skill-authoring

Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Quality-gated skill authoring for Claude Code. Build, judge, and ship skills that earn their tokens.

LLM knowledge base + zero-to-hero course for authoring production-quality AI agent skills (SKILL.md). 30+ wiki articles compiled from 18 repos, 700K+ stars combined.

Meta Agent Skill: author deterministic, weak-model-friendly Agent Skills validated against the Hermes runtime. agentskills.io-compliant, with validators and source grounding.

A plugin for Claude Code, Cursor, Gemini CLI, Codex that analyzes any plugin for cross-platform portability gaps and creates missing platform artifacts. No CLI, no scripts, no framework. Just skills that help you author your skills and plugins for multiple agentic tools

YLF 书籍蒸馏器 — 把一本书从读过到真正掌握，再到随时可调用的能力 skill

YLF 工作资料蒸馏器 — 把任意工作资料蒸馏为可直接调用的跨平台 AI skill

Quality layer for Agent Skills (agentskills.io) — lint, hash, sign, version, eval your SKILL.md files. 10 structural checks, Ed25519 signing, semantic diff, 3-stage eval pipeline. Bidirectional SKILL.md ↔ AIF conversion.

Skill scaffolding and validation, a shared catalog, and runtime overlay policy for local agent environments.

A toolkit for authoring, validating, documenting, and publishing reusable AI agent skills.

A meta-skill for AI coding agents: it teaches Claude Code, Codex, Cursor and OpenCode how to write, review and install their own Agent Skills - from naming rules to the description that decides whether a skill ever triggers.

A portable Agent Skills authoring skill（从需求、项目文档与真实工作流构建可复用、可验证的 Skill）——涵盖 SKILL.md、触发边界、references/scripts、evals 与持续迭代。Works with Claude Code, Codex, OpenCode, VS Code Copilot & any compatible agent.

Canonical workflow skill for designing, authoring, and restructuring agent skills - process discipline (modes, synthesis gates, depth rubric) merged with the skill-anatomy standard (rationalization guards, verification, context efficiency)

Agent Skill specification with a parser turning SKILL.md files into strongly-typed skill objects for downstream agent tooling.

Build reliable, self-contained AI skills from natural-language source and executable scripts—with deterministic builds and provenance.

Retired 2026-09-19: Claude Code and Codex now search and suggest skills natively. Source kept in m1nga/skills history.

编写、审查和优化 Agent Skill 的顶层原则：11 条原则，分通用/结构/流程/编写四层

Clean, portable agent skills for DeepSeek Harness, Claude Code and any harness reading the Agent Skills standard. Plain text, nothing to build. Every skill ships a checker and a measured evaluation protocol — and says what was not verified.

Build lean SKILL.md-based skills: decide when a skill is justified, draft a minimal skill skeleton, and audit skills for bloat and drift.

AI agent architecture, parallel orchestration, skill authoring, knowledge graph systems, and automation frameworks