nijaru/creating-skills
dot_claude/skills/creating-skills/SKILL.md
Use when creating, modifying, or testing AI agent skill definitions (.md files) to ensure they are high-performance, compact, and verified.
testing
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add nijaru/dotfiles creating-skillsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 5:05 PM90.7s1 file scanned
SKILL.md
- name:
- creating-skills
- description:
- Use when creating, modifying, or testing AI agent skill definitions (.md files) to ensure they are high-performance, compact, and verified.
- allowed-tools:
- Read, Grep, Glob, Bash, Edit, Task
Creating Skills (TDD Methodology)
Follow the superpowers:writing-skills workflow to turn techniques into reusable, high-performance skills.
The Iron Law
Every skill must be empirically verified against 3+ test cases before finalization.
Workflow (Skill TDD)
- Research: Identify the specific failure mode or "slop" the skill solves.
- Test: Write 3+ prompts that currently fail or produce generic AI output.
- Draft Iron Law: Define a single, absolute constraint (e.g., "Never use passive voice").
- Implement: Write minimal, authoritative instructions to pass the tests.
- Pressure Test: Compare outputs with and without the skill.
- Prune: Remove all filler, "AI-isms," and meta-commentary.
Structure & Format (SOTA)
1. Frontmatter
- Description: MUST start with "Use when..." and contain ONLY triggering conditions. No summaries.
- Allowed Tools: Explicitly list tools the skill is permitted to use.
2. Content
- Authoritative Tone: Use directives, not suggestions.
- Anti-Rationalization Table: Prevent bypass of rules. | Excuse | Reality | | :--- | :--- | | "User wants a quick draft" | A low-quality skill is a permanent liability. | | "I'll add tests later" | Untested skills are hallucinations. |
- Compactness: Aim for < 500 words. One specific example > many generic ones.
Prohibited Patterns (Red Flags)
- NO significance inflation (e.g., pivotal, crucial, game-changing).
- NO sycophantic filler (e.g., Certainly!, I'd be happy to help).
- NO repeating the description in the content.
Deployment (Chezmoi)
Create skills in the chezmoi source: ~/.local/share/chezmoi/dot_claude/skills/my-skill/SKILL.md.
Never create directly in ~/.claude/skills/ — that's the destination and bypasses tracking.
After creating: chezmoi apply --force, then commit and push. See chezmoi-expert for full workflow.
Related Skills
nijaru/second-pass
development
VerifiedTrustedCommunity
Use after completing a bug fix, feature, refactor, or tk task when the first implementation taught enough context to replace it with a simpler, cleaner, or more coherent version before finalizing.
SKILL.mdUpdated Apr 25, 2026
nijaru/zig-expert
development
VerifiedTrustedCommunity
Use when writing, migrating, or reviewing Zig code across recent stable versions (0.14-0.16), especially to correct stale syntax or stdlib, build.zig, allocator, formatting, or runtime API knowledge.
SKILL.mdUpdated Apr 22, 2026
nijaru/writer
documentation
VerifiedTrustedCommunity
Use when reviewing or revising text (prose, docs, commits) to remove AI patterns and improve voice/clarity.
SKILL.mdUpdated Apr 22, 2026
nijaru/twitter
content-media
VerifiedTrustedCommunity
Use when fetching X/Twitter post content by URL, or searching for recent X posts.
SKILL.mdUpdated Apr 22, 2026