writing-skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited writing-skills (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Writing skills IS Test-Driven Development applied to process documentation.
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
A skill is a reference guide for proven techniques, patterns, or tools. Skills help future agent instances find and apply effective approaches.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
Frontmatter (YAML):
name and descriptionname: Use letters, numbers, and hyphens onlydescription: Third-person, describes ONLY when to use (NOT what it does)Body format: Use pure Markdown headings for structure. Prefer ## Purpose, ## When to Use, ## Workflow, and ## Verification. Do not use XML-like tags such as <Purpose>, <Workflow>, or <Use_When> as normal top-level sectioning. Use XML-like delimiters only for nested examples, quoted input, external documents, or machine-readable prompt payloads.
---
name: skill-name-with-hyphens
description: Use when [specific triggering conditions and symptoms]
---
# Skill Name
## Overview
What is this? Core principle in 1-2 sentences.
## When to Use
Bullet list with SYMPTOMS and use cases / When NOT to use
## Core Pattern
Before/after comparison or step-by-step
## Quick Reference
Table or bullets for scanning common operations
## Common Mistakes
What goes wrong + fixesCritical: The description field must help agents decide whether to load the skill. It should ONLY describe triggering conditions — never summarize the workflow.
# BAD: Summarizes workflow - agent may follow this instead of reading the full skill
description: Use when executing plans - dispatches subagent per task with review between tasks
# GOOD: Just triggering conditions
description: Use when executing implementation plans with independent tasksWhy this matters: When a description summarizes the skill's workflow, agents may follow the description instead of reading the full skill content.
skills/
skill-name/
SKILL.md # Main reference (required)
supporting-file.* # Only if needed (heavy reference, scripts)Keep inline: Principles, concepts, code patterns under 50 lines, everything else.
Separate files for: API docs/reference over 100 lines, reusable scripts/utilities.
NO SKILL WITHOUT A FAILING TEST FIRSTThis applies to NEW skills AND EDITS to existing skills.
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with subagent |
| RED | Agent violates rule without skill (baseline) |
| GREEN | Agent complies with skill present |
| REFACTOR | Close loopholes while maintaining compliance |
Run pressure scenario WITHOUT the skill. Document exact behavior:
Write skill addressing those specific rationalizations. Don't add extra content for hypothetical cases. Verify agent now complies.
Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
RED Phase:
GREEN Phase:
name uses only letters, numbers, hyphensname and descriptionREFACTOR Phase:
| Anti-Pattern | Why Bad |
|---|---|
| Narrative storytelling | Too specific, not reusable |
| Multi-language examples | Mediocre quality, maintenance burden |
| Generic labels (step1, helper2) | No semantic meaning |
| Description summarizing workflow | Agent follows description, skips full skill |
Create when:
Don't create for:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.