القائمة
Scan editable code for tech debt, anti-patterns, and improvement opportunities across 5 categories. Reports findings; the code-modernizer agent applies fixes.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Write comprehensive tests using project conventions: AAA pattern, edge-case checklist, httpx.MockTransport, conftest fixtures, parametrize where it reads better than copy-paste.
Audit Prefab UI card builders (`build_*_ui` in `katana_mcp_server/src/katana_mcp/tools/prefab_ui.py`) for user-centric content: real names over IDs, no redundant text dumps, named helpers over ad-hoc rendering. Reports findings; does not modify code. Use when reviewing card UX or after touching `prefab_ui.py`.
Groom the Rolling Backlog (project #5) by reading current state and proposing diffs — not re-deriving the queue from scratch. Surfaces drift between issue state and project status, missing classification, and stale priorities. Asks per-category confirmation before mutating the board.
Quick pre-flight validation of staged and unstaged changes before committing. Lighter than the verifier/code-reviewer agents — focuses on catching common mistakes in the current changeset.
Open a PR for the current feature branch — self-review the diff, organize commits, push, create the PR, wait for CI and review, then address feedback. Use when implementation is complete and ready for review.
Address PR review comments — fetch all unresolved comments, fix the issues, validate with `uv run poe check`, commit, push, and reply to each comment on GitHub. Use when asked to handle PR review feedback.
| name | techdebt |
| description | Scan editable code for tech debt, anti-patterns, and improvement opportunities across 5 categories. Reports findings; the code-modernizer agent applies fixes. |
| allowed-tools | ["Read","Grep","Glob","Bash(uv run poe quick-check)"] |
Surface tech debt and anti-patterns in editable code; do not fix.
api/**/*.py, models/**/*.py, client.py.grep misses dynamic dispatch and re-exports; use LSP findReferences before declaring something dead.uv run poe quick-check
Categories:
LSP findReferences before flagging.katana_public_api_client/docs/guide.md "Response Handling" section and CLAUDE.md "Known Pitfalls" (UNSET misuse, manual status checks, retry wrapping, hasattr on attrs models, raw list mocks).except Exception, missing type annotations on public functions, parameter explosions, name shadowing, circular imports.@pytest.mark.asyncio, fixtures that should be scope="session".**File**: path/to/file.py:42
**Category**: outdated pattern
**Current**: if not isinstance(value, type(UNSET)): use(value)
**Fix**: use(unwrap_unset(value, default))
**Priority**: HIGH | MEDIUM | LOW
## Tech Debt Report
### Summary
- Dead code: N
- Outdated patterns: N
- Code duplication: N
- Code smells: N
- Missing best practices: N
### HIGH | MEDIUM | LOW
[grouped findings]
### Improvements to CLAUDE.md
[new anti-patterns discovered]
This skill is report-only. To apply fixes, run harness-kit:simplify for generic
cleanup, then spawn the code-modernizer agent for Katana-specific rewrites.
git grep hits — still run LSP findReferences. Pyright walks the real type graph including from m import * and aliased re-exports.code-modernizer agent — actively rewrites the patterns this skill flagsharness-kit:simplify skill — generic cleanup (run before code-modernizer)/review skill — design review (broader than tech debt)