Skill Evaluation Graph — Development skill for Claude Code
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.
How to install Skill Evaluation Graph
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MaxLaurieHutchinson/skill-evaluation-graph and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Skill Evaluation Graph does
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.
Alternatives in Development
- Understand Anything — Graphs that teach graphs that impress 80.7k ★
- PaperSpine — PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central a 5k ★
- Claude SEO — Multi-Platform Agent Instructions — For Cursor, Cursor Cloud Agents, Google Antigravity, and Gemini CLI 5k ★
README
SEG: Skill Evaluation Graph
[](LICENSE) [](https://github.com/MaxLaurieHutchinson/skill-evaluation-graph/actions/workflows/architecture.yml)
**Evidence-driven evaluation for Agent Skills.**
SEG combines deterministic static analysis, an executable Evaluation Graph, fail-closed gates, behavioural Control vs. Treatment trials, and bounded Repair Verification.
Why SEG exists
A valid `SKILL.md` is not the same thing as a reliable skill.
SEG evaluates several independent concerns without allowing one good score to hide a critical failure:
- Specification Conformance — Agent Skills and configured host manifests.
- Evaluation Integrity — required Evaluators must complete successfully.
- Safety & Privacy — destructive commands and common workstation-path leaks.
- Link Integrity — relative references and package assets.
- Static Quality — deterministic heuristics for routing, structure, context efficiency, and maintainability.
- Behavioural Reliability — optional live Control vs. Treatment trials through a Harness Adapter.
**Gates own acceptance. Scores are supporting evidence.**
Quick start
Run a deterministic evaluation:
python plugins/skill-evaluation-graph/scripts/audit_skill.py Run the Evaluation Graph and bounded repair loop. This is read-only by default:
python plugins/skill-evaluation-graph/scripts/run_loop.py --target-score 95Preview and then explicitly apply a verified Repair Candidate:
python plugins/skill-evaluation-graph/scripts/run_loop.py --applyRun static behavioural policy analysis:
pythRelated Skills
Clojure Skills
Claude Code / Gemini CLI / Codex skill for Clojure development — parenthesis repair, nREPL evaluation, clojure
Opencode Antigravity Quota
OpenCode plugin to monitor Antigravity API/Gemini Cli quotas across multiple accounts.
MigrationGuard Harness
An Evidence-Driven Agent Harness for Safe Dependency Migration, featuring Claude-powered code repair, differen
Offload
Claude Code skill: delegate plan execution to agy (Antigravity/Gemini) subagents, with an evidence gate instea
Skillry
Installable, permission-bounded, multi-platform agent skills & subagents for Claude Code, Codex, Copilot & Gem
Artcraft Skills
Agent skills (SKILL.md) for the ArtCraft Rust creative suite — evidence-verified, MCP/CLI surfaces — for Claud
Related Agents
Paf Reviewer
Runs one phone-a-friend relay or review command in the background and reports back a receipt plus the findings
CLI Subagents Antigravity
Runs a task in Google Antigravity (agy, Gemini models) on the user's Google account (CLI Subagents; extra Goog
Gemini Delegate
Delegate broad, purely reading analysis over a lot of material to Gemini (Antigravity CLI) — condense large di
