Choose the right orchestration primitive for delegated work — a single agent, parallel agents, or a dynamic workflow — using the agent → parallel → workflow ladder, plus the…
Rosetta MUST skill. MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential…
Use when coordinating Bades work across Claude Code agent teams, subagents, parallel sessions, or GitHub/workflow cleanup so the work is split safely and stays aligned with…
Create, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build skills with scripts, references, and assets.
Read, search, and manage Outlook emails and calendar via Microsoft Graph API with delegate support. Your AI assistant authenticates as itself but accesses the owner's mai — from…
Независимый аудит результата любого скилла по его чек-листу. Используй после завершения скилла для проверки качества output.
Create small, installable agent skills that wrap focused Overcast workflows. Use when the user asks to make an Overcast skill for a specific investigation, media analysis, recon,…
Use when the OZoneManager family or nearby governance skills need to be created, consolidated, tightened, validated, generalized, audited for target-session skill invocation, or…
Buat skill runtime PAAX baru, uji, bandingkan, dan sempurnakan -- adaptasi skill-creator Anthropic untuk konteks Command Room PAAX (tool ai-orchestrator, Evidence Gate, Aturan…
Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files (Obsidian-compatible).
Real Chrome automation for AI agents — authenticated sessions, PII anonymization, sealed secrets, site adapters, session checkpoints, and video recording.
把工作拆成安全、独立、可并行的子任务，并协调 subagent 避免重复劳动和冲突修改。适用于 Claude Code 通过清晰 delegation 能显著加速复杂任务时。
Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing…
Set up and manage self-improving parallel reconnaissance agent triads — eternal overlapping waves of deep invasion, target expansion, and skill evolution.
Coordinator-led parallel feature development. 5-10 features built simultaneously via native `claude --bg --worktree feat-`.
Design skill steps with explicit execution topology, asking which parts run directly, in subagents, in teammate swarms, or in parallel.
Patina Project's engineering style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
Implementa sistema completo de pagos recurrentes con Flow.cl (Chile) y Stripe (internacional). Incluye suscripciones mensuales, webhooks, firma HMAC, manejo de errores y — from…
ONLY when the user explicitly asks to refine a persona from recent corrections — persona analog of skill-improvement-pipeline; tightens a persona's Unique Questions,…
Standards and quality gates for the skill library. Audits existing skills (descriptions, dependencies, dead skills, eval coverage), proposes improvements, governs how new skills…
Pesquisa e cita legislação e jurisprudência brasileiras, com verificação de vigência e fontes verificáveis. Skill-base carregada pelas peças para qualquer busca jurídica.
How to use pi-cc-plugin slash commands (/pi:agent, /pi:status, /pi:result, /pi:cancel, /pi:setup) to delegate tasks from Claude Code to pi-subagents.
Calculate and display the token usage, turns, and estimated cost for the active session and subagent runs by parsing the harness session logs.
Analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task.
How the main Claude Code thread should treat the output returned by the pi rescue subagent and /pi:result
Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows.
Use when deciding HOW to split work between a strong planner and cheaper executors — configuring subagent models, writing delegation prompts, running the plan-big/execute-small…
Plan phase — autonomously plan a no-PR issue into an ordered unit breakdown via the built-in Explore/Plan subagents, persist the plan to the issue, and apply dispatch:planned (no…
Plan multi-step implementation tasks to minimize context usage and maximize parallelism. Automatically applies whenever plan mode is active.
Use when doing git work in this repo (or via subagents/worktrees) and hitting "files must be written to the correct artifact directory" from file-edit tools on worktree paths, a…
Design a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape it into a compliant skill.
Organizational Change Management (OCM) Lead Specialist — emulates an OCM Lead driving a go-live's organizational change end-to-end by composing the change-management…
Suite router for the PMO role-Specialist suite — reads the core/ logical skill registry (core/skills/registry.md) and routes a role-shaped request to the correct role-Specialist…
Post-phase batch reviewer. User invokes after pocket-development marks all phase tasks DONE. Main agent runs preflight and dispatches parallel reviewer subagents (one per task).
ALU execution pattern for ephemeral autonomous work. Detects hooked work, enters GUPP autonomous mode, executes the assigned bead, commits and pushes results, then self-t — from…
Analyze policy impacts for congressional districts and representatives' constituents. Use when the user mentions a specific district (NY-17, CA-52), a representative's name, or…
Generate one showcase image for PopiStudio Alice with strict character consistency. Use this when a creator agent needs a single Alice proof frame, demo still, or presentation…
Generate one image from text through the PopiArt runtime baseline. Use this when the user wants the most direct text-to-image path for smoke tests, concept frames, or simple…
Keep the universal skill compact yet discoverable by loading minimal frontmatter first and heavy content on demand.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
Mob review by multiple frontier-model agents — 完整 PR 生命週期含跨家 LLM group review：自動偵測 codex / agy，≥1 家即啟動 R1 獨立 + R2 交叉 debate + aggregate；fix → re-review 直到全員 LGTM（含 actionable…
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
Subagent for figma-from-code Phase 2.5. Captures app screenshots and structured text content for every UI component before Figma building begins.
A partnership covenant for AI agents and their human operators. v1.1 adds the Subagent Responsibility Chain and Inspectability Clause.
Apply when writing or editing prose an agent reads (a SKILL.md, CLAUDE.md or AGENTS.md, a subagent brief, a plan, a PR description), when naming a concept, or when a word in the…
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payload — from…
Audit a private skill, prompt pack, or assistant workflow before publishing it. Use when extracting public reusable method from client, product, team, or repository-specific agent…
Use when beginning analytical or strategic tasks, facing undefined problems, or facing analysis paralysis—requires explicit problem definition before proceeding.
Конституция разработки Docwise: язык коммуникации, инженерные стандарты, reuse-first подход, правила консистентности UI/анимаций, формат code review и синхронизация skill-файлов.
Create, update, and validate Codex skills under /Users/nolarose/.codex/skills and /Users/nolarose/Projects/.agents/skills.
Evaluate whether a repository is aligned with Arey Pi rules. Use when assessing specs, tests, quality tooling, AGENTS.md, skills, prompts, subagents, or project readiness.
Resolve a stable project root first, then load local skills relative to that scope before combining them with other sources.
Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use…
Creates effective prompts for AI coding agents and subagent delegation. Use PROACTIVELY when writing prompts for Task tool delegation, creating agent instructions, or designing…
Commit and push skill changes to the configured skills repository after review and validation.
Skills kanzleiweit unter QA-Kontrolle halten: zentrale Skill-Bibliothek, Versionsverwaltung, Änderungsfreigaben, Validatoren, Tests.
Publishing a QA/verification report to a merge request after approval — the branch-hosting procedure and ownership-based link placement.
Modo Reina explícito para orquestar tareas largas, críticas o multi-fase en OpenGame mediante subagentes especializados, plan persistente, TEST CONTRACT y gates de validación.
Lightweight code review via subagent. The main agent identifies commits and passes them to a subagent that retrieves the changes and reviews for correctness issues, consistency…
Distill a book, paper, or thesis into a folder of terse per-concept cheatsheets with a README index. Use whenever the user asks to "read this PDF and turn it into a doc set",…