l0z4n0-a1

Skill Anthropic Grade Optimizer — Development skill for Claude Code

Development community

Audits Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP, prompts, api_config) against 189 cited Anthropic rules across 11 dimensions.

How to install Skill Anthropic Grade Optimizer

This entry records only its repository, not the path inside it, so there is no exact command to give. Open l0z4n0-a1/skill-anthropic-grade-optimizer and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Skill Anthropic Grade Optimizer does

Audits Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP, prompts, api_config) against 189 cited Anthropic rules across 11 dimensions. Cite or stay silent. Voice drift trumps score.

Alternatives in Development

Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
Custom Dimensions — Custom Dimensions and Event Parameters 242 ★
Statistics Page Writer — Deep-research and publish a sourced statistics page journalists cite for months 195 ★

README

anthropic-grade-optimizer

[![CI](https://github.com/l0z4n0-a1/skill-anthropic-grade-optimizer/actions/workflows/ci.yml/badge.svg)](https://github.com/l0z4n0-a1/skill-anthropic-grade-optimizer/actions/workflows/ci.yml) [![Self-audit](https://img.shields.io/badge/self--audit-98%2F100-brightgreen)](evals/SELF-AUDIT.md) [![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE) [![Version](https://img.shields.io/badge/version-1.0.0-blue)](CHANGELOG.md)

**Cite or stay silent. Artifact type comes first. Voice drift trumps score.** An auditor for Claude-directing artifacts against 189 cited Anthropic rules across 11 dimensions, calibrated per model. Every finding ships with verbatim quote and source URL. Authorial voice is preserved by contract — not by accident.

Why this exists

Most prompt linters score what's *easy to count* and call it a day. This one starts from a different premise: **a Claude-directing artifact is a cognitive contract, not a configuration file.** Audit it like a contract — cite the clause, name the violation, propose the patch, and never rewrite the author into someone else. If the auditor cannot point to the doctrine, the auditor stays silent.

That is the line this skill refuses to cross, and the reason it audits itself on every release.

The Three Laws

Every finding, every diff, every score lives under these three rules. Violating any one collapses the others.

Cite or stay silent. Every 🔴 / 🟡 finding carries a source_url and a verbatim quote. No source → no finding.
Artifact type comes first. A SKILL.md rule fired against a CLAUDE.md is a false positive, not a finding. The rubric is type-aware before it is severity-aware.
Voice drift trumps score. An optimization that lifts the score by diluting the operator's voice is a regression in disguise. Drift over 10% aborts; with --push-ceiling the gate tightens to 5%.