Fix Skills — Security skill for Claude Code
Fix skill files that failed the audit, based on findings from /audit-skills.
How to install Fix Skills
Installs to ~/.claude/commands/jennydove-self-improving-claude-fix-skills.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/jennydove/self-improving-claude/HEAD/.claude/commands/fix-skills.md -o ~/.claude/commands/jennydove-self-improving-claude-fix-skills.md Restart Claude Code, or start a new session, for it to be picked up.
What Fix Skills does
Fix skill files that failed the audit, based on findings from `/audit-skills`.
Usage
Run after `/audit-skills`. Specify which skills to fix, or fix all skills below threshold.
Process
**Identify skills to fix**
- Use the findings from the most recent
/audit-skillsrun - If called directly without a prior audit, run
/audit-skillsfirst
- Use the findings from the most recent
**Read `docs/standards-skills.md`** to understand what "good" looks like
**For each skill to fix:** a. Read the current skill file
Alternatives in Security
- Security Scan Report — Generated: 2026-04-10 20:48 UTC Skills scanned: 134 Total findings: 836 Critical: 32 High: 50 Safe skills: 100 18.1k ★
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
UX A11y
WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec. Produces findings grouped by WCAG
Review UX Audit
Full UX audit of a frontend codebase. Produces persona cards, journey maps, heuristic sweep, anti-pattern find
Gse Meta Audit Fix
Post-audit fix session for the GSE-One methodology repository. Consumes the canonical registry _LOCAL/audit/au
Forward Pass Nt
Fresh-eyes whole-app audit — walk the codebase start to finish hunting bugs, security issues, stray code, and
AWS Findings Triage Skill
Triage AWS Security Hub, GuardDuty, Inspector, and Config findings for the MacMountain account by real exploit
Tier 3 Code Refinement Report
Date: 2026-03-20 Status: ALL 54 FINDINGS IMPLEMENTED Scope: Full codebase (18 plugins, 888 files, ~266K lines)
Related Agents
Issue Manager
Manages the GitHub issue lifecycle for claude-code-vault. Creates well-structured issues from review/audit fin
Re Auditor
Verifies that a fixer's changes resolved errors from a prior audit. Use after a fix phase to check whether aud
Experiment Fixer
Use this agent to diagnose and fix failed AIChor experiments. Reads analysis reports and loop state, explores