Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Writes and restructures technical documentation - READMEs, tutorials, how-to guides, user guides, architecture docs, onboarding guides, runbooks and SOPs, troubleshooting guides, release notes, and knowledge base articles - grounded in the actual code or product, with commands and examples verified where possible. Use when the user asks to document a project, feature, system, or process, write or fix a README, explain a codebase to new developers, turn notes into a guide, or make existing docs clearer. For endpoint-by-endpoint API reference or OpenAPI specs, use api-documentation-writer; for CLAUDE.md or AGENTS.md files, use claude-md-writer.
Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Write idiomatic Effect v4 TypeScript following official best practices from effect-solutions and the Effect source. Use when writing, reviewing, or refactoring Effect code: services (ServiceMap.Service), layers and dependency injection, error handling (Schema.TaggedErrorClass), data modeling (Schema.Class, branded types, variants), testing (@effect/vitest), HTTP clients (effect/unstable/http), CLI tools (effect/unstable/cli), config, observability, and project setup. Triggers on: 'Effect', 'effect-ts', '@effect/', 'Schema', 'ServiceMap', 'Layer', 'Effect.gen', 'Effect.fn', 'TaggedError', 'branded types', or any Effect-TS related code.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Finds and finishes the last 20% of a built solution — the experiential layer agents skip: what the output actually reads like, which pages or screens should exist, first-run and empty states, opinionated defaults, the golden path. Use when planning any build so the magic gets specced as concretely as the plumbing, before calling any build "done", when a solution works but feels like a demo, or when the user says "last 20%", "finish this", "make it actually good", "is this actually done", or "why does this feel flat".
Use when the user asks to “log this launch,” query a launch date/embargo, record a stage transition, or update submissions/outcomes; curates launch facts through the append-only launches event stream with optimistic revisions and derived dossier/calendar views. Not for RAMP scoring — use launch-readiness-auditor; not for planning tier/window — use launch-tier-planner. Launch registry/launch calendar/stage and embargo records
Use when the user asks to “run a launch retro / post-mortem,” “compare launch results vs targets by channel,” or “decide what to keep or kill for the next launch”; produces a structured D1/W1/M1 retrospective — a per-channel actual-vs-target table (UTM-attributed own analytics as the truth column, platform self-reported numbers as reference, every figure labeled Measured / User-provided / Estimated), a 5-Whys chain on the single largest miss, keep / kill / change decisions per channel, 3-5 actionable learnings for the next launch, and an outcome snapshot submitted to the launch registry. Not for return math (CPA / ROI) — use roi-calculator; not for the stakeholder-facing report writeup — use report-generator; not for a metric deep-dive — use performance-analyzer. Launch retrospective/channel attribution/5 Whys/keep-kill
Use when the user asks to “test our messaging before we scale it,” “design a message-market-fit panel,” or “run a 5-second comprehension test on our new tagline”; produces a message-test design spec — hypothesis, panel and recruit criteria, comprehension / 5-second / message-market-fit (Wynter-style) protocols, stimulus set drawn from the canon, success thresholds, and a stop/revise decision rule — for the TALE Evaluate phase so the message is validated before any paid scale. It designs the test; it never runs the experiment or adjudicates a claim. Not for running the panel or A/B experiment — use send-experiment-designer or ad-test-designer; not for analyzing the results — use performance-analyzer; not for authoring the message itself — use message-system-architect. Message testing/comprehension testing/panel design/5-second test/message-market fit
Use when the user asks to “plan how our narrative lands on every surface,” “write per-surface message-match specs,” or “brief each creative builder from the canon”; maps the narrative-registry canon onto every flagship surface (homepage, pricing, store listing, sales deck, social bio, docs, email) as a per-surface message-match spec — what claim, pillar, proof, and objection reframe each surface must carry — and cuts a handoff brief to each discipline's creative builder (content-writer, ad-creative-builder, email-creative-builder, social-creative-builder, message-house-builder), so the same story lands consistently everywhere. Not for writing the finished surface copy — use each discipline creative builder; not for the tier-scoped launch asset manifest — use launch-asset-packager; not for scoring cross-surface consistency — use narrative-quality-auditor; not for claim adjudication — use offer-claims-registry. Narrative rollout/per-surface message match/creative handoff brief/canvas propagation
Enforce the no-useEffect rule when writing or reviewing React code. ACTIVATE when writing React components, refactoring existing useEffect calls, reviewing PRs with useEffect, or when an agent adds useEffect "just in case." Provides the five replacement patterns and the useMountEffect escape hatch
Use when the user asks to “read back” a paid campaign change, “did this ad change work,” or “compare ROAS/CPA before and after”; reads ROAS/CPA against a control over a fixed readback window and returns a Promote / Keep-testing / Rollback / Unproven readback decision with the math delegated to roi-calculator. Not for RQS scoring or veto adjudication — use ad-account-auditor; not for the ROI ratio math — use roi-calculator; not for cross-channel rollups — use performance-analyzer. Paid campaign retrospective/ROAS readback/ad performance attribution
Names and rebrands an app clone so it's the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide, and a sweep tool that finds anything of the original left in the codebase. Use when the user says "name my app", "rebrand the clone", "make it mine", "pick a name and colours", "logo brief", "brand voice", "check for leftovers", or after /replica-entrepreneur. Always runs before /replica-launch
Writes the launch for an app clone: the landing page built on the positioning angle, pricing set against the original's public pricing and its users' complaints, and the App Store and Google Play listing linted against the stores' limits and copycat rules. Use when the user says "landing page", "pricing", "how much should I charge", "App Store listing", "store screenshots", "launch plan", "Product Hunt", or after /replica-brand
Use when the user asks to “design an email A/B test,” “set up a multivariate subject/CTA test,” “run a send-time test,” “build a hold-out group,” or “is this email result statistically and practically material?”; produces a falsifiable hypothesis, one-variable-per-cell matrix, sample-size/MDE/duration/power plan, and an effect/uncertainty read from own ESP data. Applies only a precommitted owner-approved action rule; the helper never chooses a business action. Not for EQS/vetoes or writing the email. Email A/B test design/multivariate test/send-time test/hold-out group/significance assessment
Create, build, and deploy Webflow Cloud apps from the CLI (site-attached or project apps), and manage existing ones — apps, domains, environments, deployments, build/runtime logs, and environment variables including secrets. Use when initializing or deploying a Cloud app, importing an existing GitHub repository, setting up CI/CD (GitHub Actions or GitHub-linked deploys), setting or importing secrets, retrying or rolling back a deployment, diagnosing a failed build, or resolving app/environment/workspace IDs from webflow.json or env vars
Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.
Proactive security advisor and architectural remediation assistant for secure code development. Use to query threat models, historical vulnerability lineages, verified patch patterns, triaged false positives, and learned trajectory invariants before code edits or to generate architectural remediation plans for confirmed findings. Don't use for automated multi-pass red-team exploitation or fuzzing.
Use when the user asks to “build the norm card for this platform,” “what are the char limits and visible-fold cutoffs here,” “is the LinkedIn link-in-first-comment thing documented or folklore,” or “which of our platform cards are stale”; maintains the dated, versioned per-platform norm cards in the references/platforms/ pack — char limits, visible-fold cutoffs, hashtag norms, format/aspect specs, link and first-comment placement, disclosure-label mechanics, algorithm emphases (e.g. 小红书 search+saves weighting) — every row labeled platform-documented (official doc, Measured) or Estimated-folklore (named source) with last-verified and review-by dates, and any card past its review date flagged stale rather than trusted. Extends the single pack in place; never forks a second one. Not for picking which channels to run — use channel-portfolio-planner. Platform norm cards/character limits/fold lines/hashtags/algorithm emphasis/stale flags
Wire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402, or USDC/credit-card via MPP). Specialized app-integration path. Use when the user is building application code and no API key is available, they're an autonomous agent that needs to pay for itself, or they explicitly want x402/MPP. For normal app code with an API key, use `alchemy-api`. For live agent work in this session (querying, admin, automation), use `alchemy-cli` (preferred) or `alchemy-mcp`.
A reference for Chinese-language review communication: phrasing templates, severity labels (must fix / suggested change / for reference only), and responses to common anti-patterns in domestic teams. Invoke only when the user explicitly enters /chinese-code-review; do not trigger automatically based on context.
Convert Markdown documents into professional PDF white papers with an Apple design style. Supports full Markdown syntax (code blocks, tables, quotes, lists, etc.). Automatically generates a cover, table of contents, headers, and footers. Use for technical documents, white papers, tutorials, reports, and other Markdown documents that need professional typesetting
Use when the user asks to “keep the launch momentum going after launch week,” “plan a changelog / release-notes cadence as GTM,” or “is this update worth a relaunch”; produces a T+1→T+30 momentum plan — a launch-moment calendar (milestone / shipped-loop / badge moments only), announcement-tier routing (major = full-channel, medium = targeted, minor = changelog-only), a relaunch legitimacy call, spike-to-owned handoff briefs, and the next Tier-1 moment with launch-stacking spacing. Not for the 30-day content-reuse map or paid amplification execution — use content-amplifier; not for planning the next launch end to end — use launch-tier-planner. Preventing the week-two cliff/changelog-as-GTM/relaunch/next launch moment
Use when the user asks to “make everyone tell the same story,” “write our elevator pitch ladder,” or “build a spokesperson Q&A and approved boilerplate pack”; derives from the narrative-registry canon, message house, and brand voice a repeatable enablement kit — an elevator ladder (10-second / 30-second / 2-minute), a spokesperson Q&A (tough questions with on-canon answers), an approved boilerplate/bio pack (25 / 50 / 100-word), and a do/don't language sheet — so sales, support, founders, and partners repeat one consistent story. Not for the launch-day runbook — use launch-day-conductor; not for finished per-channel copy — use content-writer or each discipline creative builder; not for launch-window battle cards — use sales-enablement-kit; this kit never adjudicates a claim. Narrative enablement kit/elevator pitch ladder/spokesperson Q&A/approved boilerplate/usage do's and don'ts
Use when the user asks to "plan the participation ramp before we promote", "how much account history or karma do we need in this community", or "design entry incentives and member lifecycle for our own Discord"; produces the per-community pre-promotion warming plan — account-history/tenure expectations (estimated, named sources), a give-before-ask ledger spec, a per-community etiquette + rule digest with last-verified dates, and the warming → active graduation criteria that channel-registry requires as state-transition evidence — plus the owned-community variant (entry paths + member lifecycle for your own Discord/Slack/forum/企业微信私域). Not for launch-day submissions or T-0 threads — use community-launch-runner. Community warm-up/give before you ask/account cultivation/graduation criteria
Use when the user asks to “codify how our founder sounds,” “build a founder voice dossier,” or “set our content pillars”; runs an 80%-extraction interview over the user's OWN posts, emails, and decks (never competitor scraping, never an invented persona) and produces the versioned voice record — a per-platform register map (incl. 小红书/微信公众号), banned phrases, per-context disclosure lines (the ECHO C2 upstream), a few-shot bank built exclusively from own posts, and 3-5 content pillars with Estimated %-allocations — submitted via memory/events/channels.ndjson for channel-registry to store as voice-dossier.md, the record every Craft-phase skill reads first. Not for the brand-level voice canon — use brand-language-codifier; not for audience/persona research — use audience-mapper. Voice dossier/brand voice/founder voice/content pillars/disclosure statements
Drive the user's existing Chromium-family browser with deterministic Playwright. Use when asked to inspect, automate, test, or interact with a visible browser tab; continue an authenticated browser workflow; handle 2FA, passkeys, CAPTCHAs, or payment confirmation; record browser behavior; or capture an authenticated network flow.
Use when declaring or initializing Go variables, constants, structs, or maps — including var vs :=, reducing scope with if-init, formatting composite literals, designing iota enums, and using any instead of interface{}. Also use when writing a new struct or const block, even if the user doesn't ask about declaration style. Does not cover naming conventions (see go-naming).
Use when the user asks to “check if our surfaces have drifted from the canon,” “watch for competitor repositioning,” or “define when we should reposition”; produces a drift report — self-drift per flagship surface vs the narrative-registry canon over time (via wayback.py, change history Measured with as-of dates), competitor-repositioning alerts, an explicit repositioning-trigger condition set, and a D1/W1/M1 message-shift retro (intended vs actual pull-through, evidence-labeled) — feeding the TALE L drift-audit sub-items and the narrative-whiplash guardrail fact base. Not for the first-time consistency check before a surface ships — use narrative-cascade-planner; not for computing the TALE profile result or running the vetoes — use narrative-quality-auditor; not for echo-rate / AI-answer resonance measurement — use narrative-resonance-monitor. Self-drift monitoring/competitor repositioning alerts/repositioning triggers/narrative drift retrospective
Use when the user asks to "measure how our narrative is landing", "track echo rate against our canon lexicon", or "check how AI answer engines describe our brand"; produces a resonance report — echo rate (overlap of market language with the narrative-registry canon lexicon, method declared), AI-answer perception via tavily.py --answer (proxy-labeled), share-of-voice on a locked competitor panel (reusing share-of-voice-tracker), and resonance signals from bluesky.py / gdelt.py / pageviews.py — every number labeled Measured / proxy / User-provided, feeding the TALE E dimension and the upstream of the E1 evidence-integrity veto. Not for rebuilding share-of-voice machinery — use share-of-voice-tracker; not for own-site GA4/GSC analytics — use performance-monitor; not for scoring TALE profile result — use narrative-quality-auditor; not for adjudicating claims — use offer-claims-registry. 回声率/AI回答感知/份额之声/共鸣信号
Manage and monitor a personal stock watchlist with support for adding, removing, listing stocks, and summarizing their recent performance using data from 10jqka.com.cn. Use when the user wants to track specific stocks, get performance summaries, or manage their watchlist
VRChat World SDK 3 guide for scene and Inspector setup, component placement, optimization, and upload. Use for VRChat world scene configuration, VRC SDK components, layers, baked lighting, Quest/Android performance, Dynamics for Worlds, Build Panel warning triage, validation, and upload. Covers WorldQualitySettings, VRC_SceneDescriptor, VRC_Pickup, VRC_Station, VRC_Mirror, VRC_ObjectSync, VRC_CameraDolly, spawn points, collision matrices, PhysBone and Contact component placement, Box Contacts, Global Avatar PhysBone Colliders, and VRCPhysBoneCollider component setup. Active support / last verified: SDK 3.10.6. Triggers on: VRChat world scene, VRC SDK, scene setup, component placement, VRCBillboard, VRCPlacementZone, Quest support, light baking, SDK validation, Build Panel warning, Auto Fix, or red/yellow/white warnings. Do not use for UdonSharp C# or VRCTween calls; use unity-vrc-udon-sharp for runtime scripting. UdonSharp package, asmdef, and Version Defines work also belongs to that skill.
Provides instructions for building with Arc, Circle’s blockchain where USDC is the native gas token. Arc offers USDC as gas (no other native token needed), stable and predictable transaction fees, and sub-second finality for fast confirmation. These properties make Arc suitable for developers and agents building payment apps, DeFi protocols, or any USDC-first application where cost predictability and speed matter. Use when Arc, Arc Mainnet, or Arc Testnet is mentioned; when working with Arc-related smart contracts, configuring Arc in blockchain projects, bridging USDC to Arc via CCTP, or building USDC-first applications. Triggers: Arc, Arc Mainnet, Arc Testnet, USDC gas, deploy to Arc, Arc chain, stable fees, fast finality
Amazon competitor monitoring and competitive intelligence for sellers. Track pricing changes, inventory levels, new product launches, review velocity, and advertising patterns for competitor ASINs. Set up monitoring alerts for price drops, stock-outs, and market changes. Works on 12 Amazon marketplaces. No API key required. Use when: (1) monitoring competitor pricing strategies, (2) tracking competitor inventory and stock patterns, (3) detecting new product launches in your category, (4) analyzing competitor review velocity and ratings, (5) identifying market opportunities from competitor gaps, (6) setting up competitive alerts and benchmarks.
Model selection and recommendations for Alibaba Cloud Bailian. Activate when the user needs to select, recommend, or compare models, or describes an AI scenario or feature requirement that implies they need help deciding which model to use. The core intent is to help the user make a decision, not simply look up information. Trigger phrases: recommend a model, which one to choose, which is suitable, compare, build an XX, implement XX functionality, which model should I use, or a solution for an XX scenario. When the user asks about both model information and model selection, prioritize this skill; it reads model data internally to make recommendations.
Building CrewAI Flows on crewai 1.15.x: structured (Pydantic) vs dict state and state.id, @start/@listen/@router wiring, or_/and_ semantics, router labels vs method names, @persist (correct import, where it stores state, restore_from_state_id), checkpointing with CheckpointConfig, @human_feedback and HumanFeedbackResult.feedback, plot(), calling crews and agents from flow methods, kickoff inputs, and the `crewai create flow` scaffold. Use when writing or debugging a Flow subclass or main.py with `from crewai.flow import ...`, when a listener never fires or fires twice, or when you see errors like \"listen condition 'x' references the handler name 'x'\", \"cannot import name 'persist'\", \"'StateWithId' object is not subscriptable\", \"Flow state model must have an 'id' field\", \"--inputs requires a declarative flow definition\", \"invoked synchronously from within a running event loop\", or HumanFeedbackCollapseError.
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
OWASP Top 10 security audit and secure coding guidelines for Laravel + React/Inertia.js applications. Use when auditing for vulnerabilities ("run OWASP audit", "security review", "check my app security") or writing secure Laravel code involving auth, payments, file uploads, or API design. Triggers on security-related tasks, payment handling, authentication, or any request to audit a Laravel codebase.
Logo design principles and AI image generation best practices for creating logos. Covers logo types, prompting techniques, scalability rules, and iteration workflows. Use for: brand identity, startup logos, app icons, favicons, logo concepts. Triggers: logo design, create logo, brand logo, logo generation, ai logo, logo maker, icon design, brand mark, logo concept, startup logo, app icon logo
Interactive scientific and statistical data visualization library for Python. Use to create charts and visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG)
Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.
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.