skills/cmd-sculpt-code/SKILL.md
Reshape code for readability, naming, structure, TODOs, and reduced surface area across any language
npx skillsauth add olshansk/agent-skills cmd-sculpt-codeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Reshape code quality across eight dimensions. Scope to branch changes by default (git diff main...HEAD), or accept explicit file/directory targets.
Philosophy: Write code for the next reader (human or agent). Minimize cognitive load. Prefer boring, obvious code over clever code. Every change must preserve business logic unless explicitly told otherwise.
git diff main...HEAD --name-onlygit diff --cached --name-onlyreferences/python.md for language-specific guidance.file_path:line_number.data, temp, result, x, val, info without contextrepo/repository, config/configuration)if not items: over if len(items) == 0, but never at the cost of clarityis_valid, has_permission, should_retrymap/filter in JS where idiomatic)Apply the project's TODO prefix standards:
TODO: — general future workTODO_IMPROVE: — code quality improvementsTODO_OPTIMIZE: — performance improvementsTODO_TECHDEBT: — technical debt to address laterTODO_REVISIT: — design decisions that may need revisitingTODO_IDEA: — potential features to considerTODO_IN_THIS_PR: — must complete before mergeTODO_REMOVE_LATER: — temporary code with removal conditionFIXME: — known bugsHACK: — temporary workaroundsEach TODO must include:
Add missing TODOs for: known shortcuts, deferred work, temporary workarounds, and obvious improvement opportunities spotted during review. Remove stale or resolved TODOs.
# increment counter above counter += 1)IMPORTANT, NOTE, CRITICAL, DEV_NOTE markers — clean up the text, not the tagFor each file changed, show:
### file_path
**Changes made:**
- [dimension] description of change (line X)
- [dimension] description of change (line Y)
End with a summary: files touched, lines removed, TODOs added/removed, helpers extracted.
testing
Ask the agent whether it finished everything or has more to do — a lightweight completeness gate for the end of any task
development
Audit personal skills for redundancy, verbosity, weak triggers, and overlap. Runs a Claude→Codex review loop, presents per-item approval checkboxes, then applies approved edits and updates README and agent metadata. Use when asked to "review my skills", "audit my skills", "revisit my skills", or "clean up my skills". Accepts an optional skill name to scope the review to a single skill.
development
Set up or extend golden/snapshot tests for a project. Covers fixture design, Makefile targets, snapshot storage, diff workflow, and update protocol.
development
Proofread posts before publishing for spelling, grammar, repetition, logic, weak arguments, broken links, and optionally reformat for skimmability or shape the writing vibe toward a known author's style