Create a durable guardrail, validator, doc, eval, or skill-reference update from a verified failure or learning.
[PROTOCOL] Generic system-optimization (skill-evolution) methodology shared by the three domain director-optimizers (dev / design / marketing).
Instructions for when to fork subagents and rules against reading fork output mid-flight or fabricating fork results
Zerlege jede gegebene Aufgabe zwingend in parallele Subagents und verteile die Arbeit. Verwende diesen Skill IMMER wenn der Nutzer "/subagent" schreibt, "mit Subagents", "parallel…
Use when delegating any implementation work to a subagent. Enforces spec traceability, TDD, and engineering standards.
Build compact, high-quality task packets for subagents with objective, scope, ranking criteria, stop rules, red flags, and expected report style.
Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic…
Record SkillTool usage with sanitized telemetry fields so built-in, bundled, and custom skills are distinguished while avoiding PII leakage.
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Skill-Modul für 5-Achsen-Heuristik-Check (read-only, kein Text-Edit). Eingabe: Text + Ziel-Niveau; Ausgabe: Score je Achse + Pass/Fail-Ampel.
Run an observed live dev session — Claude drives an interactive REPL in a named tmux session, the human spectates read-only via `tmux attach -r`.
Review third-party skill repos for format fit, provenance, and first-party adoption paths without treating them as direct harness dependencies.
Execute a trivial task inline — no subagents, no planning overhead — from 3dcom2711/thrunt-god
DEFAULT workflow for any ticket / PR / fix work in a GitHub-Projects repo. Use when the user asks to 'iterate on tickets', 'fix these issues', 'work through the backlog', 'run…
Extract CLI command structure from commander/yargs for AI agent skill generation Use when working with agent-skills, cli, commander, documentation, skill-generation, yarg — from…
Autonomously improve an MCP skill via the to-skills audit→draft→review loop (build or runtime mode) Also: to-skills, refine, mcp, skill-generation, cli, audit, overlay.
Use BEFORE dispatching 2+ Agent tools, BEFORE writing implementation plans or design specs that will trigger subagents, or whenever the user asks about agent strategy / model…
Authors or extends a skill in mc-agent-toolkit. Gates for forbidden buckets and name collisions, applies CONTRIBUTING's extend-or-split rules, then edits a peer skill or hands off…
Use when you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a…
60-Second Stock Snapshot — fast assessment with signal (BUY/HOLD/SELL/AVOID), key bullish/bearish factors, and key levels. No subagents. Terminal output only.
Drain the `.review/` report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the `triage-report`…
Use BEFORE shipping high-stakes output, considering an architectural alternative, working with compliance/legal/safety-critical content, or stuck in a debug loop >2 cycles — fork…
SwiftUI full-stack development for TTBaseUIKit apps. Use for SwiftUI/SUIBaseView/TTBaseSUI screens, reusable SwiftUI views, list/grid screens, SwiftUI ViewModels, and native…
tunaFlow Architect가 Developer subagent 또는 다른 Claude 세션에 일감을 넘길 때 쓰는 핸드오프 문서를 작성한다. 한 plan을 1~3개의 정확한 PR로 쪼개고, DO/DO NOT/Verification/CI 정책/보고 포맷을 명시해 다른 세션이 가정 없이 그대로 따라갈 수 있게…
The definitive end-to-end pipeline for creating the highest quality portable AI skills. Orchestrates six individual skills in sequence — each run fully, separately, and in its…
Agile development execution with TDD workflow. Writes state via task.update; review via review.run (Phase 3 wired) / subagent CLI fallback; pre-review checkpoint via…
Quality-first per-stage model routing AND a pre-flight cost gate for Claude Code dynamic workflows. Use when authoring or running ultracode / dynamic-workflow scripts, spawning…
Removes a locally-installed Claude Code subagent from `~/.claude/agents/` (user) or `.claude/agents/` (project). Deletes the `.md` file and the `.maxv-source-.json` sidecar.
Regenerate every `SKILL.md` from the project's currently-registered MCP tools into the configured skills folder (or a project-relative override path).
Referenz-Skill für die Deinstallation, Deaktivierung und Reaktivierung von Community-Skills, die über den Kanzlei-Builder-Hub installiert wurden.
Orchestrated documentation sync. Audits committed git changes over a time range (1w/2w/1m/3m/1y), delegates zone mapping to a doc-updater subagent, presents proposed Notion…
Actualizar el contenido de un SKILL.md existente para mejorar su precisión, completitud y claridad. Cubre el incremento de versión, el refinamiento de procedimientos, la expansión…
Use TOON (Token-Oriented Object Notation) with schema.org vocabulary for prompting and instructing subagents and builtin agents.
Use when starting any conversation - establishes mandatory workflows for finding and using skill-set plugins — from majiayu000/claude-skill-registry
Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skill-auditor);…
Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions.
Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes.
Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass/fail checks, severity-graded findings,…
Use after modifying plugin skills, docs/skills/ pages, or site/src/data/skills-meta.ts. Validates content consistency between SKILL.md files and their documentation surfaces:…
PR-scoped validation sweep. Runs after every successful PR merge to catch issues the merge introduced before they compound across subsequent PRs.
PROPOSAL: Add explicit skill chaining to Agent Skills spec. Defines chain metadata field for ordered skill execution with async option for sequential/parallel loading.
Execute a clear plan, issue, or agent brief with workspace safety, TDD, scoped subagent coordination, continuous verification, and tiered review gates.
Distills a completed user workflow, session interaction or pattern into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process…
Мета-навык для создания новых навыков Veda. Шаблон SKILL.md, структура папок, правила именования, чеклист качества. Используй когда нужно упаковать новое знание в навык.
Author and review first-party Vellum skills in the repository. Use when editing files under skills/, assistant bundled skills, skill manifests, tool definitions, SKILL.md files,…
Design or operate adversarial verification agents that independently validate implementation work with command-backed evidence, strict read-only boundaries, and explicit PASS FAIL…
Drain the verification queue — pick up unverified claims emitted by the working agent, spawn isolated verifier subagents to check them, write results back to the log.
Verification protocol for agent outputs. Use when: (1) a subagent or ACP agent claims to have completed a fix or implementation, (2) reviewing agent results before committing, (3)…
The Reviewer subagent's playbook for checking a finished CRE build. Audit-cell checks, error-value scans, convention compliance, structural integrity.
Verwandte Community-Skills basierend auf aktueller Tätigkeit in anderen Plugins empfehlen. Prüft, ob die Community etwas Relevantes für eine Aufgabe gebaut hat, und erwäh — from…
Use when a PR is open and CI green - dispatches a fresh subagent for two-stage code review (spec compliance then quality), posts findings to the GitHub PR as review comments with…
Architectural patterns for building agent systems that dynamically decompose complex tasks, generate specialized subagents just-in-time, and prevent cascading failures through…
Two-tier diagnostic protocol — spawns fresh subagents to analyze problems when stuck. Invoke manually or triggered by rabbit hole detection.
Executes the agreed session plan in waves with role-based execution and parallel subagents. Handles inter-wave quality checks, plan adaptation, and progress tracking.
Construction d'un sous-agent spécialisé dans la collecte de données web pour un agent parent. Crawling, extraction, parsing et retour structuré.
Spawn a one-shot subagent that surfaces unstated assumptions, counterfactuals, and out-of-scope gaps in a piece of analysis.
Analyze skill library to identify coverage gaps, redundant overlaps, optimization opportunities, and provide recommendations for skill portfolio improvement
Stage 3a of the WinDAGs meta-DAG. Given a decomposed subtask graph and a pre-narrowed candidate list per subtask, picks a primary and runner-up skill, plus model tier and cost…
Stage 4 (final) of the WinDAGs meta-DAG. Assembles the final PredictedDAG from Sensemaker, Decomposer, Skill Selector, and PreMortem outputs.
A template for skills that include executable code for deterministic operations.