coding-agent
openclawDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
agent-harness-construction
affaan-m设计和优化AI代理的动作空间、工具定义和观察格式，以提高完成率。
eval-harness
affaan-mFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
evaluating-llms-harness
davila7Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
evaluating-code-models
davila7Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
nemo-evaluator-sdk
davila7Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
harness-writing
trailofbitsTechniques for writing effective fuzzing harnesses across languages. Use when creating new fuzz targets or improving existing harness code.
coverage-analysis
trailofbitsCoverage analysis measures code exercised during fuzzing. Use when assessing harness effectiveness or identifying fuzzing blockers.
flow-next-ralph-init
gmickelScaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.
cli-e2e-test-harness
a5c-aiSet up E2E test harness for CLI applications with process spawning and assertions.
eval-harness
sangrokjungFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
evaluating-llms-harness
sangrokjungEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
init-harness
Creates AI agent task management structure with feature backlog (ai/tasks/), TDD enforcement, and progress tracking. Use when setting up agent-foreman, initializing feature-driven development, creating task backlog, or enabling TDD mode. Triggers on 'init harness', 'setup feature tracking', 'create feature backlog', 'enable strict TDD', 'initialize agent-foreman'.
workflow guide
Chachamaru127Provides guidance for the Cursor ↔ Claude Code 2-agent workflow. Use when the user asks about workflow, collaboration, or process. Do NOT load for: implementation work, workflow setup, or executing handoffs.
setup
Chachamaru127Unified setup hub: project init, tool setup, 2-agent config, harness-mem, codex CLI, and rule localization. Use when user mentions setup, initialization, new projects, workflow files, CI setup, LSP setup, MCP setup, codex setup, opencode setup, 2-Agent setup, PM coordination, Cursor setup, harness-mem, claude-mem integration, cross-session memory, localize rules, adapt rules. Do NOT load for: implementation work, reviews, build verification, or deployments.
codex-review
Chachamaru127Codexにセカンドオピニオンを求める。AI同士の忖度なしガチレビュー。Use when user mentions 'Codex レビュー', 'セカンドオピニオン', 'Codex の意見', 'Codex でレビュー', or 'Codex セットアップ'. Do NOT load for: 'Codex に実装させて', 'Codex Worker', 'Codex に作らせて', '実装を依頼'.
ci
Chachamaru127Call when CI goes red. Pipeline fire brigade, dispatch. Use when a user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, routine implementation work, code reviews, or setup.
maintenance
Chachamaru127ファイル整理とクリーンアップ。散らかった部屋をピカピカに。Use when user mentions cleanup, archive, file bloat, or organizing Plans.md/session logs. Do NOT load for: implementation work, reviews, new feature development, or deployment.
plans-management
Chachamaru127Plans.mdのタスク管理とマーカー操作。Use when user mentions adding tasks, updating Plans.md, marking complete, or changing task status. Do NOT load for: implementation work, reviews, or non-Plans file operations.
sync-status
Chachamaru127進捗とPlans.mdを現実に同期。『今どこ？』がすぐわかる現在地確認。Use when user mentions '/sync-status', progress check, where am I at, or sync Plans.md. Do NOT load for: casual 'how is it going' chat, informal progress questions.
crud
Chachamaru127Quickly auto-generate CRUD. Leave the boilerplate to AI. Use when the user mentions CRUD, entity generation, or wants to create API endpoints. Do NOT load for: UI component creation, form design, or database schema discussions.
handoff
Chachamaru127PMへの完了報告やエージェント間バトンタッチ。スムーズな引き継ぎを実現。Use when user mentions '/handoff', completion report, handoff to Cursor/OpenCode, auto-fix, or reporting to PM. Do NOT load for: casual completion statements, progress chat, informal status updates.
principles
Chachamaru127Provides development principles, guidelines, and guidance for VibeCoder. Use when the user mentions principles, guidelines, safety, or diff-aware editing. Do not use for actual implementation—if execution or code generation is needed, direct the user to the impl skill instead.
plan-with-agent
Chachamaru127アイデアをPlans.mdに落とし込む。夢を計画に変える魔法使い。Use when user mentions '/plan-with-agent', create a plan, organize tasks, feature planning, or TDD planning. Do NOT load for: implementation, reviews, or setup.
troubleshoot
Chachamaru127Diagnosis and repair guide for errors and failures including CI. Use when user mentions something broken, errors, it doesn't work, CI failures, CIが落ちた, build errors, test failures, or pipeline issues. Do NOT load for: successful builds, new feature implementation, or reviews.
harness-ui
Chachamaru127Harnessダッシュボードを表示。現状を一目で把握できる司令塔。Use when user mentions '/harness-ui', dashboard, monitoring, or UI display. Do NOT load for: app UI implementation, dashboard component creation, admin panel features.
session-state
Chachamaru127Session state transition management based on SESSION_ORCHESTRATION.md. Controls state updates at /work phase boundaries, escalated transitions on errors, and safe return to initialized when resuming sessions. Internal workflow use only. Do NOT load for: user session management, login state, or application user session handling.
session-memory
Chachamaru127セッション間の学習と記憶の永続化を管理。Use when user asks about previous sessions, history, or to continue from before. Do NOT load for: implementation work, reviews, or ad-hoc information.
notebookLM
Chachamaru127Generate YAML and slides for NotebookLM — a showcase for document craftsmanship. Use when the user mentions NotebookLM, YAML, slides, or presentations. Do NOT load for implementation work, code fixes, reviews, or deployments.
harness-update
Chachamaru127Harnessを安全にアップデート。バックアップ付きで安心安全。Use when user mentions '/harness-update', update harness, update version, or template updates. Do NOT load for: app updates, dependency updates, product version bumps.
harness-review
Chachamaru127コード・プラン・スコープを多角的にレビュー。品質の番人、参上。Use when user mentions reviews, code review, plan review, scope analysis, security, performance, quality checks, PRs, diffs, or change review. Do NOT load for: implementation work, new feature development, bug fixes, or setup.
work
Chachamaru127Plans.mdのタスクを実装。スコープを聞いて自動判断、1タスクから全タスクまで。Use when user mentions '/work', execute plan, implement tasks, build features, work on tasks, 'do everything', 'implement', '実装して', '全部やって', 'ここだけ'. Do NOT load for: planning, reviews, setup, deployment, or breezing (team execution).
session-init
Chachamaru127Initializes a session by performing environment checks and a task-status overview. Use when the user mentions starting a session, beginning work, or requesting a status check. Do NOT load for implementation work, reviews, or when executing individual tasks mid-session.
memory
Chachamaru127Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, claude-mem, past decisions, record this, or cursor-mem integration. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.
deploy
Chachamaru127VercelやNetlifyへいざ出陣。本番環境への片道切符を手配します。Use when user mentions deployment, Vercel, Netlify, analytics, or health checks. Do NOT load for: implementation work, local development, reviews, or setup.
vibecoder-guide
Chachamaru127Guides non-technical VibeCoder users in natural-language development. Use when a user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for technical-user work, direct implementation requests, or reviews.
cc-cursor-cc
Chachamaru127Validate ideas with Cursor PM and update Plans.md to hand off. Supports the Cursor ↔ Claude Code two-agent workflow. Use when the user mentions Cursor PM handoff, two-agent plan validation, a CC–Cursor round trip, or a brainstorm review. Do NOT load for implementation work, single-agent tasks, or direct coding.
verify
Chachamaru127ビルド検証、エラー復旧、レビュー修正の適用。Use when user mentions build verification, error recovery, applying review fixes, test failures, lint errors, or CI breaks. Do NOT load for: implementation work, reviews, setup, or new feature development.
Agent Browser
Chachamaru127Control the browser like an extension of your hands and feet. Page navigation, form input, screenshots — anything. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request. Do NOT load for: sharing URLs, embedding links, or screenshot image files.
auth
Chachamaru127認証と決済機能を実装。Clerk、Supabase Auth、Stripeに対応。Use when user mentions login, authentication, payments, subscriptions, or Stripe. Do NOT load for: general UI work, database design, or non-auth features.
ui
Chachamaru127Generates UI components and feedback/contact forms. Use when the user mentions components, UI, hero sections, forms, feedback, or contact requests. Do NOT load for authentication features, backend implementation, database operations, or business logic.
parallel-workflows
Chachamaru127複数タスクの並列実行を最適化。Use when user mentions running tasks in parallel or together. Do NOT load for: single tasks, sequential-only work, or tasks with dependencies.
generate-video
Chachamaru127Automatically generate product demo videos. Embodies ‘seeing is believing.’ Use when the user mentions '/generate-video', video generation, product demos, or visual documentation. Do NOT load for embedding video players, live demos, or video playback features. Requires Remotion setup.
session-control
Chachamaru127Controls /work session resume/fork based on the --resume/--fork flags. Internal workflow–only skill that updates session.json and session.events.jsonl. Do NOT load for: user session management, login state, app state handling.
session
Chachamaru127セッション管理の総合窓口。初期化・記憶・状態を一手に引き受けます。Use when managing Claude Code sessions, /session command. Do NOT load for: app user sessions, login state, authentication features.
impl
Chachamaru127Plans.mdのタスクに基づいて機能を実装しコードを書く。Use when user mentions implementation, adding features, writing code, or creating new functions. Do not use for review or build verification.
harness-init
Chachamaru127プロジェクトをHarness仕様に初期化。開発の準備体操はこちらで。Use when user mentions '/harness-init', new project setup, launch a project, or introduce harness to existing project. Do NOT load for: implementation, reviews, or planning.
Angular Testing Patterns
PramodDuttaAngular application testing with TestBed, component harness, service testing, directive testing, and Angular-specific testing utilities.