craft-skills

Research-backed, eval-driven skills for AI agents

ZSeven-W/craft-skills

View on GitHub ↗

Research-backed, eval-driven skills for AI agents

craft-skills grew +4.3% in the last 30 days, ranks 1542nd of 2,795 in Agent SDK / Framework, last commit 60 days ago.

Star trajectory

76 days tracked
2026-09-06242 stars today2026-11-22
Momentum

+4.3% in 30d, above the Agent SDK / Framework median of +1.4%.

Maintenance

Last commit 60 days ago, staler than the median of 15d.

How it compares in Agent SDK / Framework

craft-skills
242
stars
+4.3% 30d
commit 60 days ago
Agent SDK / Framework median
290
stars
+1.4% 30d
commit ~15d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 1542nd of 2,795 by stars.

Ranked by shared tags, then keywords, then stars
  1. 面向 AI/CS 科研的多 Skill 实验智能体:助力全自动科研实验,以 Claim 驱动、骨干实验优先、独立结果审计与 Evidence Freeze,把发散的模型能力收束为可追溯、可复现、可收敛的论文证据。

    Committed 31d ago · Python · Apache-2.0

    Shares Agent SDK / Framework, Agent Skills, Evaluation & Guardrails

  2. An agent harness built for teaching: ~1,400 lines of Python with goal mode, permissions, skills, MCP and…

    Committed 14d ago · Python · MIT

    Shares Agent SDK / Framework, Agent Skills, Evaluation & Guardrails

  3. Verification-gated skill routing and self-improvement harness for Hermes-style agent skills

    +0 (+0.0%) in 30d · Committed 57d ago · Python · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Agent Skills

  4. Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness…

    +3.8k (+634%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework, Agent Skills

  5. Evaluate Agent Skills and environments. Evolve Skills with evidence.

    +243 (+19%) in 30d · Committed 2d ago · Go · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework, Agent Skills

  6. A test runner for agentskills.io-style AI agent skills

    +16 (+2.0%) in 30d · Committed 6d ago · TypeScript · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework, Agent Skills

  7. Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks…

    Committed 18d ago · Go · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Agent Skills

  8. SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments…

    -5 (-4.5%) in 30d · Committed 137d ago · Other license

    Shares Evaluation & Guardrails, Agent SDK / Framework, Agent Skills

  9. AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup…

    -4 (-4.2%) in 30d · Committed 96d ago · Shell · AGPL-3.0

    Shares Evaluation & Guardrails, Agent SDK / Framework, Agent Skills

  10. An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on…

    +1 (+1.1%) in 30d · Committed 24d ago · Python

    Shares Agent SDK / Framework, Evaluation & Guardrails, Agent Skills

Language
Python
License
Apache License 2.0
Contributors
1
Forks
35
Watchers
1
Open issues
0
Releases
0
Created
2026-08-03
Stars this week
+0

You've seen where craft-skills stands today.

Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain craft-skills?

Claim this page to add your own call-to-action.

Claim this page