Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skill, update an existing skill, or need guidance on s — from…
Guidelines for creating new Agent Skills and MCP tools for this WordPress MCP server. Use when adding new capabilities, creating skills, or registering MCP tools.
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and…
Manage and optimize custom agent definition files (IDENTITY.md, AGENTS.md, SOUL.md, TOOLS.md). Also handles first-time employee initialization when .workspace/ has no IDENTITY.md.
Dispatches the `adversarial-critic` subagent (Opus, read-only) against the master plan currently in conversation context.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
Use when deciding whether a capability deserves its own skill, whether something should be a skill or a reference, where a new skill belongs, or whether two skills overlap —…
Review code changes with the Bugbot subagent. Computes diffs, launches a bugbot subagent, and summarizes findings by severity.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing sk — from…
Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that the cw-prose-writing skill can…
Give an AI agent a persistent, verifiable cognitive self-model via a Cypher Tempre Timechain: an append-only, hash-chained ledger of its own experience.
Matches natural language task descriptions to appropriate skills using semantic similarity, ranks candidates by fit and performance history, and maintains the skill catal — from…
Executive-grade data analysis with pandas/polars and McKinsey-quality visualizations. Use when analyzing data, building dashboards, creating investor presentations, or ca — from…
重要数据同步工具。通过云服务器中转站在多台电脑间同步 Claude Code 关键配置（skills、hooks、记忆库、skill-factory），GitHub 作为大版本归档。支持 init/pull/push/backup/status 五个子命令。
Sous-agent spécialisé dans les requêtes base de données — SQL generation, exécution et analyse de résultats.
Strukturiertes Erstgespraech im Datenschutzmandat. Sieben gezielte Fragen ordnen den Sachverhalt in eine Mandantenmatrix ein: Rolle nach Art.
Start structured red vs. blue team debates via subagents. Use when exploring a topic from multiple adversarial perspectives.
Use when you need to create an execution plan from a feature spec - handles worktree context, dispatches subagent for task decomposition, validates quality, analyzes dependencies,…
Deep Agents LangChain CLI (import deepagents, deepagents-cli). ТОЛЬКО при: deepagents, FilesystemBackend, StoreBackend, CompositeBackend, TodoListMiddleware, SubAgentMiddleware,…
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in- — from…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing sk — from…
token cost の削減を第一目標として、explore / implement / review のどれにも明確に当てはまらない雑務のうち、 対象 content を読んで判断する必要があり、 親エージェントの context を膨らませたくない作業を安価な subagent に委譲するフォールバックスキル。…
token cost の削減とデザインの一貫性確保を目標として、固定デザインテンプレートに沿った 自己完結型 HTML ドキュメントの生成を安価な subagent に委譲するスキル。 調査結果・レポート・issue まとめ・技術資料・議事録などを「HTML で」「ドキュメントにして」 「レポート化して」といった形で文書化する要求に使う。…
画像生成 capability を持たない requester から、画像生成 capability を持つ Codex 子プロセスへ画像生成・画像編集作業を委譲するスキル。 ユーザーが画像、イラスト、写真風ビジュアル、バナー、サムネイル、アイコン案、テクスチャ、モック画像などの生成や編集を求め、 main agent…
token cost の削減を第一目標として、コードの実装・修正を安価なモデルの subagent に委譲するスキル。 複数ファイルまたは既存パターン調査を伴う実装タスク（機能追加・バグ修正・リファクタ等）を、 親エージェントの context を汚さずに処理したいときに使う。単一ファイルの小変更、明確な一括置換、 main…
main の context 消費の削減（context isolation）を第一目標として、 コード/ドキュメントレビュー（差分の指摘出し）を判断比重の高いモデルの subagent に委譲するスキル。 大きめの diff、複数ファイルにまたがる変更、main が差分全体を読むと重い一次レビューに使う。 数行の diff、main…
Delegates bounded subtasks (text-in/text-out, large-token, no harness MCPs needed) to a local CLI agent (claude/codex/gemini) via scripts/delegate.sh.
Delegates a task to a local LLM running as a Pi coding-agent session in a herdr pane - the subagent is visible in herdr, can be steered mid-session, and costs no cloud tokens.
Orchestrates work across subagents to save the main session's context and tokens — deciding what to delegate, packing full context into each prompt, picking the right model per…
Audit model delegation and subagent effectiveness for a session — which models handled which subagent types, per-type success rates and average durations, and wasted delegations…
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
Scientific delegation framework for orchestrators coordinating sub-agents. Provides WHERE-WHAT-WHY context patterns while preserving agent autonomy.
Expert in Jira operations using Atlassian MCP - automatically detects workspace Jira configuration or prompts for project details.
Use source-aware admission rules so trusted local skills can surface automatically while plugin or MCP-provided entries must supply explicit descriptive metadata.
Use when executing an approved implementation plan — dispatches fresh subagents per task with two-stage review (spec compliance then code quality).
Use when creating a new Atelier skill or rewriting an existing one — structures authoring, runs a self-review gate, and verifies with a subagent before registering.
Smoke-test the Vion Dale DevHost end-to-end. Tier 1 (headless, CI) covers the HTTP/runtime surface; Tier 2 (live, chrome-devtools) drives the no-build SPA UI on a real server.
Use when a proposal has unanimous support or relies on a single high-impact assumption—constructs the strongest possible counter-argument (Steel Man) and runs a Pre-Mortem.
Heavyweight 6-pass adversarial review — fans out to 5 domain-minion subagents + 1 synthesis pass for deep/risky changes. For a quick single-pass review use review-adversarial.
手动触发的「问题列表批量修复」编排器。接收问题列表文件（.md/.json/.yaml/.txt）和可选编号，把未修复问题排成队列， 逐个派发独立 subagent——每个 subagent 在隔离上下文里调用 diagnose-and-fix skill 完成单问题的「诊断 → 选方案 → 修复 → 测试 → 修复后验证 → 提交代码 →…
Looks up a skill by name, keyword, or domain in the curated catalog (skill-sources.json). Returns the source repo, tier of trust, install methods supported, and any guardrails…
Use when you have 2+ independent tasks with no shared state — dispatches parallel subagents for each task.
Claim the earliest-due JIT issue, then either run a configured skill (for skill-running jits such as digest) or summarize it for the user and stop.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch subagents to work concurrently. — from S3YED/appie-kit
Fan out N independent tasks to parallel subagents, collect their results, optionally synthesize. Use when another skill needs work that decomposes into independent pieces — review…
Internal — Tier 2 (structured-row) Atelier writes through memex:index:write with a caller-built librarian_output. No Librarian subagent dispatch, no LLM. Not user-visible.
Use when about to spawn or delegate work to a subagent (Agent/Task tool), choosing a model tier (haiku/sonnet/opus/fable) for a task, writing a delegation prompt, deciding whether…
Distribute a skill across configured agent skill folders while respecting local symlink layouts.
Parallel subagent execution with code review gates between task batches for issue resolution
Use when supervising a full SDLC pipeline run in a local Claude Code session. Loops the /sdlc router — dispatching each stage to a subagent on the stage-appropriate model…
Analyzes recent commits and uses a smart AI subagent to check if they invalidate any documentation in docs/.
Scrape external documentation (API references, library docs, protocol specifications) and generate Claude Agent Skills in SKILL.md format.
Generate comprehensive {node_name}.example.json files that showcase real-world usage of Workscript workflow nodes.
Enforces dogfooding for the skills CLI project. Use when working on packages/skills-cli or packages/skills-library.
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a…
BEFORE dispatching any implementation agent or starting to code - if you're about to write "Task(subagent_type=..., prompt=...)" for implementation, or about to implement a plan…
Iteratively polish code through successive quality passes run in fresh subagents.
Framing discipline for any artifact instructing a downstream reader — handoffs, plans, ADRs, subagent prompts.
Compare Google Drive skill definitions with a GitHub skills repository and identify Drive skills not yet published.
Subagent delegation for data analysis. Dispatches fresh Task agents with output-first verification.