发现 Skills

Manages task queues for asynchronous job execution with retry policies and rate limiting.

Orchestrates multi-agent workflows (sequential pipelines, supervisor-worker delegation, group chat coordination, parallel task execution with result synthesis) for complex AI system coordination.

>-

Audits and improves CLAUDE.md files by scanning repositories and evaluating quality against templates. Outputs a quality report with scores and applies targeted updates. Use for CLAUDE.md maintenance and optimization or when reviewing what project instructions should contain.

Generates implementation skeletons aligned with project conventions. Supports endpoints, UI components, IaC modules, migrations, tests, and services. Uses project.yaml context and domain rules to prefill structure and guardrails.

Guide a person through healing modalities including energy work (reiki, chakra balancing), herbal remedies, basic first aid stabilization, and holistic techniques (breathwork, visualization, body scan). AI coaches the practitioner through assessment triage, modality selection, energetic connection, remedy preparation, and integration. Use when a person describes a physical ailment or injury, reports energetic imbalance (fatigue, emotional stagnation), wants coaching through a holistic breathwork or visualization session, or needs post-meditation integration with directed healing attention.

Plan garden activities using solar, lunar, and biodynamic calendars. Covers USDA hardiness zones, frost date calculation, equinox/solstice anchoring, synodic lunar cycle (waxing/waning), ascending/descending moon, Maria Thun biodynamic calendar (root/leaf/flower/fruit days), succession planting schedules, and seasonal task planning. Use when planning a new growing season and needing a planting schedule, integrating lunar or biodynamic timing into garden practice, calculating frost dates and planting windows for a specific zone, setting up succession planting for continuous harvest, or conducting end-of-season review.

ALWAYS auto-load at conversation start and keep active for the entire session without being asked. Universally applicable to every task and response. Enforces concise, token-efficient behavior to minimize API costs.

Comprehensive guide to agent-browser usage patterns, test seam planning workflow, browser testing optimization patterns, and when to use agent-browser vs alternatives. Use when working with web applications, frontend tasks, or when development servers are running.

This skill should be used when the user asks to "upgrade a sample", "update to new Dev Proxy version", "bump the version", "update schemas", or needs to upgrade existing Dev Proxy samples to a new version with updated schemas and documentation.

This skill should be used when the user asks to "validate a sample", "check my sample", "review before submitting", "verify sample structure", or needs to validate a Dev Proxy sample for correctness before submission.

Incorporate documents into an existing or new workflow and advance stages intelligently

Reverse engineer and analyze a specific feature in Claude Code's source. Use when the user wants to understand how a Claude Code feature works internally, or when asked to analyze Claude Code internals.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Create a staged refactor plan for a module. Use when a mid-level developer needs a safe refactor path.

Central authority on git hook implementations, modern best practices, and tooling for .NET/C#, JavaScript/TypeScript, Python, and polyglot repositories. Covers framework selection (Husky.Net, lefthook, Husky, pre-commit), setup workflows, Conventional Commits, semantic versioning, secret scanning (gitleaks, TruffleHog), performance optimization, CI/CD integration, testing strategies, and team collaboration patterns. Adaptive to project scale from solo developers to enterprise teams. Use for setting up git hooks, configuring pre-commit/commit-msg/pre-push hooks, integrating dotnet format/dotnet test, ESLint/Prettier, Black/Ruff/mypy, commitlint, choosing between frameworks, optimizing hook performance, enforcing code quality, automating testing, and troubleshooting hook issues.

Review pull requests thoroughly and critically. Focus on correctness, security, and quality.

Automate the creation and updating of a CHANGELOG.md file based on Semantic Versioning (SemVer) and “Keep a Changelog” principles. Use this skill when you need to summarize changes between the current HEAD and the latest git tag, or when initializing a new changelog for a project.

ALWAYS use for ANY C# operation: renaming (files/classes/methods/properties/namespaces), finding references/usages ("where is X used"), finding definitions ("where is X defined"), understanding code structure (hierarchies/dependencies/relationships). Roslyn-powered semantic analysis ensures all references are updated correctly across the entire solution.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Start an autonomous improvement loop that finds and fixes issues in the current project. Each cycle has three phases — a maintainer agent keeps existing PRs healthy, an executor agent finds one improvement, and an evaluator agent reviews it before raising a PR. Cycles run with a 20-minute gap between them. Use this skill when the user wants to run continuous autonomous improvements, background PR generation, automated code quality sweeps, or hands-free codebase maintenance. Trigger on phrases like "auto improve", "background improvements", "keep finding things to fix", "autonomous PRs", or "improvement loop".

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Infrastructure AI : LiteLLM, Langfuse, RAG, modeles LLM, embeddings, vector stores, evaluation, observabilite AI.

Capture et organisation des connaissances