Agents
AI agents and automation
plan-review
by HerbHall
Submit the current implementation plan for independent review by the plan-reviewer agent. Spawns the reviewer with fresh context and limited file scope — no implementation history carried over. Use before starting any significant implementation. Blocks on REVISE/REJECT until the plan is approved or the user overrides.
skill-creator
by rory-data
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the Agent's capabilities with specialised knowledge, workflows, or tool integrations.
herdres
by luminexord
"Use Herdres to operate the Herdr-to-Telegram bridge: install and configure it, set up per-agent forum topics, send/interrupt/queue messages to agent panes, read status and reports, manage child bots, drive the macOS cockpit, and run maintenance like cleanup-duplicates. Use when a user wants to control or set up Herdr agents over Telegram. This is herdres (the Telegram bridge), NOT herdr (the terminal multiplexer)."
ClawTrust Skill — AI Agent Integration Guide
by clawtrustmolts
See skills/clawtrust-integration.md for the complete API reference.
anysystem-design
by freedomw1987
LLM Agent Skill for AnySystem Design React component library
summoner
by Overlord-Z
Multi-agent orchestration skill for complex tasks requiring coordination, decomposition, and quality control. Use for large implementations, refactoring projects, multi-component features, or work requiring multiple specialized agents. Excels at preventing context bloat and ensuring SOLID principles. Integrates with oracle, guardian, and wizard.
VertexOracle Multi-Agent AI
by tachfineamnay
Complete guide to the 4-agent AI architecture for spiritual reading generation.
backend-node
by shaul1991
Node Developer Agent. Node.js/TypeScript 기반 백엔드 개발을 담당합니다. NestJS, Express, Prisma 전문.
agent-browser
by zhongjis
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
plan-to-spec
by miracloon
将 Plan Mode 的讨论结论固化为可执行的 Markdown 施工图纸。当用户完成 Plan 讨论、准备进入开发阶段时使用。生成 overview.md（战略层）、taskXX_*.md（战术层）、summary.md（审计层）三类文档，实现上下文序列化，避免 Plan 与 Code 偏航。
kaiqiao
by leslietong2046-ship-it
Agent行为校准器，让AI学会"什么时候该问、该干、该拦、该说话"。 触发关键词：开窍、AI行为诊断、prompt检查、助手行为规范、诊断报告、行为校准、该问还是该干、授权闭嘴、定时提醒、主动拦截
agent-evaluation
by yunaamelia
"Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world ben..."
migrate-pip-to-uv
by squirrel289
Skill to migrate a monorepo Python project from pip/pip-tools to uv, converting requirements files to pyproject.toml and uv.lock, and updating workflows for universal, locked, multi-group dependencies.
config
by Fibrous-Finance
View and modify fibx CLI configuration, such as setting custom RPC URLs to avoid rate limits.
oro-gold
by behfar-dev
ORO GRAIL gold infrastructure for AI agents. Use when building agent integrations that involve: - Checking gold prices (via Pyth oracle) - Buying or selling gold (GRAIL tokens) - Managing user gold balances - Agent treasury/wealth features - Building fintech agents with gold savings, DCA, or rewards Based on Oro GRAIL API: https://docs.grail.oro.finance/
tech-lead-web
by emalorenzo
Tech Lead for web development projects. Orchestrates a fleet of Opus agents to build pixel-perfect websites from Figma designs. Use with /tech-lead-web to start a new project.
find-skills
by zhongjis
Helps users discover agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Discovery only — for installing or maintaining skills, use the skill-maintainer skill.
agent-workspace-clean
by samuerio
"Safely remove the current git worktree only when it is an agent workspace under <repo>/.worktree/*. Use when asked to clean/remove/delete the current agent workspace/worktree. Use --force only if explicitly requested in the latest user message."
agent-define-skill
by maxoreric
v1.0.0 (2026-01-19): åå§çæ¬
performing-retro
by squirrel289
"Conduct a post-session review to organize changes into logical commits and document work. Use when: (1) Session has implemented features, fixes, or refactoring and changes are scattered across files, (2) Need to group related changes into atomic commits with conventional messages, (3) Want to create summary documentation of work completed, (4) Final validation before pushing changes. Helps transform a working session into clean git history and clear documentation."
support-analytics
by elifokaju
Answer questions about support ticket data by querying SQLite and interpreting results. Use when asked about ticket volume, trends, resolution times, agent workload, or issue patterns.
user-proxy
by metyatech
Use when reviewing an agent's plan, work output, or completion claim on behalf of the user. Evaluates against established rules, known error patterns, and quality standards. Do not use for direct implementation work.
deepagent
by htooayelwinict
Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.
harness-skill
by zhuiyi1472-lgtm
Use when designing, auditing, or refining an AI agent, skill system, or multi-tool harness where reliability, boundary clarity, tool routing, memory policy, scheduling, and failure handling matter more than raw autonomy. Also applies to requests about Agent/Skill/Workflow 边界、工具路由、事实校验、失败退路与 Eval 设计.