Files
msd-core/skills/gsd-audit-fix/SKILL.md
Tom Boucher da4a86d8c1 feat(#1596): ship GSD skills via .claude-plugin/plugin.json
Phase B-provide of epic #1258. Adds a build-generated skills/ dir +
a skills manifest field so plugin-installed GSD exposes gsd-core:<skill>
the native Claude Code way. Closes the gap where plugin-only installs
lacked the skill surface because bin/install.js never ran.

- scripts/gen-plugin-skills.cjs: build step converting commands/gsd/*.md
  to skills/gsd-<stem>/SKILL.md via convertClaudeCommandToClaudeSkill
- .claude-plugin/plugin.json: add "skills": "./skills/"
- package.json: add skills to files, gen:plugin-skills to build chain
- tests/issue-766-plugin-manifest.test.cjs: Section H conformance
  (manifest field + dir + frontmatter + count parity) + C2 skills symlink
- docs/adr/766-*.md: dated amendment adding skills surface row
- .changeset/rapid-bears-hum.md: type Added
- skills/: 69 generated gsd-<stem>/SKILL.md files (build-committed)

Closes #1596
2026-06-22 18:07:35 -04:00

901 B

name, description, argument-hint, allowed-tools
name description argument-hint allowed-tools
gsd-audit-fix Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit --source <audit-uat> [--severity <medium|high|all>] [--max N] [--dry-run]
Read
Write
Edit
Bash
Grep
Glob
Agent
AskUserQuestion
Run an audit, classify findings as auto-fixable vs manual-only, then autonomously fix auto-fixable issues with test verification and atomic commits.

Flags:

  • --max N — maximum findings to fix (default: 5)
  • --severity high|medium|all — minimum severity to process (default: medium)
  • --dry-run — classify findings without fixing (shows classification table)
  • --source <audit> — which audit to run (default: audit-uat)

<execution_context> @~/.claude/gsd-core/workflows/audit-fix.md </execution_context>

Execute end-to-end.