skill judge

Security Community

Skill notes

What is a Skill?

A Skill is NOT a tutorial. A Skill is a knowledge externalization mechanism. Traditional AI knowledge is locked in model parameters. To teach new capabilities: Skills change this: This is the paradigm shift from "training AI" to "educating AI" — like a hot-swappable LoRA adapter that requires no training. You edit a Markdown file in natural language, and the model's behavior changes.

The Core Formula

Good Skill = Expert-only Knowledge − What Claude Already Knows A Skill's value is measured by its knowledge delta — the gap between what it provides and what the model already knows. Expert-only knowledge: Decision trees, trade-offs, edge cases, anti-patterns, domain-specific thinking frameworks — things that take years of experience to accumulate What Claude already knows: Basic concepts, standard library usage, common programming patterns, general best practices

Tool vs Skill

Concept · Essence · Function · Example Tool · What model CAN do · Execute actions · bash, read_file, write_file, WebSearch Skill · What model KNOWS how to do · Guide decisions · PDF processing, MCP building, frontend design Tools define capability boundaries — without bash tool, model can't execute commands. Skills inject knowledge — without frontend-design Skill, model produces generic UI.

Three Types of Knowledge in Skills

When evaluating, categorize each section: Type · Definition · Treatment Expert · Claude genuinely doesn't know this · Must keep — this is the Skill's value Activation · Claude knows but may not think of · Keep if brief — serves as reminder Redundant · Claude definitely knows this · Should delete — wastes tokens

D1: Knowledge Delta (20 points) — THE CORE DIMENSION

The most important dimension. Does the Skill add genuine expert knowledge? Score · Criteria 0-5 · Explains basics Claude knows (what is X, how to write code, standard library tutorials) 6-10 · Mixed: some expert knowledge diluted by obvious content 11-15 · Mostly expert knowledge with minimal redundancy

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Security
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@softaworks · no license declared
Token usage
Heavy
Setup complexity
Guided setup
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 1: First Pass — Knowledge Delta Scan

Read SKILL.md completely and for each section ask: "Does Claude already know this?" Mark each section as: [E] Expert: Claude genuinely doesn't know this — value-add [A] Activation: Claude knows but brief reminder is useful — acceptable

02
Step 2: Structure Analysis

Step 2: Structure Analysis

03
Step 3: Score Each Dimension

For each of the 8 dimensions: Find specific evidence (quote relevant lines) Assign score with one-line justification Note specific improvements if score < max

04
Step 4: Calculate Total & Grade

Grade Scale (percentage-based): Grade · Percentage · Meaning A · 90%+ (108+) · Excellent — production-ready expert Skill B · 80-89% (96-107) · Good — minor improvements needed C · 70-79% (84-95) · Adequate — clear improvement path

05
Step 5: Generate Report

Step 5: Generate Report

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.