write-a-skill
Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progressive-disclosure conventions. Trigger…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-13 00:15
Agents & models
26,215 results
backlog-manager
Manage an engineering backlog for humans and AI agents: review the whole loop, classify issues, improve issue quality, sync pull-request state, and label safe…
army-agent-contract
Writes the session contract for a fleet agent - what it may read, what it may write, what it owns, what it produces, and when it is done - and fixes agents…
army-fanin
Reconciles parallel agent worktrees into one repository with per-change provenance - agent, harness, cost, tests - then archives the losing branches and reaps…
army-hitl
Implements non-blocking human-in-the-loop for a running agent fleet - agents ask in-thread and release their session, verdicts bind the exact action, and…
army-join
Lets a session from another harness join a running fleet as a subagent, cross-reviewer or human-in-the-loop, via a scoped context package whose output is…
army-run
Starts and operates a continuously running agent fleet - supervisor loop plus web workspace - and diagnoses a loop that is not dispatching or an agent that…
army-workload-adapter
Points a running agent fleet at an existing project - importing its roster and charters, tailing its human-in-the-loop files read-only, and opening a write…
add-skill
Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use…
add-skill
Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use…
advise-session
Opens a persistent, project-aware session with every logged-in coding-agent CLI (Claude Code, Codex, Grok CLI, Kimi Code, Antigravity), returns one session id,…
add-skill
Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use…
agent-evaluation
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality,…
analyzing-mlflow-session
Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation,…
mlflow-agent
Master dispatcher for all MLflow workflows. Use this skill when the user wants to do anything with MLflow — tracing, evaluating, debugging, or improving an…
mlflow-onboarding
Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart…
awesome-skills-deepdive
Deep dive analysis of the awesome-openclaw-skills repository. Forks and clones the upstream repo, then systematically fetches every skill's SKILL.md source…
generate-judgements
Use when creating or updating test judgement definitions (judge_definitions) for an agent skill evaluation YAML config. Analyzes a skill's SKILL.md and…
autoplan
Fully automated review pipeline: CEO, Design, and Eng reviews with auto-decisions using 6 principles (completeness, boil lakes, pragmatic, DRY, explicit over clever, bias toward action). Only pauses for premise confirmation. Classifies decisions as Mechanical (silent) or Taste (surfaced at final gate).
codex
Multi-AI second opinion via OpenAI Codex CLI. Three modes: Review (pass/fail gate), Challenge (adversarial edge-case finder), Consult (freeform with session continuity). Read-only with streaming output and thinking traces. Cross-model analysis when review has already run.
consult
Cross-tool AI consultation — get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI
create-agent-skills
Expert guidance for creating, writing, building, and refining Claude Code Skills. Covers SKILL.md authoring, router patterns, progressive disclosure, references, workflows, templates, and self-healing via heal-skill.
debate
Structured multi-round debate between AI tools with proposer/challenger roles and verdict
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies