Loading...
Loading...
Found 11,931 Skills
Autonomously optimize an existing AI skill by running it repeatedly against binary evals, mutating one instruction at a time, and keeping only changes that improve pass rate. Based on Karpathy-style autoresearch, but applied to SKILL.md iteration instead of ML training. Use when optimizing a skill, benchmarking prompt quality, building evals for a skill, or running self-improvement loops on reusable agent instructions. Triggers on: skill-autoresearch, optimize this skill, improve this skill, benchmark this skill, eval my skill, run autoresearch on this skill, self-improve skill.
Cross-platform landscape scan before planning or implementation. Researches context, workarounds, existing solutions, and structural gaps, then writes reusable survey artifacts for OMC, OMX, OHMG, and general agent workflows.
Ouroboros specification-first AI development — the complete system. Socratic interviewing crystallizes vague ideas into immutable specs (Ambiguity ≤ 0.2) before any code is written. Nine Minds agents (socratic-interviewer, ontologist, seed-architect, evaluator, contrarian, hacker, simplifier, researcher, architect) execute the Double Diamond. Ralph mode loops with state persistence until verification passes — the boulder never stops. Use when user says "ralph", "ooo", "ooo interview", "ooo seed", "ooo run", "ooo evaluate", "ooo evolve", "ooo unstuck", "ooo status", "ooo ralph", "stop prompting", "start specifying", "specification first", "socratic interview", "don't stop", "must complete", "keep going", or "the boulder never stops".
Integrated AI agent orchestration skill that combines plannotator, ralphmode, team or bmad execution, agent-browser verification, and agentation feedback loops, while maintaining a project-local `.jeo` ledger for planning, development, and QA. Use when the user wants an end-to-end multi-agent workflow with plan approval, implementation, UI review, cleanup, and durable task history. Triggers on: jeo, annotate, ui-review, multi-agent orchestration.
Find the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same session. Whenever you start a task, use this skill first.
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.
Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "code review", "check my changes", or wants a comprehensive multi-perspective code review of the current branch's changes. Spawns parallel specialist agents (security, database, reliability, compatibility, data integrity, performance, frontend, copy) that independently review the diff and produce a converged report. Also includes two generalist reviewers for convergence validation.
Use when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.
Build and maintain a personal knowledge base using Karpathy's llm-wiki methodology across Claude Code, Codex, and OpenClaw agents.
Run structured multi-agent debates using argue CLI for cross-examined, high-confidence answers. Use when facing strategic decisions, ambiguous trade-offs, architecture debates, or questions where multiple perspectives improve the answer. Triggers on: argue, debate, cross-examine, second opinion, multi-agent, 'Should we X or Y?' with real stakes, consensus-building, risk analysis, or confirmation-bias mitigation.
Delegate subtasks to specialized AI agents. Use when: complex workflows need multi-agent collaboration or specialization.
Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendations. Use when auditing a skill, comparing skills, prioritizing improvements, or performing quality control on a skill library. Activate on "grade skill", "evaluate skill", "skill quality", "skill audit", "skill review", "rate skill". NOT for creating skills (use skill-architect), grading code quality, or evaluating non-skill documents.