arc-skill

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.

pbshgthm/arc-skill

View on GitHub ↗

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.

arc-skill grew +1.1% in the last 30 days, ranks 2608th of 2,792 in Agent SDK / Framework, last commit 24 days ago.

Star trajectory

81 days tracked
2026-08-3190 stars today2026-11-21
Momentum

+1.1% in 30d, below the Agent SDK / Framework median of +1.5%.

Maintenance

Last commit 24 days ago, staler than the median of 14d.

How it compares in Agent SDK / Framework

arc-skill
90
stars
+1.1% 30d
commit 24 days ago
Agent SDK / Framework median
290
stars
+1.5% 30d
commit ~14d ago
Leader · rea
471.9k
stars
+31.2% 30d
commit today

Ranked 2608th of 2,792 by stars.

Ranked by shared tags, then keywords, then stars
  1. Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness…

    +3.7k (+631%) in 30d · Committed today · Python · Apache-2.0

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

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

    -4 (-4.2%) in 30d · Committed 95d ago · Shell · AGPL-3.0

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

  3. 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

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

    +15 (+1.9%) in 30d · Committed 5d ago · TypeScript · MIT

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

  5. Research-backed, eval-driven skills for AI agents

    +10 (+4.3%) in 30d · Committed 59d ago · Python · Apache-2.0

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

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

    -7 (-6.2%) in 30d · Committed 136d ago · Other license

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

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

    +0 (+0.0%) in 30d · Committed 56d ago · Python · MIT

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

  8. Agent-Native multi-platform reverse engineering and CWE-602 client-side authorization audit workbench.

    +486 (+27%) in 30d · Committed 4d ago · Lua · GPL-3.0

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

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

    +248 (+20%) in 30d · Committed yesterday · Go · Apache-2.0

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

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

    Committed 17d ago · Go · MIT

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

Language
Python
License
-
Contributors
1
Forks
4
Watchers
0
Open issues
0
Releases
0
Created
2026-08-19
Stars this week
+0

You've seen where arc-skill 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 arc-skill?

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

Claim this page