Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Touch only what you must. Clean up only your own mess.
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
The test: Every changed line should trace directly to the user's request.
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
- User instructions override this guide; this guide overrides generic defaults.
- Save generated markdown under
doc/; save plans underdoc/plans/and archive finished plans underdoc/plans/archive/. - Prefix generated markdown filenames with
YYYYMMDD; reports must be Markdown and include exact reproducibility commands. - Assume no
sudo; keep installs user-local and reproducible. Prefermamba, standalone binaries,conda,uv, thenpip. - Run checks in the same environment as the user's workflow. If the authoritative environment is unclear, ask.
- Python targets 3.11+. Use
ruffandpyrightfrompyproject.toml. - Keep reusable logic in importable modules under
src/; keep runnable scripts thin and under domain-specificsrc/subfolders. - Prefer clear typed Python:
pathlib, f-strings, explicit names, no wildcard imports, guarded entry points, and Google-style docstrings for public APIs. - Use
logging.getLogger(__name__)for production code and include stable identifiers when useful.
- Run the smallest meaningful verification for the change.
- During Python iteration, run
ruff check <changed_files> --fixandruff format <changed_files>. - Add
pytesttests for reusable/shared logic; one-off scripts may use lightweight validation. - Run full
ruff,pyright, andpython -m pytestbefore handoff for shared/core logic, multi-file changes, or behavior changes. - Report type-check pass/fail when
pyrightis relevant.
- For iEnigma usage, follow
/home/jhuang/project/NER_label_extraction/doc/iEnigma_v1.0_readme.md; if inaccessible, ask for constraints. - Never commit secrets. Keep large generated artifacts in designated output folders such as
result/, do not commit caches/temp/env folders, and update.gitignorefor new artifact patterns. - For commits, PRs, pushes, merges, and GitHub work, use the installed git workflow skills and ask for approval before mutating remote or commit history.