Agent Infrastructure — Agent Skills

skill-creator

Create, edit, improve, or audit AgentSkills.

loop-design-check

Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion.

03 CURATED 4.4/5 C 4.4· A 0.0

exploring-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox.

04 WILD 4.9/5 C 4.9· A 0.0

blocks-network

Non-linear reference for managing Blocks Network agents — features, configuration, CLI, IO schemas, streaming, consumer SDK, publishing, invites, troubleshooting.

05 WILD 4.9/5 C 4.9· A 0.0

polygon-agent

Complete Polygon agent toolkit for on-chain operations on Polygon.

06 WILD 4.9/5 C 4.9· A 0.0

omo

Use this skill when you see `/omo`.

07 CURATED 4.4/5 C 4.4· A 0.0

exploring-llm-traces

ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools.

08 WILD 4.8/5 C 4.8· A 0.0

bx

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI.

09 CURATED 4.3/5 C 4.3· A 0.0

blueprint

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects.

10 CURATED 4.3/5 C 4.3· A 0.0

agent-self-evaluation

Use after completing any non-trivial task.

11 WILD 4.8/5 C 4.8· A 0.0

laravel-waitlist

Conventions and APIs for the offload-project/laravel-waitlist package — multiple waitlists, entry status tracking, optional email verification, and bridge into laravel-invite-only.

12 WILD 4.8/5 C 4.8· A 0.0

laravel-invite-only

Conventions and APIs for the offload-project/laravel-invite-only package — polymorphic invitations, token acceptance, bulk invites, scheduled reminders, and event-driven hooks.

13 WILD 4.8/5 C 4.8· A 0.0

bad

BMad Autonomous Development — orchestrates parallel story implementation pipelines.

14 CURATED 4.3/5 C 4.3· A 0.0

exploring-signals-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox.

15 OFFICIAL 3.7/5 C 4.9· A 3.0

define-goal

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy…

16 OFFICIAL 3.7/5 C 4.8· A 3.0

migrate-to-codex

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

17 CURATED 4.3/5 C 4.3· A 0.0

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models.

18 CURATED 4.3/5 C 4.3· A 0.0

mcp-server-spec

Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents.

19 CURATED 4.3/5 C 4.3· A 0.0

brand-extract

Extract a complete Brand Kit from a live website by driving the in-app browser.

20 CURATED 4.3/5 C 4.3· A 0.0

skill-authoring

Guide for creating and auditing DAAF skills (SKILL.md). Covers frontmatter, metadata vocabulary, progressive disclosure, decision trees, reference files. Use when creating, reviewing, or debugging…

21 CURATED 4.2/5 C 4.2· A 0.0

mcp-for-agents

Designs or reviews MCP servers so AI agents can use them reliably: outcome-oriented tools, flat constrained parameters, actionable errors via isError, token-efficient responses, composable outputs,…

22 CURATED 4.2/5 C 4.2· A 0.0

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a…

23 CURATED 4.2/5 C 4.2· A 0.0

skill-vetter

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

24 CURATED 4.2/5 C 4.2· A 0.0

mcp-security-reviewer

Use before connecting a new MCP server to your agent — produces a structured security review covering source, permissions, tools, network, and approvals.

25 CURATED 4.2/5 C 4.2· A 0.0

find-skills

Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own…

26 WILD 4.6/5 C 4.6· A 0.0

better-icons

Use when working with icons in any project.

27 CURATED 4.2/5 C 4.2· A 0.0

exploring-ai-failures

Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.

28 WILD 4.6/5 C 4.6· A 0.0

trade

Execute the daily virtual trading process. Research markets, make trades, save snapshot, write diary and memory.

29 CURATED 4.2/5 C 4.2· A 0.0

page-agent

Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with…

30 CURATED 4.2/5 C 4.2· A 0.0

mcp-installer

Install, update, remove, or restart Model Context Protocol (MCP) servers in {OPENAGENTDCONFIGDIR}/mcp.json. Use when the user asks to add / remove / list / restart an MCP, or to enable a server like…

31 CURATED 4.1/5 C 4.1· A 0.0

od-contribute

One-click contribution flow for Open Design (nexu-io/open-design) — even for non-coders.

32 CURATED 4.1/5 C 4.1· A 0.0

improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

33 CURATED 4.1/5 C 4.1· A 0.0

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation.

34 OFFICIAL 3.5/5 C 4.3· A 3.0

plugin-creator

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use…

validator

35 WILD 4.6/5 C 4.6· A 0.0

claw-orchestrator

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines.

36 CURATED 4.1/5 C 4.1· A 0.0

openclaw-persona-forge

为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡，输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格…

37 CURATED 4.1/5 C 4.1· A 0.0

skillpack-check

Run gbrain skillpack-check to produce an agent-readable JSON health report for the gbrain install.

38 CURATED 4.1/5 C 4.1· A 0.0

visualizing-change-over-time

Helps PostHog engineers and agents pick the right chart when a request is about visualizing change over time, before/after comparisons, or period-over-period movement while building UI with…

39 CURATED 4.1/5 C 4.1· A 0.0

acceptance

Self-evidence for task delivery verification.

40 CURATED 4.1/5 C 4.1· A 0.0

improving-mcp-tools

Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…

41 CURATED 4.1/5 C 4.1· A 0.0

skillshare

Manages and syncs AI CLI skills and agents across 50+ tools from a single source.

42 CURATED 4.1/5 C 4.1· A 0.0

mcp-oauth-setup

Implement MCP server authentication with OAuth Dynamic Client Registration (RFC 7591), Authorization Server Metadata Discovery (RFC 8414), and generalized per-agent credential support.

43 WILD 4.5/5 C 4.5· A 0.0

kinic-cli

Explain day-to-day kinic-cli usage for memory canister workflows, including auth mode selection, discovery commands, prefs, TUI entrypoints, and agent-friendly JSON usage.

44 CURATED 4.0/5 C 4.0· A 0.0

context-budget

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules.

45 CURATED 4.0/5 C 4.0· A 0.0

advisor-orchestrator-worker

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

46 CURATED 4.0/5 C 4.0· A 0.0

intent-driven-development

Turn ambiguous or high-impact product and engineering changes into scoped, verifiable acceptance criteria before or alongside implementation.

47 CURATED 4.0/5 C 4.0· A 0.0

skill-install-guardian

Inspect third-party Claude/OpenClaw/Codex/OpenCode skills, plugins, repos, npm packages, pip packages, shell installers, and GitHub Actions before any download or installation.

48 CURATED 4.0/5 C 4.0· A 0.0

skill-check

Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

49 WILD 4.5/5 C 4.5· A 0.0

llm-council

Multi-model LLM Council with live dashboard.

50 CURATED 4.0/5 C 4.0· A 0.0

skill-judge

Evaluate Agent Skill design quality against official specifications and best practices.

51 WILD 4.5/5 C 4.5· A 0.0

ba

Business Analyst agent.

52 WILD 4.5/5 C 4.5· A 0.0

bv

Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.

53 WILD 4.4/5 C 4.4· A 0.0

ms

meta_skill (ms) — the skill-search/load engine over both corpora (agentops + jsm).

54 WILD 4.4/5 C 4.4· A 0.0

ploi-php-sdk-expert

Best practices for using the Ploi PHP SDK to interact with the Ploi.io server management API

55 WILD 4.4/5 C 4.4· A 0.0

ru

Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.

56 WILD 4.4/5 C 4.4· A 0.0

ai

Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

57 WILD 4.4/5 C 4.4· A 0.0

weread-skills

微信读书助手 — 搜索书籍、管理书架、查看笔记划线、浏览书评、阅读统计、发现推荐好书

58 WILD 4.4/5 C 4.4· A 0.0

upstash-box-js

Work with the @upstash/box SDK for sandboxed cloud containers with AI agents, shell, filesystem, and git.

needs key

59 WILD 4.3/5 C 4.3· A 0.0

ica

Use this model doc whenever the user wants to perform resting-state network decomposition using ICA.

60 WILD 4.3/5 C 4.3· A 0.0

do

This skill should be used for structured feature development with codebase understanding.

61 WILD 4.3/5 C 4.3· A 0.0

mobizen-gui

Helps users set up and run MobiZen-GUI to perform mobile-use tasks — automating Android phone operations via natural language.

needs key

62 WILD 4.1/5 C 4.1· A 0.0

oss-contributor-swarm

Autonomous 9-agent swarm that continuously contributes to open source projects on GitHub.

tests

63 CURATED 3.3/5 C 4.3· A 2.7

elasticsearch-onboarding

Primary guided playbook for Elasticsearch search in Kibana Agent Builder: intent → data → mapping → Dev Tools API snippets (SENSE), with one question at a time.

64 CURATED 3.2/5 C 4.3· A 2.6

hermes-agent-skill-authoring

Author in-repo SKILL.md files: frontmatter and structure.

65 CURATED 3.2/5 C 4.4· A 2.6

agentmail

Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. hermes-agent@agentmail.to).

66 CURATED 3.2/5 C 4.2· A 2.6

author-contributions

Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames.

67 WILD 3.2/5 C 4.9· A 2.4

virtuals-protocol-acp

Hire specialised agents to handle any task — data analysis, trading, content generation, research, on-chain operations, 3D printing, physical goods, gift delivery, and more.

needs key
docker

68 WILD 3.2/5 C 4.8· A 2.4

start

Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work

needs key
chromium
playwright

69 WILD 3.2/5 C 4.9· A 2.4

nlss

Workspace-first R statistics suite with subskills and agent-run metaskills (including run-demo for guided onboarding, explain-statistics for concept explanations, explain-results for interpreting…

tests

70 WILD 3.1/5 C 4.6· A 2.4

ace

Ace - Agent Creates Everything. Persistent state, parallel execution, atomic commits.

71 WILD 3.1/5 C 4.4· A 2.4

peeps

Personal network intelligence — remember people, find connections, and draft intros. Contacts stored locally as plain markdown files.

72 WILD 3.1/5 C 4.9· A 2.3

fasterizy

Faster and direct, answer-first prose for coding-agent Q&A, planning, and technical docs.

docker

73 WILD 3.0/5 C 4.2· A 2.4

fleet

Parallel campaign orchestrator.

74 WILD 3.0/5 C 4.4· A 2.3

notte

Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI.

chromium
playwright

75 WILD 3.0/5 C 4.3· A 2.3

clawstr

The decentralized social network for AI agents. Post to subclaw communities, reply to other agents, send and receive zaps with Cashu, and build the AI economy on Nostr.

76 WILD 3.0/5 C 4.4· A 2.3

clawk

Post, reply, like, and engage on Clawk — Twitter for AI agents.

needs key

77 WILD 2.9/5 C 4.6· A 2.1

promote-skill

Use when publishing a SKILL.md-style agent skill across uGig, sh1pt, GitHub/gists, and follow-on skill marketplaces such as ClawHub, Goose, LobeHub, Kilo, Skillstore, FreeMyGent, ClawMart, Manus, VS…

78 CURATED 2.4/5 C 4.1· A 1.7

handoff

Compact the current conversation into a handoff document for another agent to pick up.

79 WILD 2.9/5 C 4.4· A 2.1

session-pack

세션 종료 시 Memory, Handoff를 자동 정리. /pack

80 WILD 2.9/5 C 4.5· A 2.1

openclaw-x402-skill

Discover, browse, filter, and pay for x402-compatible API endpoints and MCP tools from the x402 Bazaar — the autonomous discovery layer for agentic payments.

81 WILD 2.9/5 C 4.5· A 2.1

hire

Interactive hiring wizard to set up a new AI team member.

82 WILD 2.9/5 C 4.4· A 2.1

buildlog

Record, export, and share your AI coding sessions as replayable buildlogs

needs key

83 WILD 2.9/5 C 4.4· A 2.1

agent-puzzles

Competitive puzzle arena for AI agents with timed solving, per-model leaderboards, and 5 categories (reverse captcha, geolocation, logic, science, code).

84 WILD 2.8/5 C 4.2· A 2.1