GitHub
requesting-code-review
Use when completing tasks, implementing major features, or before merging
Skills IA Recherche
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Catégories: Recherche
Recherche Effacer les filtres
Explorer
GitHub
spellbook-auditing
Meta-audit skill for spellbook development. Spawns parallel subagents to factcheck docs, optimize instructions, find token savings, and identify MCP candidates. Produces actionable report.
GitHub
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans
GitHub
smart-reading
Use when reading files or command output of unknown size to avoid blind truncation and context loss
GitHub
finding-dead-code
Use when reviewing code changes, auditing new features, cleaning up PRs, or user says "find dead code", "find unused code", "check for unnecessary additions", "what can I remove".
GitHub
emotional-stakes
Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness
GitHub
devils-advocate
Use before design phase to challenge assumptions and surface risks
GitHub
receiving-code-review
Use when you have received code review feedback and need to process it. [DEPRECATED] Routes to code-review --feedback
GitHub
fun-mode
Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona
GitHub
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
GitHub
using-lsp-tools
Use when mcp-language-server tools are available and you need semantic code intelligence for navigation, refactoring, or type analysis
GitHub
code-quality-enforcement
Use when writing or modifying code. Enforces production-quality standards, prohibits common shortcuts, and ensures pre-existing issues are addressed. Invoked automatically by implementing-features and test-driv...
GitHub
tarot-mode
Use when session returns mode.type='tarot' - tarot archetypes collaborate via roundtable dialogue with instruction-engineering embedded
GitHub
implementing-features
Use when building, creating, or adding functionality. Triggers: "implement X", "build Y", "add feature Z", "create X", "start a new project", "Would be great to...", "I want to...", "We need...", "Can we add......
GitHub
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
GitHub
pr-distill
Use when reviewing large PRs to surface changes requiring human attention
GitHub
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
GitHub
instruction-optimizer
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability. Triggers: "optimize instructions", "reduce tokens", "compress skill", "make this shorter...
GitHub
project-encyclopedia
Use on first session in a project, or when user asks for codebase overview. Creates persistent glossary, architecture maps, and decision records to solve agent amnesia.
GitHub
executing-plans
Use when you have a written implementation plan to execute
GitHub
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
GitHub
worktree-merge
Use when merging parallel worktrees back together after parallel implementation
GitHub
debugging
Use when debugging bugs, test failures, or unexpected behavior
GitHub
merge-conflict-resolution
Use when git merge or rebase fails with conflicts, you see 'unmerged paths' or conflict markers (
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.