skills-improve
Capture and apply continuous improvements to Codex CLI skills during regular work. Use when a user wants to refine a skill, add a new skill after repeating a workflow, or keep skills up to date based on recent...
Découvrez les skills databases productivity tools, comparez leurs dépôts et consultez leurs instructions.
Capture and apply continuous improvements to Codex CLI skills during regular work. Use when a user wants to refine a skill, add a new skill after repeating a workflow, or keep skills up to date based on recent...
Review Agent Skills and provide findings and improvement suggestions from the perspective of official specification compliance and best practices. Use for skill review requests, SKILL.md quality checks, skill s...
Stack prompts in queue while agent runs, minimizing context switches to achieve sustained 6k lines per day output and preserved flow state. Use for heavy coding sessions, iterative refinements, rapid iteration...
Scrape external documentation (API references, library docs, protocol specifications) and generate Claude Agent Skills in SKILL.md format. Use when creating skills from documentation, integrating third-party kn...
Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-hop reasoning through consistent context. Use for repo-wide context, coding standards enforc...
Integrate external REST and GraphQL APIs with proper authentication (Bearer, Basic, OAuth), error handling, retry logic, and JSON schema validation. Use when making API calls, database queries, or integrating e...
Meta-skill to generate new Claude Agent Skills from natural-language descriptions. Use when creating skills, building custom workflows, generating new capabilities, or extending Claude's functionality. Outputs...
Two-phase workflow that generates explicit YAML plan before execution, with approval gates and checkpointing. Use for complex multi-file changes, refactoring, bug fixes with dependencies, or any task where mist...
Extract lessons from task failures using Reflector agent, merge insights via Curator pattern, achieving 10% accuracy improvement without context collapse. Use for post-failure analysis, lesson extraction, self-...
Convert repeated tasks into versioned skills, track performance gaps, and iteratively polish through Git version control. Use for identifying repeated patterns, improving skill consistency, tracking skill evolu...
Run multiple agent tasks in parallel cloud sandboxes with real-time progress monitoring, achieving 2x throughput vs sequential execution. Use for multi-repo tasks, independent bug fixes, concurrent feature deve...
Provides a systematic workflow for resolving GitHub Issues. Use this skill when assigned a GitHub Issue or when delegated by the Issue Auto-resolver.
Intelligent test generation from components, functions, and APIs
Automated git commit message generator from approved tasks
Backup and restore database and configurations with automatic scheduling
Quick API endpoint testing without external tools
Local cloud server providing API access to skills and files for Claude.ai
Common Supabase operations and workflows
Kanban Initializer role. USE WHEN board is empty OR user says /kanban-initializer. Scaffolds new projects with feature breakdown.
Kanban Sprint orchestrator. USE WHEN user says /kanban-sprint OR wants to run a full automated development cycle.
Kanban Agent role. USE WHEN user says /kanban-agent OR wants to work on assigned kanban tasks as an agent.
Clone GitHub repositories into Daytona sandbox environments and set up development environments. Use when Claude needs to: (1) Clone a repository into a sandbox, (2) Set up a development environment from a Git...
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 avoid...
Browser automation scripts for testing, screenshots, and web interaction. 16 scripts with persistent state.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.