binding a DPDK port id to a `doca_dev` (`doca_dpdk_port_probe` / `doca_dpdk_port_as_dev`), converting `rte_mbuf` ↔ `doca_buf`, querying `doca_dpdk_cap_is_rep_port_supported`, or debugging `DOCA_ERROR_*` from a bridge call. Trigger even without "DOCA DPDK Bridge": "how do I add DOCA Flow to my DPDK app", "make a DPDK port visible to DOCA", "the bridge loads but every operation returns errors", "pkg-config --exists doca-dpdk-bridge fails", or "DOCA_ERROR_NOT_FOUND on port registration". Route elsewhere for fresh DOCA-native packet I/O (doca-eth), flow-rule programming (doca-flow), DOCA or DPDK install (doca-setup), or RDMA data movement (doca-rdma).
Library-documentation lookup methodology — API behavior, version-specific changes, idiomatic usage, or why production diverges from docs — independent of which library. Distills the generic navigation moves shared across libraries — classify the question before searching (changelog vs API reference vs idiom vs known-bug), check llms.txt before scraping HTML, pin to the user's version before reading reference pages, read changelog first for "did X change" questions, treat examples/ dirs as truth for idioms, and fall back to GitHub issues / status page / Discord when docs match but reality doesn't. Per-library topography lives in the shared /knowledge/libraries/ graph as thin reference data, alongside code-distill's section. Triggers on "where in <library> docs", "look this up in <library>", "did <library> change X", "docs say X but code does Y", and any prompt where the next move is to consult a library's official documentation.
Check docs.celo.org, docs.minipay.xyz, and other live sources for drift against this repo's cached reference files (contracts, network info, docs sitemap, ecosystem, grants, MiniPay, wFIAT access) and fix or flag it. Use when asked to check docs updates, run the docs watch, or on the scheduled weekly run.
.NET SDK and runtime installation across Windows, macOS, and Linux. Handles version detection, platform-specific installers (WinGet, Homebrew, apt, dnf), SDK vs runtime selection, offline installation, Docker setup, and troubleshooting. Auto-activates for .NET installation, setup, version management, and multi-platform deployment.
Authors and queries Fabric Eventhouse and KQL databases: tables, functions, policies, materialized views, ingestion, and read-only KQL for real-time and time-series analytics. All KQL database work belongs here, table creation and simple queries included. An Eventstream item is eventstream-cli; an Event Schema Set is eventschemaset-cli.
Analyze images using AI — segment objects, detect objects, extract text (OCR), describe images, and answer questions about images. Use when the user requests "Segment image", "Detect objects", "OCR", "Extract text from image", "Describe image", "What's in this image", or "Image analysis".
Feature planning, specification, phased implementation, progress tracking, per-phase PRs, and archival workflow. Use when starting a new feature, creating spec documents, breaking work into phases, tracking progress, managing PRs, or archiving completed specs
Scope, plan, and execute the reorganization behind approval gates. TRIGGER WHEN: organizing messy folders (Downloads, Desktop, Documents), finding duplicate files, cleaning up old files, restructuring project directories, separating work from personal files, or automating file cleanup tasks.
Use when the user wants to \"fill in this letter for each person\", \"mail merge\", \"generate letters for this list\", \"turn this filled letter into a template\", or hands over a template plus a list. Bulk-fills ONE master template — a Word (.docx) letter/form or an Excel (.xlsx) form — from a data table, one filled file per row (mail-merge); or the reverse: extract a reusable tokenised .docx template + data-table skeleton from a filled example document, confirm the mapping, then fill. Reads the master, proposes a TOKENISED version (varying parts become {{tokens}}), confirms the mapping, then regenerates one output per data row, preserving the master's layout exactly. Data is an .xlsx or .csv (one row per output); outputs are one named file per record. Never invents: a token with no data is a VISIBLE flag, never a silent blank. Runs fully local and generates files only — it does not send, post or sign. Extract is .docx only this round (not .xlsx). Not a substitute for a hand-crafted single letter.
Design, structure, and animate code-first video compositions using the framefields WebGPU SDK. Use when writing or changing a framefields film — scenes and transitions, layout trees, keyframes and easing, kinetic typography, shapes and morphs, charts, blend modes and mattes, 3D scenes (cameras, lights, materials, outlines, models), physics, GPU particles, procedural VFX layers, time remapping, or audio-synchronized motion.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
