workflowharness
WHAT: Ralph Wiggum external harness pattern for autonomous Claude Code loops with spec-based progress tracking. WHEN: implementing multi-step features, refactoring with clear criteria, autonomous development. K...
Skills correspondant au nom, à la description ou à l’auteur GitHub.
WHAT: Ralph Wiggum external harness pattern for autonomous Claude Code loops with spec-based progress tracking. WHEN: implementing multi-step features, refactoring with clear criteria, autonomous development. K...
This skill should be used when the user asks to "change the commit attribution", "remove the co-authored by", "stop adding the co-authored by", "change Claude's name", "configure the PR attribution", "update at...
Workflow step compliance guidance with mandatory step reminders and visual progress tracking. Reminds Claude to complete all workflow steps before PR creation.
Analyzes repositories for AI agent development efficiency. Scores 8 aspects (documentation, architecture, testing, type safety, agent instructions, file structure, context optimization, security) with ASCII das...
This skill should be used when creating Docker containers for Claude Code sandboxing, configuring isolated development environments, setting up Docker volumes and persistence, configuring port forwarding for sa...
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Create and register MCP tools for the Hub. Use when adding new tools that should be available via Claude Desktop/Bridge, or when linking existing tools with their skills for maintainability.
Long-running coding sessions (background + tmux) for Codex, Claude, OpenCode, or Pi.
This skill should be used when the user wants to create a git worktree for parallel Claude Code sessions. This allows multiple AI sessions to work on different branches simultaneously.
Automatically discovers coding standards from project files (CLAUDE.md, tsconfig.json, ESLint, etc.) and generates validation scenarios for the benchmarks framework. Use when user wants to generate test scenari...
Validate .claude/ configuration quality and compliance with 2026 best practices. Use when auditing project setup, checking skills/mcp/hooks compliance, or validating local-first configuration. Do not use for st...
Install, manage, and remove Claude skills from GitHub repositories. Use when you need to add new skills from git or manage installed skills.
Proactively capture and archive project discoveries during work. Maintains CLAUDE.md by capturing working commands, architectural decisions, gotchas, and insights as they emerge during development. Use during a...
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks (skills/commands/a...
Configure and audit project guardrails in .claude/ configuration with multi-workflow orchestration. Automatically detects INIT/SECURE/AUDIT/REMEDIATE workflows. Creates component-scoped hooks with PreToolUse/Po...
Orchestrate parallel Claude Code agents across git worktrees for large implementations
.claude/skills/以下に新しいスキルを作成するためのガイドとテンプレートを提供します。スキルの目的、アクティベーション条件、チェックリスト、詳細なリファレンス、例、テンプレートの作成を支援します。
Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation for complex tasks, refactors, or API changes.
Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or API integration.
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
Analyze the current repository and create or refresh .claude/PROJECT.md to match the project. Use when PROJECT.md is missing, stale, or the user asks to generate/update project-specific rules, structure, comman...
Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (plan validation + implementation review)
Universal guide for all unmangleJS pass development tasks. Covers creating, modifying, debugging, refactoring, reviewing, and documenting passes. Integrates with existing project documentation - see CLAUDE.md f...
Model Context Protocol server for Sigil MPC signing. Use for deploying Sigil as a universal agent-compatible signing server that works with Claude Desktop, VS Code, and any MCP-compliant client.
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.