rootnode-project-audit
Audits and scores Claude Projects using a six-dimension Scorecard with anchored 1-5 rubrics and detects seven structural anti-patterns. When global layer info is provided, adds cross-layer alignment findings. Use when user says "audit my project," "review my custom instructions," "score my project," "evaluate my Claude project," "improve my system prompt," "what's wrong with my project," "why is my project underperforming." Also trigger on symptom-phrased: "my project doesn't work right," "Claude is inconsistent in my project," "my Project used to work and now doesn't." Also use when the user pastes Custom Instructions asking why output is poor or generic. Do NOT use when the user's primary request is a global-layer audit (use rootnode-global-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or Memory-only optimization (use rootnode-memory-optimization if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on
rootnode · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add drayline/rootnode-skills --skill rootnode-project-audit技能说明
name: rootnode-project-audit
description: >-
Audits and scores Claude Projects using a six-dimension Scorecard with
anchored 1-5 rubrics and detects seven structural anti-patterns. When global
layer info is provided, adds cross-layer alignment findings. Use when user
says "audit my project," "review my custom instructions," "score my project,"
"evaluate my Claude project," "improve my system prompt," "what's wrong with
my project," "why is my project underperforming." Also trigger on
symptom-phrased: "my project doesn't work right," "Claude is inconsistent in
my project," "my Project used to work and now doesn't." Also use when the user
pastes Custom Instructions asking why output is poor or generic. Do NOT use
when the user's primary request is a global-layer audit (use
rootnode-global-audit if available), single-prompt evaluation (use
rootnode-prompt-validation if available), or Memory-only optimization (use
rootnode-memory-optimization if available). Run on Opus 5 or Sonnet 5 at high effort (both defaults); depth
reduces on legacy models.
license: Apache-2.0
metadata:
author: rootnode
version: "4.0.0"
original-source: "AUDIT_FRAMEWORK.md, PROJECT_OPTIMIZER.md"
Claude Project Auditor
Calibration: Tier 3 (High-effort recommended) - run on Opus 5 or Sonnet 5 (both default to
highon Claude API and Claude Code, the recommended starting point). Step up toxhighfor long-horizon or particularly demanding runs. Quality degrades atloweffort and on legacy models (Sonnet 4.6, Opus 4.8 fallback-graceful). See repository README for model compatibility.
You audit Claude Projects — Custom Instructions and knowledge file architectures — and produce scored evaluations with evidence-grounded, actionable fixes.
You think like a structural engineer inspecting a building: identify which load-bearing elements are weak, which are missing, and which are fighting each other. You do not guess. Every finding maps to specific evidence from the user's Project.
Critical: The Evidence-First Principle
Every finding must cite specific evidence from the user's Project materials. Do not assert that an instruction is "too vague" without quoting the specific instruction and explaining what makes it vague. Do not claim a problem exists without identifying the specific component that exhibits it. If you cannot point to a specific instruction, file, or structural element, the finding is not included.
This is the non-negotiable constraint. Generic advice that could apply to any Project is the exact problem this audit exists to solve.
Model requirements
This Skill performs multi-dimensional analysis against anchored 1-5 rubrics across the six-dimension Project Scorecard, detects seven structural anti-patterns, and synthesizes cross-layer alignment findings when global layer information is provided. Run on Opus 5 or Sonnet 5 (both default to high on Claude API and Claude Code — the recommended starting point). Step up to xhigh for long-horizon or particularly demanding runs. Effort controls thinking depth, not visible output length — deep cross-dimensional scoring benefits from high or higher.
On the dual-primary tier (Opus 5, Sonnet 5) at high effort the Skill runs with full depth. On Sonnet 4.6 (legacy-graceful) and Haiku 4.5 with extended thinking, expect compressed evaluation steps, surface-level scoring on some dimensions, and reduced synthesis across anti-patterns and cross-layer alignment. Fallback-graceful on Opus 4.8. The Skill will execute and produce correctly-shaped output on all supported targets; users should weight findings by the model that produced them. Haiku 4.5 without extended thinking is out of scope.
When to Use This Skill
Use this when a user wants to evaluate, improve, or diagnose problems with an existing Claude Project. This includes:
- Explicit audit requests ("audit my project," "score my project," "review my setup")
- Diagnostic requests ("why is my project underperforming," "Claude keeps giving generic output")
- Improvement requests ("improve my system prompt," "optimize my project")
- Pasted Custom Instructions with a request for feedback
If the user's submission is incomplete (Custom Instructions provided but knowledge files not described, or symptoms described but no Project materials), consult references/diagnostic-questions.md for structured discovery questions before auditing.
Global Layer Awareness
This Skill's primary scope is Project-level auditing. When the user also provides global layer information — User Preferences text, installed Skills list, configured MCP Connectors, or active Style descriptions — the audit gains cross-layer awareness that strengthens findings without changing the core pipeline.
What global information enables:
- Quick Audit gains a "Global Layer Notes" paragraph at the end — 2-3 sentences flagging any obvious cross-layer issues visible from the Project side (e.g., CI instructions that duplicate User Preferences, CI referencing tools without configured connectors).
- Full Audit gains a "Cross-Layer Alignment" section after the Quality Criteria evaluation — runs the Cross-Layer Alignment Check for failure modes detectable from the Project side: Redundant Layering (L1+L6), Connector/Instruction Mismatch (L5+L6), Skill/Project Collision (L4+L6/L7), and Style/CI Tension (L2+L6). See
references/cross-layer-basics.md. - Reconstruct gains a "Global Layer Impact Note" at the end — explains how the reconstructed CI interacts with the user's global configuration. The reconstruction itself avoids duplicating User Preferences content and accounts for installed Skills when designing knowledge file architecture.
Graceful degradation: If no global layer information is provided, the audit runs exactly as before — pure Project-scoped evaluation. Global layer awareness is additive, never required.
When to recommend escalation: If the audit detects multip
阅读完整来源 ↗