Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Add a timed activation window to a GrowthBook feature flag rule — automatically enable it at a start time and/or disable it at an end time. Use when the user says "turn this on at 9am", "schedule the flag to go live Friday at noon", "disable the rule after the sale ends", "set an end date on this rule", "run this rule during the promotion window", or "time-gate this rule". Applies to force and rollout rules. For multi-step progressive rollouts with intervals between steps, use flag-ramp. For the broader campaign of rules around this schedule, use flag-targeting first.
Governed workflow for AI-assisted coding on a real repo. Triggers: bounded tasks, file scope, task ledgers, claim-before-implement, evidence trails, critique/review/security gates, or multi-agent/multi-repo coordination. Use on any mention of "FORGE", `docs/forge/`, or governed development, or when agents drift outside scope. Not for one-off edits or unstructured review.
Plateforme de conception, planification et spécification de nouveaux produits logiciels. Transforme une idée initiale en un plan d'implémentation exhaustif, sans ambiguïté, suffisamment précis pour être exécuté par une IA même peu performante. Couvre PRD, roadmap, benchmarks, design UI/UX, architecture, découpage en slices, plan d'implémentation par slice, plan de tests, analyse d'impact, et validation automatique des plans (mode Fast Track). Utiliser pour tout nouveau projet (greenfield) — de l'idée vague jusqu'au plan prêt à coder. Ne pas utiliser pour migrer un projet existant vers une autre stack, ni pour un travail sur du code legacy. — Design, planning and specification platform for new software products. Turns a rough idea into an exhaustive, unambiguous implementation plan precise enough for a low-capability model to execute: PRD, roadmap, benchmarks, UI/UX design, architecture, slice breakdown, per-slice implementation plans, test plan, impact analysis, and automated plan validation (Fast Track mode). Use this skill for any greenfield project, from a vague idea to a code-ready plan. Do not use it to migrate an existing project to a different stack, or to work on legacy code.
Connects a website or app form to Forminit (forminit.com), the headless form backend, creates one when there is none (a paste-ready HTML form when there is no code to edit), or fixes a broken Forminit integration. Works with HTML, React, Next.js, Vue, Nuxt, Svelte, SvelteKit and Astro: maps each input to fi-* field names such as fi-sender-email and fi-checkbox-topics[], wires the submit with the forminit SDK and keeps the existing design and logic. Use when the user mentions Forminit, gives a Forminit Form ID, pastes a Forminit setup prompt, has forminit.com/f/ URLs or fi-* names in code, or hits Forminit errors like FORM_NOT_FOUND. Also use when a contact, lead, quote, booking, RSVP, feedback, waitlist or job application form on a static or AI-built site must deliver submissions without a backend. Not for login, account signup, password, payment or search forms.
Help founders run companies using contrarian principles with real examples from successful founders. Challenge standard advice designed for professional managers. Use when facing strategic decisions, organizational challenges, or receiving conventional advice that conflicts with founder instincts.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Frontend patterns for Rails applications using Slim templates, Stimulus JavaScript framework, CSS with Optics utilities. Use when building views, adding interactivity, styling components, or when the user mentions Slim, Stimulus, JavaScript, CSS, or frontend development.
Plan and run an early-stage fundraising process and produce a Fundraising Pack (raise decision memo, round design brief, pitch narrative + deck outline, investor pipeline + tracker, outreach/follow-up scripts, diligence checklist). Use for fundraising, raising capital, venture capital, pitch deck, investor outreach, pre-seed, seed. Category: Career.
Guides implementation of the GDPR accountability principle under Articles 5(2) and 24, including documentation requirements for policies, DPIAs, RoPA, training records, and breach logs. Activate when establishing or reviewing accountability measures, preparing evidence portfolios, or demonstrating compliance to supervisory authorities. Keywords: accountability, Article 5(2), Article 24, documentation, compliance evidence, governance.
Guides the GDPR Article 36 prior consultation process with supervisory authorities when a DPIA indicates high residual risk. Covers timeline requirements, documentation, and outcome handling. Activate when DPIA residual risk remains high or when preparing regulatory submissions. Keywords: prior consultation, Article 36, DPIA, high risk, supervisory authority.
Guides conversion of gap analysis findings into phased implementation plans with milestones and risk-based prioritisation. Activate when building compliance programmes or allocating privacy budgets. Keywords: remediation roadmap, implementation plan, phased approach, prioritisation.
Unified deep research tool. Dual mode: Deep (Gemini Deep Research API, with planning and verification) / Lite (Gemini CLI quick draft). Supports the user providing ideas, materials and a discussion framework, and executes after confirming the outline over multiple rounds of conversation. Trigger scenarios: deep research/investigation/literature review/competitive analysis/industry report/quick research
Write or revise AGENTS.md per embedded output contract to establish project identity, authoritative sources, and behavioral expectations. Use when creating Agent entry for new projects, auditing existing AGENTS.md, or adopting the AI Cortex entry format.
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
Draft a review-friendly commit message and create the Git commit non-interactively. Use when you need to commit either the already-staged changes or the full current working tree relative to `HEAD`, while preserving a review-friendly message and footer handling. Trigger for requests such as the skill `git:commit` or the skill `git:commit` with `HEAD`, especially when the user wants safe staging behavior and a clean commit created from the drafted message.
WHEN: User is writing Go code, asking about Go patterns, reviewing Go code, asking "what's the best way to...", "how should I structure...", "is this idiomatic?", or any general Go development question. Trigger this skill liberally for ANY Go-related development work as a routing hub to specialized skills. WHEN NOT: Non-Go languages, questions entirely unrelated to programming
Modernize Go code with the rebuilt go fix command in Go 1.26+. Applies safe, version-aware rewrites to newer language and stdlib idioms (interface{} to any, 3-clause loops to range-over-int, min/max, strings.Cut, new(expr), and 20+ more), iterating to a fixed point and verifying the build afterward. Use whenever Go code should be modernized, cleaned up, or made idiomatic — after a go.mod version bump, when old-style or AI-generated patterns accumulate, when migrating callers off deprecated or renamed APIs (go:fix inline directives), when the user mentions go fix or gofix, or to enforce modern idioms as a CI gate. Not for gofmt formatting, dependency upgrades, or go vet bug-finding.
Use gogcli for Google Workspace CLI operations (Drive/Sheets/Docs/Slides). Trigger when a user asks to check, list, search, export, read, or update Google files via gogcli; when a Google URL/ID needs parsing; when auth/account selection or safe read-only workflows are needed; or when troubleshooting gogcli access/errors. Do NOT load for: general file operations, non-Google cloud storage, or standard shell commands.
Searches Google's public careers site (careers.google.com) via the Crawlora API and pulls single job postings by id, returning clean JSON. Use when the user wants to search Google Jobs, see what roles Google is hiring for in a location, or pull the full detail of a specific Google Jobs posting.
Use when scanning an AAB or APK for Google Play policy compliance before submission, or checking signing key consistency across releases. Trigger when the user mentions preflight, compliance check, policy scan, pre-submission check, signing key consistency, certificate mismatch, or wants to verify their AAB/APK meets Google Play requirements. Also trigger for questions about restricted permissions, target SDK requirements, 64-bit compliance, hardcoded secrets detection, Data Safety form reminders, foreground service declarations, or App content declarations
Apply event study methodology to measure abnormal returns and cumulative abnormal returns (CAR) around corporate or market events. Use this skill when the user needs to quantify the market impact of announcements, design event and estimation windows, or when they ask 'did this event affect stock price', 'how do I calculate abnormal returns', or 'what is the market reaction to this announcement'.
Apply panel data analysis with fixed effects, random effects, and dynamic GMM to exploit longitudinal variation and control for unobserved heterogeneity. Use this skill when the user has repeated observations over time for multiple entities, needs to choose between FE and RE via Hausman test, or when they ask 'how do I control for firm-specific effects', 'fixed or random effects', or 'how to handle endogeneity in panels'.
Apply Agency Theory (Jensen and Meckling, 1976) to diagnose principal-agent problems — moral hazard, adverse selection — and design governance mechanisms to align interests. Use this skill when the user needs to analyze conflicts of interest between owners and managers, design incentive or monitoring structures, evaluate corporate governance effectiveness, or when they ask 'how do we ensure managers act in shareholders interest', 'why is this incentive plan failing', or 'what governance mechanisms reduce agency costs'.
Use for any question about a codebase, its architecture, file relationships, or project content—especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools
Production recipes for cursor and pointer-driven GSAP animations. Companion to official gsap-core and gsap-performance skills (API reference). Triggers: cursor follower, cursor effect, mouse follower, magnetic button, spotlight cursor, cursor trail, particle trail, spring cursor, elastic cursor, pointer animation, custom cursor, cursor glow, clipPath cursor, quickTo cursor, image preview hover, perspective tilt, 3D tilt cursor. Non-triggers: Not for hover/tilt card effects (use gsap-interact), not for scroll animations (use gsap-scroll), not for general mouse events without cursor effects. Outcome: Produces cursor-driven animation effects with proper cleanup, overwrite management, and performance optimization (quickTo, ticker, will-change lifecycle).
Production recipes for GSAP SVG animations. Companion to official gsap-plugins skill (API reference). Triggers: SVG animation, GSAP SVG, path drawing, strokeDashoffset, DrawSVG, drawSVG, SVG morph, MorphSVGPlugin, circuit tree, circuit board, CTAHud, HUD animation, pulse ring, scallop wave, SVG stagger, SVG fill, SVG stroke, SVG cleanup, feGaussianBlur, SVG glow, SVG blink, shape overlay, page transition, section transition, smooth morph, morph interpolation, dynamic morphing, SVG curtain, shape transition. Non-triggers: Not for text animation (use gsap-text), scroll reveals without SVG (use gsap-scroll), mouse interactions (use gsap-interact), or non-SVG visual effects (use gsap-vfx). Outcome: Produces SVG animations — path drawing, morphing, circuit board patterns, HUD systems, pulse rings, and scallop waves.
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.