Sahir619/
fable-method
Sahir619/fable-methodSkills
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
2.3k
greyhaven-ai/
autocontext
greyhaven-ai/autocontextHarnesses
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
1.3k
skillberry-ai/
cap-evolve
skillberry-ai/cap-evolveHarnesses
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
56
thiientv/
godmode
thiientv/godmodeSkills
Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.
94
agentvitals/
checkup
agentvitals/checkupSkills
AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scoring, a personality-style title, and a public cross-platform leaderboard. One-line install for Claude Code / OpenClaw / Codex / Coze. Bilingual EN/ZH.
95