Marketplace de Skills
des procédures prêtes pour vos agents

Use when creating new React components. Generates them with TypeScript, Tailwind, and colocated tests.

Use when refactoring or adding Tailwind classes. Enforces ordering, dedupes utilities, replaces arbitrary values with design tokens.

Use when reviewing or writing UI code. Flags missing ARIA, keyboard handlers, focus traps, and contrast issues before shipping.

Use when authoring a PostgreSQL migration. Enforces backwards-compatible patterns and concurrent index creation.

Use when adding or modifying a REST endpoint. Enforces the project's auth check, validation, error shape and pagination conventions.

Use when integrating Stripe. Generates payment-intent endpoint, idempotent webhook handler, and the orders table migration.

Use when adding or fixing CI workflows. Generates idempotent GitHub Actions with caching, matrix builds, and proper secret scoping.

Use when writing a Dockerfile. Multi-stage build, slim base image, non-root user, sensible CMD/ENTRYPOINT split.

Use when writing or updating tests. Picks the right matcher style for the project and avoids brittle assertions.

Use when reviewing a diff or PR. Checks readability, edge cases, error handling, security, and tests in that order.

Use when handling API keys, tokens, or any credential. Refuses to commit, hardcode, or log them; suggests safer storage.

Use when adding a README to a project or sub-package. Generates the minimum useful sections without filler.

Use when writing a commit message. Conventional Commits format with a clean scope and a why-not-what body.

Use when a function exceeds 40 lines or a file exceeds 300. Extracts cohesive sub-units with names that describe intent.

Used to help me create more creative prompts. When I am frustrated about not being able to describe something beautiful, interesting, creative, or whatever, this is the skill to use.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Use while writing, changing or reviewing code whenever the change adds an exported or importable name, creates a module, class, component, helper, hook, service or wrapper, centralizes repeated code, or changes an API. Ousterhout rules (deep modules, information hiding, pulling complexity down) plus the invariant test for sharing code, the reader-cost test, and a required design note at the end.

Apply contextual software architecture guidance when analyzing system boundaries, quality requirements, communication, styles, decisions, risks, or evolution.

Standardizes user requirements into structured Agile user stories with Given-When-Then acceptance criteria.

Fetches web page content using Gemini CLI when Claude's native WebFetch fails or for explicit URL fetching. Returns clean Markdown.

Expert backend architect for Node.js, Python, and modern serverless/edge systems. Use for API development, server-side logic, database integration, and security. Triggers on backend, server, api, endpoint, database, auth.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Use when refactoring or building React views, fixing element overlapping, updating text inputs, and parsing raw strings.

'Assist with api testing helper operations. Auto-activating skill for

Enforce Conventional Commits format for git commits, including project-specific type/scope conventions (plugin name as scope) and squash-vs-new-commit strategy selection.

Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.

Audit test suite health — find flaky tests, slow tests, coverage gaps, and testing anti-patterns. Use when asked to "audit tests", "fix flaky tests", "why are tests slow", "test health", or "improve test suite".

Audit npm projects for Shai-Hulud-class supply-chain exposure: lifecycle scripts, Git dependency prepare hooks, release-age gaps, publish-token exposure, trusted publishing, signed releases, and verifier docs.

Use when user says 'release', 'リリース', 'publish', 'vtag', 'version up', 'バージョンアップ', 'bump version', 'prepare release', 'ship version', or discusses merging to main/develop. Guides through version bump and release flow.

Use when editing or refactoring frontend React views, modifying container widths, adjusting dark-mode CSS variables, styling user chat input elements, and handling real-time data lookups.

Generate comprehensive test cases including edge cases, stress tests, and counter-examples for algorithm correctness verification. Supports random generation, constraint-based generation, and brute force oracle comparison.

'Generate express route generator operations. Auto-activating skill for

Use when connecting frontend endpoints to the forecasting server or updating client-side states to guarantee absolute numbers alignment.

Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.

Use when refactoring messy code, improving readability, eliminating code smells, or applying SOLID/DRRY principles — always with tests as safety net

Helps maintain documentation pages based on the Diataxis method. Analyzes existing docs, classifies pages into tutorials/how-to/explanation/reference categories, identifies gaps, and helps create or restructure documentation following Diataxis principles. Use when user mentions documentation structure, Diataxis, doc categories, tutorials vs how-to guides, or reorganizing docs.

>

Detect ANY credential/secret flowing to ANY output sink. Use when asked about "credential leakage", "secret logging", "sensitive data exposure", "CWE-532", "password in logs", "token exposure", or security logging issues.

Use when managing database schema transitions, writing math rate routes, and creating server endpoints.

Use whenever code being written or reviewed creates or changes a boundary — a new module, class, component, helper, hook, service, or wrapper; any extraction or centralization of shared code; any "let's make this reusable" moment — and when explicitly reviewing, refactoring, or designing a module. Judges whether an abstraction earns its keep: module depth, whether to hide a design decision, whether duplicated code protects a shared invariant or merely rhymes, whether an interface is stable. Guards against mechanical SOLID/Clean Code that produces many shallow classes. Also defines the reader-cost test (code that is cheap for humans and agents to read and change) and the procedure for refactoring an existing codebase to this standard.

Use while writing or changing code, before calling the task done, whenever the change adds an exported or importable name, creates a module, class, component, helper, hook, service or wrapper, or centralizes repeated code. Author-time checklist for building deep modules: name the decision the boundary hides, pass the depth and invariant tests, fix problems instead of relocating them, never split on size alone, and end with a short design note. Compact companion to ousterhout-quality-program, which remains the full review lens.