Inventory the installed skills and which plugins contribute them, then flag overlap with the user's own skills — read through the Agent Monitor Config Explorer API.
Invoke and execute Nexus skills. Use when the user says "use skill X", "run skill X", "invoke skill X", or references a specific Adverant Nexus skill by name or ID.
Audit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable…
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Iterative skill tuning via execute-evaluate-improve feedback loop. Uses ccw cli Claude to execute skill, Gemini to evaluate quality, and Agent to apply improvements.
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
Guide for iterating and improving skills. Use when updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Informationen aus dem Jira-Projekt und -Board SYS-FLOW zu SYS-AEMs in Systemschaltplänen abrufen. Nutze diesen Skill bei Fragen zu SYS-FLOW Tickets, Epics, Sprints, Board-Status…
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages.
Nutze local_rag systematisch fuer evidenzbasierte Antworten zu Prozess, Systemschaltplan, Bordnetz- und VOBES-Themen.
Turn one bounded skill opportunity into a concrete proposal packet with explicit approval before packaging.
定义所有 Skill 必须遵循的设计法则（Skill Laws），包括 AI 优先、人类中心、即调即用等核心法则。何时使用：当用户创建新 Skill、优化现有 Skill、询问 Skill 设计规范、或需要评估 Skill 质量时。
Three lawyer/paralegal flows — brief a matter from prior context, run a forward-window deadline check, or translate an incoming email.
MUST use AFTER цикла работы с ≥2 итерациями (написал → ошибка → исправил → успех). Provides процедуру ретроспективы и формат записи приём/антиприём в…
Meta-skill for recognizing learnings, validating improvements, and contributing back to the collective knowledge base.
Search, load, and adapt methodologies from the shared Git-backed skill library for use in Codex without modifying the canonical Claude-authored skills.
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.
Search and load an on-demand archived skill snapshot when a specialized workflow is not directly installed or the user names an archived skill.
Play the LIE.WATCH AI social deduction game - survive through trust, deception, and strategic betrayal — from satoshistackalotto/skills
The authoritative skill lifecycle state model including container states, version states, review workflow states, visibility overlay, and governance actions.
Manage Agent Skills across Codex, Claude Code, local/global/project roots, Skill Hubs, GitHub, skills.sh, and managed plugin caches.
Use when adding or auditing Agentlas skill lifecycle metadata, skill-registry.json, trial evidence, Curator promotion decisions, or first-class skill promotion gates.
Use when a reusable Skill needs create, validate, publish, monitor, update, deprecate, or retire decisions after workflow changes.
Audit project and global .agents/skills and .claude/skills layouts. Verify that .agents/skills contains the real source and .claude/skills mirrors it through a parent or per-skill…
List every skill currently available in this session, each with a concise Traditional Chinese explanation of its purpose, in list format. One-shot display, read-only.
Improve a skill's public listing before publish. Use when tightening title, description, tags, changelog, and scan-friendly packaging so the listing looks clearer and less…
Dynamic skill loading via polynomial functor arrangements. Loads skills as interfaces p = A^y^B where state changes rewire the system.
Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude.
Drive one skill through the 7-step build loop (contract → deterministic tools+L1 → workflow → fallback gating → DeepSeek live L2 UI-lane two rounds → cross-provider smoke →…
Instructs Claude how to self-pace a recurring loop by arming event monitors as primary wake signals and scheduling fallback heartbeat delays between iterations
Audit, improve, split, deduplicate, and validate repository skills. Use when the task is to inspect a local skills tree, find contradictory guidance, detect broken skill…
Keep the skills repo consistent: update README.md and run codegen whenever a skill is added or changed.
Detect project tech stack and disable irrelevant skills to save context window space. Use when the user says "manage skills", "optimize skills", "disable irrelevant skills",…
Lists all registered GDD skills and agents, with descriptions, from the intel store. Falls back to directory scan if intel store not present.
Publish, submit, and verify local skills across public skill marketplaces, directories, and registries.
Publish a Codex or Claude skill to Skillstore, SkillMap, or similar public skill marketplaces. Use when you need to audit a skill for public safety, build a public package, create…
Создать новый skill (slash-команду) по шаблону.
SKILL.md is an open specification released by Anthropic in 2025 that standardizes how tools discover and auto-invoke procedural knowledge (skills, patterns, guides, rules).
Interactive system builder. Invoke for /meta command to create tasks for .claude/ system changes.
Craft better prompts using proven optimization techniques — use when your prompt needs refinement
Initialize or update the metadata field in one specific skill's SKILL.md according to this repository's CONTRIBUTING.md rules.
Route tasks to appropriate model size based on confidence estimation. Use small model by default, escalate to large model only on low confidence.
Register and manage ERC-8004 Identity NFTs on Monad. Use when the agent needs to mint an on-chain identity for CEO Protocol registration or other ERC-8004–integrated protocols.
Generate short, molty-native names for skills, ENS domains, and agent-economy primitives when the obvious words are taken.
Validiert und optimiert Skill-Namen und Beschreibungen nach Best Practices. Verwenden bei Skill-Erstellung, Skill-Überarbeitung, Frontmatter-Optimierung, Verbesserung der…
The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you…
Decide whether a capability should become a skill. Use when asking "should this be a skill?", pruning a library, choosing skill vs CLAUDE.md vs MCP vs hook, or before building an…
Visualize the skill network as an ASCII dependency graph. Use when the user wants to see how skills connect, trace dependency chains, find orphaned skills, or understand the…
Defines the skill observability event contract (event.schema.json) and emit substrate (obs-emit.mjs). The SSOT for the measurement layer of the skill improvement loop.
Package and publish one local agent Skill, or audit and release a Registry-driven public Skill portfolio, as polished installable GitHub packages.
Generates new .skills//SKILL.md entries on demand from a one-line description, guarded by a review gate so unreviewed skills do not become defaults.
Evaluates and optimizes skill file quality using 8 content patterns and 9 editing principles. Use when creating skills, refining skill content, or auditing skill quality.
Run a structured evaluate-analyze-improve cycle on any GAAI skill to measure quality, detect regressions, and propose targeted improvements.
Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user sugge — from…
Skill-aware agent routing with explicit competence/cost modeling. +22.5% accuracy, 700x cheaper than RL routers. Based on arXiv:2602.19672.
Dynamic skill router — discovers available SKILL.md metadata, matches the current task to the smallest relevant skill set, and loads those skills before acting.
Route to the optimal sequence of skills for any marketing, product, or business challenge. Stop using one skill at a time—orchestrate intelligent workflows that compound results.
Stand up a self-contained second-brain "OS" that lives entirely inside a Claude skill — a short SKILL.md router plus context files, no vault, cloud, or MCP server.
Audit overlap between proposed or existing skills. Use when adding a skill near an existing skill, renaming a skill, splitting a skill, or reviewing a skill set that may be…
Übersicht aller installierten Skills mit Qualitäts-Score — listet root- und projektspezifische Skills, bewertet sie kurz nach der autoloop-Rubrik und priorisiert Verbesserungen.