Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when creating or improving persuasive copy, launch offers, fundraising appeals, onboarding prompts, sales pages, calls to action, or behavior-change messages where the goal is effective persuasion without deception, coercion, fake proof, fake scarcity, or overstated authority.
Use when exactly one of several properties should be present. Use when modeling mutually exclusive options. Use when building component props with alternative configurations. Use when designing API parameters that have variants.
Executes exactly one planned Jira or GitHub work-item task after critique approval. Use when a numbered task should move through kickoff, implementation, documentation, requirements verification, clean-code, architecture, and security gates, targeted fix cycles, tracker finalization, and a final report
Create and run LangWatch experiments for pre-deployment batch testing. Use when the user wants to test an agent against a dataset, compare prompts or models, benchmark quality, detect regressions, or add a CI quality gate. Do not use for production monitoring or guardrails.
Takes a GitHub PR URL or the current branch and writes a plain-English explanation of what it does and why, then posts it as a PR comment. Use when asked to explain a PR, summarize a pull request, write a plain-English description of a PR, add a summary comment to a PR, or understand what a PR changes. Trigger when a user says "explain this PR", "summarize this pull request", "what does this PR do", "add a comment explaining the PR", or shares a GitHub PR URL and asks what it does.
Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
Take a new feature or product update and generate the full launch kit: changelog entry, email announcement, LinkedIn post variants, in-app banner text, Twitter/X thread, and internal sales enablement one-pager. Pure reasoning skill that chains product context with audience-specific copy generation. Use when a product marketing team needs to turn a feature spec into launch-ready assets fast.
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items. Use when asked to prioritise features, rank a backlog, decide what to build next, or evaluate tradeoffs between competing ideas. Produces a scored, ranked feature list with framework-specific tables, recommended build order, deprioritised items, and assumptions made.
Guides creation and modification of domain feature systems organized under a systems/ directory. Covers directory layout, API service layer patterns, TanStack Query hooks (queries, mutations, optimistic updates), React context and XState store conventions, hook organization, and public API barrel exports. Use when adding a new domain system, extending an existing one, or fixing bugs in a system-layer codebase. Don't use for generic React component work, backend API implementation, or codebases not organized around a systems/ domain pattern.
Capture how the system feels — energy, momentum, burnout, breakthrough. Emotional intelligence for Oracle-human collaboration. Use when user says 'feel', 'how are we', 'energy check', 'burnout', 'momentum', or wants emotional awareness of the work.
Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.
Write a structured design brief for a Figma design task from a product requirement or feature request. Use when asked to write a design brief, create a design spec for Figma, turn a PRD into design requirements, or brief a designer on what to build in Figma. Produces a brief with goals, scope, user flows, components needed, constraints, and success criteria.
Measure laid-out frames of a running UI against a Figma living artifact (inventory + spec + Verify section). Use when checking pixel alignment / 对照 Figma 验收 after implementation, including light/dark or hover/variant states (switch theme and state, measure each row). Non-document UIs use a layout-probe; source-constant comparison is not a pass. Fix and remeasure in the same run until overall PASS, without asking a person. Critical unmeasured rows fail overall. The checker must exit 0; a layout probe mounts the shipping parent. An openable channel must cite a saved, non-empty screenshot file; layout-probe may say not-openable. Triggers — 「检查像素对齐」「对照 Figma 验收」「设计保真检查」「是否对齐稿面」「figma 保真检查」「暗黑模式验收」「多主题保真检查」 / verify Figma fidelity, pixel check, dark mode fidelity check, multi-theme verify. Do NOT use as the primary implementation workflow (use figma-pixel-implement) or for code→Figma.
Plan prototype interactions and flows for user testing in Figma. Use when asked to plan a Figma prototype, set up prototype interactions, define what to prototype for a user test, or prepare a Figma prototype for usability testing. Produces a prototype scope, interaction specification, test task scripts, and Figma setup guide.
Design a spacing and layout token system for a Figma design system. Use when asked to create a spacing system, define layout tokens, set up a grid system, build a spacing scale, or establish layout foundations for a Figma file. Produces a complete spacing scale, grid definition, component spacing conventions, and Figma implementation guide.
This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies
AI film editor for post-production, footage organization, pacing, video editing workflows. Use when: editing, post-production, cuts, assembly, rough cuts, final cuts, color, sound. Integrates with video generation. Keywords: film, editing, post, cuts, video.
Build an Ishikawa diagram, cause and effect analysis, or 6M fishbone to brainstorm and categorise all possible causes before narrowing to root cause with 5-Why. Covers Man, Machine, Method, Material, Measurement, and Environment (Mother Nature). Essential for 8D D4 brainstorming sessions and CAPA root cause investigations.
Orchestrate the path from a raw research idea to a formal claim with a defensible proof design — drawing the hypothesis out of the idea, stating it as a precise theorem/claim, and designing (and auditing) the proof strategy. Use whenever the user says "help me turn this idea into a theorem", "I have a hunch, can we make it rigorous", "design a proof for this", "what would I need to prove this", "formalize this claim", "is this provable and how", or hands over an informal conjecture they want to develop into a formal result. This is a ROUTER that sequences existing singleton skills; it does not write the proof itself. Use flow-learn-new-topic or flow-deep-understanding when the goal is to understand existing work rather than formalize the user's own idea. Use gap-finder when the starting point is an existing paper's weakness rather than a fresh idea.
Runs a multi-step procedure as a Python DAG, so ordering, branching and retries are enforced by the runner rather than described in prose a model can generate past. Use for "run these steps in order and retry the flaky one until the check passes", "build a pipeline that fetches, validates, then skips the upload when nothing changed", "make sure these steps cannot be skipped", "resume from where it broke instead of redoing the expensive early stages", "run these independent calls at once and merge the results", or any procedure of 3+ steps with branches, input contracts, or side effects that must not block the critical path. Primitives are depends_on, when=, validate=, retry_until=, detached= and journal_path=. Not for a single sequential call, for steps needing reasoning between them that no predicate captures, or for async and distributed work. To audit whether one verification check can actually go red, use gating. To fan work out across many subagents, use a dynamic workflow.
Runs and records showcase/flutter_test_app dogfood iterations (tool_quality_rubric, run_dogfood_eval.sh, dogfood_web_eval.yaml). Use when scoring MCP/intentcall quality, appending iteration N, comparing regressions, or CI static/weekly eval gates.
Maintains the showcase/flutter_test_app macOS showcase, native intentcall hooks (codegen, app_links invoke), and VM MCP validation. Use when editing macOS Runner, intentcall_codegen.sh, macOS dogfood, Screen Recording capture, or comparing macOS parity to web WebMCP.
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
Implement an Issue, plan file, or free-text description on a feature branch, following project standards, and stop at an open PR. Asks the user to approve the plan unless --unattended. Use when the user or an orchestrating agent asks for forge-implement or to take an Issue to a PR, not for a quick edit or fix in the current session; use forge-ship to also run review.
Review and design form UX for signup, checkout, onboarding, settings, support, enterprise lead forms, creator submission, marketplace listing, payment, cancellation, data export, and admin workflows across web, mobile, and desktop. Use when improving form completion, clarity, accessibility, validation, errors, field order, progressive disclosure, autosave, trust, fraud controls, and support evidence.
Turn a feature request, stakeholder request, idea, complaint, or vague design assignment into a clear UX problem frame with user outcome, evidence, constraints, assumptions, unknowns, and success signals. Use before solutioning when the real problem or reason for the work is unclear.
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.