butler-workflow
1849Skill Claude CodeCodex
Orchestrate Butler MCP for multi-agent coordination, persistent memory, and cross-session continuity.
not rated 9 22d ago A 23 tokens
agent-protocols
1850insodimension/awesome-agent-protocols
Skill Claude CodeCodex
Guide agent harness engineering toward the right AI agent protocol standards (MCP, A2A, ACP, AG-UI, AP2, x402, etc.) instead of reinventing. Analyzes what you're building, recommends protocols, pulls spec details and wire-message examples, checks compliance, and surfaces contribution opportunities. Triggers…
not rated 9 3mo ago A 163 tokens
original CC0-1.0
opencode-automator
1851alphaparkinc/genpark-skill-opencode-automator
Skill Claude CodeCodex
OpenCode Automator — High-performance execution agent that utilizes dynamic code generation (Python/JS) to automate complex, multi-step workflows with mathematical precision and API reliability.
not rated 9 4mo ago A 39 tokens
iron-system
1852Skill Claude CodeCodex
Meta-skill for reverse loop engineering that transforms an AI agent's approach to any complex task. Combines systematic deconstruction (reverse engineering) and iterative construction (loop engineering) in an EXTRACT→SYNTHESIZE→BUILD→AUDIT cycle. Includes 7 named tactical loops (FORGE, SIEGE, PRISM, RAZOR, MIRROR…
not rated 9 2mo ago A 235 tokens
original MIT
using-nilscript
1853Skill Claude CodeCodex
Use when an MCP server exposes nil tools (a NILScript / Network Intent Layer gate to a backend) — teaches the propose→approve→commit→rollback discipline, reversibility tiers, and how to read refusals so an agent drives any NIL backend safely and correctly.
not rated 9 1mo ago A 60 tokens
atrib
1854Skill Claude Code
Use atrib as the verifiable substrate for memory, reasoning, and getting sharper over time, not as instrumentation that observes you from the outside. atrib gives the agent two cognitive verbs: attest (write: sign an observation, mark a past record's importance, or supersede a prior position) and recall (read: look up…
not rated 9 today A SkillSpector: warn 242 tokens
original Apache-2.0
project-scaffold
1855Skill Claude CodeCodex
Set up agent-friendly project structures with AGENTS.md, specs, workflows, and TODO files for long-horizon autonomous execution. Use when starting a new project, onboarding to a brownfield codebase, or when a project lacks clear documentation for agents to follow. Do NOT use when the project already has a…
not rated 9 7mo ago A 100 tokens
Reins
1856Skill Claude CodeCodex
Reins CLI skill for scaffold/audit/doctor/evolve workflows. Use when setting up or evaluating harness-engineering repo readiness and maturity with Reins commands.
not rated 9 6mo ago A 35 tokens
original MIT
AgentPrecept
1857Skill Claude CodeCodex
A project workflow for coordinating several coding agents on the same software project. It uses shared project structure, decisions, handoffs, checklists, and memory so agents can continue each other's work.
not rated 9 3mo ago A 0 tokens
original MIT
skill-creator
1858Skill Claude CodeCodex
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 9 12d ago A 45 tokens
skill-creator
1859Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 9 3mo ago A 64 tokens
cc-godmode
1860cubetribe/openclaw-godmode-skill
Skill Claude CodeCodex
Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW.
not rated 9 4mo ago A 23 tokens
original MIT
agents
1861zllovesuki/cloudflare-agent-skills
Skill Claude CodeCodex
Build Cloudflare Agents SDK applications for autonomous multi-step tool use, AIChatAgent chat agents, Durable Object-backed state, tools, scheduling, callable methods, WebSockets, SQL state, and constrained agent behavior. Use when RAG or Workflows are not enough.
not rated 9 4mo ago A 55 tokens
runyuan-wang/book-to-skill-distillation
Skill Claude CodeCodex
End-to-end workflow for rewriting a book, long PDF, EPUB, manual, course, guideline library, same-domain multi-book source pack, large database, or methodology into an agent-native LingTai / Agent Skill structure. Use when the task is not a summary, but a reusable skill/knowledge system: source triage…
not rated 9 2mo ago A 120 tokens
review-task
1863Skill Claude CodeCodex
Guide for reviewing completed tasks and deciding whether to create or update skills. Use after task completion to evaluate skill usage and determine if new skills should be created or existing ones updated.
not rated 9 6mo ago A 38 tokens
original MIT
replit-prd
1864Skill Claude CodeCodex
Generate sequential PRD prompt sequences optimized for Replit Agent development. Use when: building applications with Replit Agent, creating PRDs or technical specifications for Replit, experiencing Replit Agent failures and needing better prompting strategy, or decomposing complex projects for Replit Agent. Triggers…
not rated 9 8mo ago A 86 tokens
original MIT
codebase-context
1865Skill Claude CodeCodex
Generates a codebase-context.md file that provides pre-built context for AI agents. This skill analyzes your project structure, patterns, and conventions to create a comprehensive context document that reduces token usage and improves agent effectiveness. Use when setting up a new project for AI-assisted development…
not rated 9 7mo ago A 67 tokens
original MIT
goal-loop
1866Skill Claude CodeCodex
The /goal pattern: cron jobs that run until an objective condition is met, checked by an independent model (maker/checker split). Source: loop engineering framework by 0xCodez / Anthropic evaluator-optimizer pattern.
not rated 9 2mo ago A 49 tokens
original Apache-2.0
codex-harness-mcp
1867Skill Codex
Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits…
not rated 9 4mo ago A 232 tokens
original MIT
ai-knot
1868Skill Codex
Deterministic, self-hosted long-term memory for AI agents. Trigger when the user wants persistent memory, MCP-backed assistant memory, or wants to integrate ai-knot into Python, CrewAI, LlamaIndex, AutoGen, the OpenAI Agents SDK, PydanticAI, LangChain/LangGraph, TypeScript, or HTTP services. This is the default…
not rated 9 2mo ago A 89 tokens
original MIT
upjack-app-builder
1869Skill Claude CodeCodex
Builds complete, compliant NimbleBrain Upjack apps from natural language descriptions. Generates manifest, entity schemas, skills, context, seed data, and server entry point. Use when creating a new Upjack app, building an AI-native app, or scaffolding a domain-specific application. Triggers include "create me a todo…
not rated 9 5mo ago A 92 tokens
original Apache-2.0
skill-creator
1870kasperjunge/agent-resources-legacy
Skill Claude Code
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 9 8mo ago A 45 tokens
self-evolving-agent
1871Skill Codex
Build a phase-aware capability-evolution runtime for OpenClaw and coding agents. Use when the agent should classify work into tasklight, taskfull, agendareview, or promotionreview mode; retrieve only the most relevant prior records; write canonical evidence into .evolution/records; maintain a capability map and…
not rated 9 5mo ago A 77 tokens
original MIT
effective-harnesses
1872Skill Claude Code
A framework for running an agent over a long project, with project setup, feature management, and progress tracking.
not rated 9 7mo ago A 25 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: