Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Release and recover first-party Composio CLI binaries through Build CLI Binaries, including automatic beta builds, promote-stable dispatches, beta-tag selection, asset and installation verification, and failed release recovery. Use when a contributor asks to build a CLI beta, publish or promote a stable CLI version, choose a release candidate, monitor a CLI release, or diagnose a failed CLI release. Do not use for TypeScript SDK Changesets releases or CLI source implementation.
Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avoid. Use when reviewing PRs, establishing review standards, or improving review quality.
Get an INDEPENDENT second opinion from the OpenAI Codex CLI — a separate reviewer runtime run over the real diff, not Claude reviewing its own work. Verifies Codex is available, resolves the scope (branch, a commit, or uncommitted), writes a focused instruction file grounded in the actual change set, runs `codex review` with disk-read sandbox so it can verify findings against source, then summarizes them by priority. Keeps secrets and credential values out of the instruction file, treats findings as candidates to verify locally before any fix, and reports an explicit clean result rather than fabricating one. Use only when the user explicitly asks for a Codex review or cross-review.
Document solved problems for team reuse. Provides process knowledge for /ia-compound. Use when documenting a resolved issue, writing up lessons learned, capturing a post-mortem, adding to the knowledge base, or building searchable institutional knowledge after debugging.
Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.
Route work across Arthur's private Mac, Windows/WSL, and Android agent environments. Use when choosing between ChatGPT Remote, raw SSH, app SSH projects, Computer Use, Logitech Flow, or SkillPort synchronization, or when diagnosing cross-device behavior; not for detailed monitor cabling.
Generate professional, ATS-optimized CVs and resumes as polished HTML files. Use this skill whenever the user asks to create, write, build, update, or improve a CV, resume, curriculum vitae, or job application document — even if they just say "make me a resume" or "help with my CV". Also trigger when the user provides career info, work history, or asks to format their experience for job applications. This skill produces visually stunning, eye-catching HTML that is simultaneously ATS-friendly — the best of both worlds.
Detects and revises templated phrasing, posturing, hidden parallelism, structurally identical analytical examples, repeated semantic frameworks, fake rankings, fixed rhythms, and other AI-like expressions in Chinese article body text, while preserving the author's facts, existing heading hierarchy, necessary functional lists, legal terminology, Markdown images, and established voice. Must be used after an article's first draft is complete when the user asks to “remove the AI feel,” “make it sound more human,” “rewrite it based on the author's samples,” or “check the parallelism or tone.” Without author samples, make only minimal edits; do not invent first-person narration, metaphors, punchy one-liners, or experiences, and do not restructure the article under the pretext of removing AI-like wording.
Evidence-led debugging for unexpected, silent, intermittent, or regressed behavior, including slowdowns and leaks. Use when tracing a bug to its root cause, finding what broke something that used to work, adding or removing targeted debug logs, or verifying a fix. Not for known one-line fixes, code review of a diff, runtime review of deployed services, or PM bug triage.
Inventing deterministic metrics — turning a fuzzy property like 'maintainability', 'risk', or 'how reducible this code is' into a deterministic, computable number an agent can trust and optimize. Covers the path from construct to adoption — operationalizing the construct, confronting computability limits (Kolmogorov, Rice) with sound proxies, picking the right measurement scale, proving properties (monotonicity, invariance, the Weyuker/Briand axioms), guaranteeing determinism, establishing construct validity (not just LOC in disguise), and hardening against Goodhart-style gaming when an agent optimizes the metric. Trigger when designing, reviewing, or validating a quantitative metric, score, measure, or index — and even when the user doesn't say 'metric' but wants to quantify, score, rank, or measure code/behavior, build a deterministic optimization target, or invent a measure for something previously unquantified (e.g., behavior-preserving codebase-size reduction).
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
Hardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compression and decompression, plus LZ4 decompression (stream and block; LZ4 encoding is NOT supported), instead of CPU zlib / zstd. Trigger on “offload this gzip,” “decompress incoming network data on the NIC,” “compress task returns INVALID_VALUE on alloc_init,” “submitted a task but no completion arrives,” or “decompress LZ4 on the BlueField,” even without naming DOCA Compress. Covers enabling compress-deflate, decompress-deflate, decompress-lz4-stream, and decompress-lz4-block tasks on a doca_compress context; sizing source / destination doca_buf against the per-task cap query; mmap permissions; offload vs. CPU decisions; a round-trip smoke test; and DOCA_ERROR_* from Compress calls. Refuse and route elsewhere for zstd / Snappy / brotli, LZ4 encoding (a CPU LZ4 library), pure mmap-to-mmap copies (doca-dma), or DOCA Core lifecycle internals
Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing between the DPA comm component (inter-DPA messaging) and the DPA verbs component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path Accelerator": "run compute on the DPA from my host", "DPA kernel hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC version skew", or "does this BlueField expose a DPA". Route elsewhere for DPA-side kernel programming itself, DPACC compiler internals, host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and GPU-initiated networking (doca-gpunetio).
Use this skill when operating the DOCA Firefly Service container on BlueField: choosing the four PTP configuration axes (role / profile / domain / interface), connecting the BlueField PHC, host follower, and consumer workload, deciding whether PTP-grade time is needed (vs. chrony / NTP), or debugging a Firefly deployment where PTP is not syncing or the host clock is not following. Trigger even when the user does not explicitly mention “DOCA Firefly” or “PTP.” Typical implicit requests include “container green but PTP never advances past LISTENING,” “Firefly says synced but the host clock still drifts,” “sync acquired but offset is tens of microseconds,” “my Rivermax SMPTE workload needs PTP,” or “is chrony good enough.” Refuse and route elsewhere for installing DOCA, host-side chrony / ptp4l configuration, PTP topology / boundary-clock design, building DOCA apps that read the disciplined PHC, or other DOCA services (DMS, Flow-Inspector, HBN); those belong to other skills.
Docker containerization for development and production. Covers Dockerfiles, multi-stage builds, layer caching, Compose services, networking, volumes, health checks, security hardening, and production deployment patterns. Use when writing Dockerfiles, optimizing image size, configuring Compose services, debugging container networking, setting up health checks, hardening containers for production, or troubleshooting build cache issues.
Write or update the user-facing posthog.com documentation for a PostHog Data warehouse import source. Use when adding a new source doc, fixing an inconsistent or stub source doc, or standardizing the docs at contents/docs/cdp/sources. Covers the canonical template, shared snippets, the auto-rendered <SourceParameters /> and <SourceTables /> components, frontmatter, and the docsUrl/slug rule that prevents 404s.
Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags, locators, and assertions. Do not use for Vitest, React Testing Library, backend tests, or generic browser automation outside the E2E suite.
Use this skill to set up and configure the Education Cloud Student Recruitment Agent (SRA) — the packaged Agentforce agent (namespace sturecruitment) that answers admissions FAQs, captures inquiries, registers campus tours, and files applications for prospective students. TRIGGER when the user wants to: create or configure an admissions, recruitment, or enrollment agent, set up the Student Recruitment Agent, deploy SRA to an Experience Cloud site, clone the SRA flows or permission sets, add the SRA subagents (Admissions and Enrollments FAQ; Admissions Application; Campus Tours, Visits, and Events Registration; Request for Information), wire Learning Program grounding, or build the escalation subagent. Guides platform enablement, permissions, grounding, agent creation, and channel deployment — API-first with UI fallback. DO NOT TRIGGER for the Transfer Credit Agent, generic Agentforce authoring (use agentforce-generate), or base Education Cloud domain enablement (use education-cloud-domain-configure).
Draft a professional, audience-aware email or reply with calibrated tone and a clear call to action. Use when the user needs one message, response, follow-up, support note, or meeting request; use sales-email-sequences for a coordinated multi-touch outbound campaign.
Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via distributed `owners.yaml`, `products/*/product.yaml`, and `.github/CODEOWNERS`). Use when assigning a reviewer, attributing a bug or slow query to a team, routing work, scoping a team-wide audit, or answering "who owns X" / "what does team Y own".
This skill should be used when the user asks to "execute this blueprint", "execute the blueprint", "run the blueprint", "run the plan", "execute the plan", "start building from the plan", "implement the blueprint", "implement the plan", "continue the plan", "resume execution", "execute 01_milestone_name.md", "execute step 3", "run steps 3-5", or "skip to step 4".
Extract structured data from any web page using Playwright — screenshots, design tokens, page text as Markdown, interactive element maps, and full page data packs. Use this skill whenever the user wants to capture a web page screenshot (full page or element), extract CSS design tokens or theme information, convert page content to Markdown, collect links and interactive elements from a page, or export a complete page analysis package. Triggers on any URL that isn't an Axure prototype — for Axure URLs use extract-axure-data instead.
Feature-Sliced Design (FSD, a frontend architecture method) reference and rules. Also known as fsd / feature-sliced. Covers layers (app / pages / widgets / features / entities / shared), dependency direction, Public API, @x notation (cross-import), slice groups, segments (ui / model / api / lib / config), steiger, and Next.js and TanStack Query integration. Automatically referenced during code reviews and refactoring
Evaluate the financial health of an A-share company through earnings quality, cash conversion, working capital, leverage, and balance-sheet risk. Use this skill when revenue and profit trends diverge from cash flow, when debt and capex matter, or when impairment and receivable quality are major concerns. All outputs must include accessible source links.
Fix TypeScript errors and loop the type-check until green. Use when the user says "ts errors" or "fix types", when a change "still isn't working" in a TS context, after editing any TypeScript file, and when another skill needs the type-check loop (/done, /parallel-review, /fix-pr-review).
Evaluate and improve the usability of existing front-end interfaces — either local source code or live websites by URL. Use this skill whenever the user has existing front-end code OR a live website URL and wants to understand why users struggle with it, find usability problems, or make it easier to use. Triggers on direct requests like "review my UI", "audit my interface", "check accessibility", "evaluate my design", "improve the UX", "audit this website", "review https://example.com" — but ALSO on indirect symptom descriptions like "users keep abandoning this form", "something feels off about this page", "we're getting complaints about the checkout flow", "conversion dropped after the redesign", "people say it's confusing", or "make this less painful to use". If someone has a front-end component, page, or URL and the problem sounds like usability, user confusion, or poor interaction design rather than a bug or performance issue — use this skill. NOT for building new interfaces from scratch, performance optimization, or backend logic.
Create distinctive, production-grade frontend interfaces with high design quality and accessible markup. Use this skill when the user asks to build or beautify web components, pages, applications, landing pages, dashboards, artifacts, or React/HTML/CSS UI. Generates creative, polished code that avoids generic AI aesthetics, then self-checks it against an objective accessibility and quality rubric.
Futu `futu` CLI market-data skill. Use for stock, option, and futures quotes, K-lines, snapshots, tickers, intraday data, order books, rankings, capital flow, company profiles, financials, shareholders, valuation, plates, IPOs, calendars, watchlists, and paginated queries. Do not use it to place orders
Use when adding or editing a GitHub Actions workflow that pushes a container image to a registry (ECR/ghcr/Docker Hub via build-push-action) or dispatches a production deploy (a `commit_state_update` repository_dispatch to PostHog/charts). Those run from a single canonical deploy repo, gated by the CD_DEPLOY_ENABLED variable. Does NOT apply to workflows that publish GitHub releases, npm, crates, or Homebrew — those stay on the public repo.
Work with Google Drive through its MCP tools - search, read, create, organize, share, comment, and export files. Use when creating files in specific folders, moving or renaming, converting Markdown/CSV into Docs/Sheets, managing comments, or exporting a rendered PDF.
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase. ALSO triggers when users are frustrated or complaining about agent quality — e.g. 'the agent keeps ignoring conventions', 'it never follows instructions', 'why does it keep doing X', 'the agent is broken' — because poor agent output almost always signals harness gaps, not model problems. Covers: context engineering, architectural constraints, multi-agent coordination, evaluation, long-running agent harness, agent loops (autonomous operation, verifiers, stop conditions), agent memory (cross-session memory, consolidation), and diagnosis of agent quality issues
Deploy AI Agent development platform (Dify) on Huawei Cloud Flexus L instance, providing deployment operations, password management, MaaS model configuration, and workflow import capabilities. Trigger keywords: deploy flexusagent/一键部署Flexus AI Agent开发平台、change password/修改开发平台管理员密码、change dify password/修改dify平台密码、add maas provider/添加MaaS模型供应商、configure maas model/配置MaaS模型、view workflow/查看AI Agent工作流、import workflow/导入AI Agent工作流
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
Ensures zero-mismatch integrity between server-rendered HTML and client-side React trees. Use when debugging hydration errors, fixing text content mismatches, handling browser extension DOM pollution, implementing selective hydration with Suspense, using the React 19 use() hook for deterministic server-to-client data bridges, or applying Next.js use cache for data drift prevention. Use for hydration mismatch, SSR, hydrateRoot, suppressHydrationWarning, onRecoverableError, two-pass rendering.
Reviews an ADK integration documentation page (a Markdown file under docs/integrations/) or an integration pull request for correctness, structure, style, working code, valid links, and catalog conventions. Produces a scored risk report (Critical, High, Medium, Low), a recommended decision (approve, request changes, or close PR), a top-level review response, and draft line-anchored comments; only fixes issues when explicitly asked. Triggers on "integration-review", "review integration page", "review integration PR", "review this integration", "check integration docs".
Write clear, searchable help center articles and FAQ entries based on support data, product documentation, and common customer questions. Use when the user requests knowledge base article writing or provides relevant inputs for this workflow.
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.
