ralph-specum-start
This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Specum in Codex to start or resume a spec.
498 repo starsObserved in 2 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
re2-feedback-loops
Apply RE2 Feedback Loops to create mechanisms where system outputs influence future inputs.
498 repo starsObserved in 2 repos
Agent Building
recompile-workflows
Regenerate and post-process all agentic workflows. Use when gh-aw is updated, workflow .md files change, or when asked to recompile/regenerate workflows.
498 repo starsObserved in 2 repos
Agent Building
reflect-status
Show reflection configuration and learning statistics. Activates for reflect status, reflection status, memory status, learnings status.
498 repo starsObserved in 2 repos
Agent Building
reload-context
ユーザーメモリ、プロジェクトメモリ、READMEを再読み込み。「コンテキストを再読み込み」「設定をリロード」「CLAUDE.mdを読み直して」と言われた時、またはclear後にコンテキストを復元したい時に使用
498 repo starsObserved in 2 repos
Agent Building
remembering-conversations
ALWAYS USE THIS SKILL WHEN STARTING ANY KIND OF WORK, NO MATTER HOW TRIVIAL. You have no memory between sessions and will reinvent solutions or repeat past mistakes UNLESS YOU USE THIS SKILL. Gives you perfect recall of all your past conversations and projects.
498 repo starsObserved in 2 repos
Agent Building
retro-memory-enterprise
Enterprise post-session retrospective: writes evidence-ledger, delegates to retro-auditor subagent (isolated context), updates .claude/rules, runs validations.
498 repo starsObserved in 2 repos
Agent Building
role-prompting
AIエージェント・システムロール・ペルソナのための役割プロンプト設計スキル。 責務分離、専門家思考様式の適用、効果的なプロンプト構造化の指針を提供する。 Anchors: • The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: DRY原則・責務分離 / 目的: ロール設計の品質向上 • Domain-Driven Design (Eric Evans) / 適用: ユビキタス言語・境界づけられたコンテキスト / 目的: 責務境界の明確化 • Thinking, Fast and Slow (Daniel Kahneman) / 適用: 専門家思考様式の理解 / 目的: 適切な思考モード設計 Trigger: Use when designing AI agent roles, system prompts, persona definitions, or separating responsibilities between agents. role prompting, persona design, agent role, system prompt, responsibility separation, ロール設計, ペルソナ
498 repo starsObserved in 2 repos
Agent Building
running-codeagent-tasks
Executes codeagent-wrapper for multi-backend AI code tasks supporting Codex, Claude, and Gemini. Use when running complex code analysis, large-scale refactoring, or parallel AI tasks with backend selection. Triggers include "codeagent", "multi-backend", or "parallel code tasks".
498 repo starsObserved in 2 repos
Agent Building
sandbox-setup
Configure Claude Code sandbox settings for this repository
498 repo starsObserved in 2 repos
Agent Building