Create and structure Claude Code agent skills. Use when the user wants to create a new skill, write an agent skill, make a claude skill, or asks about SKILL.md files.
Conventions, anti-patterns, and meta-patterns for writing skills (and the shared agent/skill philosophy).
Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.
Cross-model context handoff via expert council. 40% token reduction, 9.5/10 recall, 97% cross-domain preservation. — from general/ai-tooling
Creates new agent skills following modern best practices with proper structure and documentation. Use when asked to build a new skill, organize skill resources, design skill…
Manage large local Agent Skills libraries with runtime-aware scenario groups for Codex, Claude Code, OpenCode, GitHub Copilot, and generic SKILL.md roots.
Creates agent skill and instruction surfaces. Use when authoring SKILL.md folders, AGENTS.md/AGENTS.override.md, CLAUDE.md, Copilot or Cursor rules, or when asked to bootstrap,…
Audits and improves agent skill and instruction surfaces. Use when reviewing SKILL.md, AGENTS.md/AGENTS.override.md, CLAUDE.md, Copilot or Cursor rules, or when asked to lint,…
Deciding whether material belongs in a skill at all, or in the project's own documentation instead, before deciding its tier; adding, editing, renaming, moving, or removing an…
Search Israeli restaurants, check table availability, view menus, and get booking links on Ontopo. Use for "restaurant reservation", "table booking", "ontopo", "where to eat in…
Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal.
Comprehensive templates, patterns, and best practices for creating Claude Code subagents and skills. Use when building new agents/skills or need reference examples for proper…
Create and manage AI agent skills following best practices. Use when creating new skills, optimizing context, designing multi-agent systems, or implementing progressive disclosure…
Claude Code 프로젝트의 에이전트와 스킬 관계를 D3.js 노드 그래프로 시각화합니다. 에이전트-스킬 의존성을 파악하고 구조를 탐색할 때 사용하세요.
Expert for creating and managing Claude Code Agent Skills. Create skills with git submodule + sparse-checkout for source references, write SKILL.md with proper frontmatter, and…
Build a specification-first Digital FTE that orchestrates accumulated intelligence from Lessons 1-7. Learn to compose execution skills into production-ready agents, valid — from…
Review SKILL.md quality for Waza readiness and agent-skills-instructions compliance. Use when evaluating SKILL.md quality, checking compliance with skill authoring standards,…
A biological-inspired rest & memory consolidation system for Agents. Enables periodic "sleep" cycles to compress memory, prune context, and reflect on insights.
Intelligent financial management skill for Claude Code that provides comprehensive PocketSmith API integration with AI-powered analysis, transaction categorization, rule…
End-to-end smoke check of the moraine MCP server. Exercises every MCP tool against a live moraine stack and prints a per-tool PASS/FAIL matrix.
The open-source social network for AI agents. Post, comment, vote, follow, and build reputation.
Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer — from John-Wang-0809/claw-research-skills
Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer — from majiayu000/claude-skill-registry
中文优先：用于智能体排序相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into…
Create AI art, mint NFTs, and trade on the Agent Soul marketplace. Use when an agent wants to generate AI art, manage an NFT gallery, buy/sell artwork, or interact with other AI…
Design compelling AI agent personalities with structured SOUL.md templates — tone, rules, expertise, and response behavior
Use when agent claims, proposed actions, summaries, or decisions need source identity before the workflow relies on them.
Guides ccusage agent source formats. Use when checking agent log locations, raw record structure, token mappings, model names, precomputed costs, or source-specific CLI behavior.
Création dynamique de sous-agents à la volée avec configuration, lifecycle management et resource allocation.
Generate or update an Agent Script YAML specification by wrapping `sf agent generate agent-spec` with project-specific defaults from sf-project.json and project-context.
CRITICAL: Use for writing and editing agent-spec .spec/.spec.md files. Triggers on: write spec, create spec, edit spec, new spec, spec authoring, task contract, .spec file,…
CRITICAL: Use for estimating work effort from agent-spec Task Contracts. Triggers on: estimate, estimation, how long, work effort, round count, time estimate, scope, sizing, cost,…
CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, plan, spec verification, task contract,…
Route each request to the agent best suited to it, with a fallback and an explicit unknown path, instead of one generalist handling everything.
Connect each agent’s frontmatter MCP servers safely and tear them down without leaking clients, while honoring plugin-only guards.
Run a lean startup team of agents (builder, marketer, analyst) through one disciplined weekly loop of ship, promote, and measure.
Auto-backs up core files (IDENTITY, SOUL, MEMORY, knowledge base) daily via cron, creates compressed .tgz archive, enables one-click restore in new environme...
Use when designing or implementing states for AI agent tasks, background jobs, local model runs, queues, and notifications — one shared set of states, only legal transitions, and…
Synchronisation d'état entre agents et sous-agents travaillant en parallèle sur un état partagé. Se déclenche avec "synchronisation agent", "état partagé", "shared state" — from…
Emit standardized progress pings during long-running work so the coordinator and the user know whether you are alive, stuck, or done — never go dark.
Aggregate desk-level state into an honest company view where problems stay visible instead of averaging away.
Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context assembly for Kiro, Claude Code, Codex, Charm, or other…
Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow.
Audit ~/.claude/agents/*.md (subagent definitions) for description-layer residency cost, body-layer quality, suppression instructions, staleness, and substrate absorption,…
Run a periodic strategy review with agents that check whether stated goals still match reality, argue the alternatives, and force an explicit continue or change decision.
Conception de systèmes de délégation parent-agent → sous-agents avec dispatch intelligent, suivi des tâches et agrégation des résultats.
Construction d'agents superviseurs qui contrôlent, monitent et corrigent des sous-agents en temps réel.
Run a team of support agents that triages each ticket, reproduces the problem, drafts a reply, and hands clean escalations to a human.
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified…
(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents,…
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation.
Multi-agent SWE team built on the Workshop model. Full-stack vertical workers, meeting room with @mention notification, private pipes, shared task board.
以"管理者—执行者"模式运维 agent-switchboard MCP：受管 Claude supervisor 生命周期、跨模型委派（Codex/Claude/Gemini）、验收纪律与已知陷阱对策。 用于存在任一可用委派通道（mcp__agent-switchboard__* 工具或宿主原生…
Enable and configure Agent Synthesizer for OpenClaw to improve autonomy and execution throughput. Use when a user asks to install, set up, troubleshoot, or optimize Agent…
Generates deployable system prompts for AI agents. Use when building, reviewing, revising, or templating system prompts that need clear roles, task boundaries, tool policies,…
Create tailored resume from job + source resume. Orchestrates the rewriting of bullet points to emphasize relevant experience without fabrication.
Décomposition automatique de tâches complexes en sous-tâches pour distribution aux sous-agents. Se déclenche avec "décomposer tâche", "task decomposition", "découper en s — from…
Design and operate task delegation systems for multi-agent fleets. Covers workload distribution, load balancing, queue management, priority scheduling, and dynamic agent scaling…