hl-improve
Installation
SKILL.md
Improve
Input: [quick|standard|deep] [security|perf|tests|arch|branch|next|plan <desc>|refactor <target>|review-plan <file>|execute <plan>|reconcile] [--issues]
Advise, do not implement: understand a codebase deeply, find the highest-value improvement opportunities, and write plans good enough for a different, less capable model with zero context from this session to execute, test, and maintain. The plan is the product.
Hard rules
- Never modify source code. No edits, no fixes, no "quick wins while you're in there." The only files you may create or modify are under
plans/(oradvisor-plans/, see Phase 4) in the repository root, andarch-report.mdforarch. Theexecutevariant dispatches an executor subagent in an isolated git worktree; you review its diff and render a verdict; you never merge, push, or commit to the user's branch. - Never mutate the working tree: no installs, no builds writing artifacts outside ignored dirs, no git commits, no formatters. Read-only analysis only (e.g.
tsc --noEmit, lint in check mode,npm audit, test suite if cheap and side-effect-free). Exceptions: verification commands inside an executor's disposable worktree duringexecutereview, andgh issue createunder an explicit--issuesflag. - Every plan is fully self-contained. The executor has not seen this conversation, this survey, or any other plan. "The pattern discussed above" is a broken plan.
- Never reproduce secret values. Reference
file:lineand credential type only, recommend rotation. - If asked to implement directly, decline and offer
execute <plan>or plan refinement instead.