Building agents skills

A-EVO-Lab/a-evolve

Skill Claude Code

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.

countbot-ai/CountBot

Skill Claude CodeCodex

A command-line manager for teams of AI agents, where each agent has a role and the team can use different workflows or models.

maddada/Ghostex

Skill Claude CodeCodex

Use this skill to execute a multi-phase coding task with a Fable-planned, Codex-implemented, Fable-verified pipeline inside Ghostex: the invoking session plans inline and writes a phase plan file, launches one Codex (gpt-5.6) worker pane per phase through the Ghostex CLI, then launches a Fable verifier pane that…

getomnico/omni

Skill Claude Code

Build a new connector for Omni workplace agents. Use when creating a new data source integration, scaffolding connector structure, exposing agent actions/tools/resources, or needing help with the connector SDK.

tenfoldmarc/llm-council-skill

Skill Claude CodeCodex

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this'…

LSTM-Kirigaya/openmcp-client

Skill Codex

Guidance for installing, upgrading, verifying, and using the npm package @agent-ruler/openmcp and its openmcp CLI. Use when a user asks how to install OpenMCP from npm, start or diagnose the Gateway, use OpenMCP CLI commands, configure skills through SKILLPATH, troubleshoot global installs, or publish/test the CLI…

pskoett/self-improving-agent

Skill Claude CodeCodex

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge…

Ark0N/Codeman

Skill Claude CodeCodex

Drive Codeman, the session manager this agent is running inside, over its HTTP API: list sessions, start worker sessions, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session…

ClawRunr/JavaClaw

Skill Claude CodeCodex

Create new skills, modify and improve existing skills for JavaClaw. Use when users want to create a skill from scratch, edit or improve an existing skill, or refine a skill's description so it triggers more reliably. Also use when a user asks to "turn this workflow into a skill", "save these instructions as a skill"…

modiqo/skillspec

Skill Claude CodeCodex

Universal first-hop for any tool-backed request that may execute, inspect, mutate, automate, browse, call, fetch, generate, install, test, run, or create artifacts through CLI, shell, API, adapter, browser, provider, local process, or external tool, with trace, alignment, evidence capture, and future recall. Use for…

microsoft/TypeAgent

Skill Claude Code ✓ vendor

Configure TypeAgent integration mode and settings.

infragate/capa

Skill Claude CodeCodex

Manage capa CLI configuration — capabilities.yaml / capabilities.json, skills, MCP servers, tools, hooks, sub-agents, rules, plugins, AGENTS.md / CLAUDE.md, security options, tool exposure modes, capa wrap shadow workspaces, --passthrough native writes, registries (including Claude marketplaces), activity traces, and…

joelhooks/swarm-tools

Skill Claude CodeCodex

Implicit feedback scoring, confidence decay, and anti-pattern detection. Use when understanding how the swarm plugin learns from outcomes, implementing learning loops, or debugging why patterns are being promoted or deprecated. Unique to opencode-swarm-plugin.

DenisSergeevitch/repo-task-proof-loop

Skill Claude CodeCodex

Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASKID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's Claude guide file with the workflow, and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

alikon-art/DeterminFlow

Skill Claude CodeCodex

A guide for working with DeterminFlow workflows, which are automated sequences of tasks connected by steps and decisions.

mikehasa/agentacct

Skill Claude CodeCodex

Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.

modoojunko/awesome-novel-agent

Skill Claude CodeCodex

A nine-agent workflow for writing a novel with AI, from creating the initial setting through organizing the finished material. It can also bring an existing novel into the workflow.

whitelonng/dshcode

Skill Claude CodeCodex

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider…

ksimback/looper

Skill Claude Code

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a…

alinaqi/maggy

Skill Claude Code needs its repo

Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API.

mgechev/skillgrade

Skill Claude CodeCodex needs its repo

Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.

zli12321/LHTB

Skill Claude Code

Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.

eunomia-bpf/agentsight

Skill Codex

Analyze Codex, Claude, AgentSight, or other agent trajectories to find repeated failure modes and turn them into evidence-gated skill improvements. Use when the user asks why agents keep making the same mistakes, whether a skill should change, how to learn from many sessions, how to convert repeated workflows into…

arcjet/arcjet-js

Skill Claude CodeCodex needs its repo

Integrate Arcjet security into a Vercel Eve agent using @arcjet/guard — add guard gates to tools and connections, screen inbound messages, and record agent lifecycle events correlated to the session. Use when asked to add Arcjet to an Eve agent, rate limit its tools, guard connection access, or screen inbound messages.