Menu
Close the pipeline cycle: regenerate the living spec from current tests, summarize the carry-over cache files, regenerate source docstrings then strip all .py so the next cycle starts compact.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Compile the contract set in your head — simulate how the real application would run from the specs, and disprove (or confirm) it works before any source .py is written.
Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.
Funnel level 3 — identify building-block names and rough boundaries only, and run gap analysis.
Funnel level 1 — establish the big picture with seven broad questions, applying CIT, Laddering, and CI Perspective throughout.
Squash-merge the feature commits into dev, regenerate docstrings, and verify the whole suite plus whole-suite stubtest are clean.
Publish the delivered batch as release notes, a PR to main, or a tagged release.
| name | refresh-cycle |
| description | Close the pipeline cycle: regenerate the living spec from current tests, summarize the carry-over cache files, regenerate source docstrings then strip all .py so the next cycle starts compact. |
docs/state.md from .templates/docs/state.md.template, substituting <name>, <version> (from pyproject.toml), <YYYY-MM-DD>, and <session_id>. Derive every field from the truth — the current test .pyi/.py, pending marks (uv run pytest --collect-only -m pending -q), cassettes, migrations, and docs/glossary.md — never from prose or memory. The contract-index intent column is read from each test body; the composition and data-flow lines are read from the e2e path the tests express. This file is a derived view; when prose and a test disagree, the test wins. Never hand-edit it..cache/<session_id>/interview-notes.md, .cache/<session_id>/external-contracts.md, .cache/<session_id>/data-model.md, and .cache/<session_id>/journal.md as a ~1000-word summary of this cycle — the decisions made, the contracts built, the gaps closed, the escalations resolved. Preserve the headers each template carries so the next pass appends in the right place; replace the body with the distilled record. Transient per-pass files (build-target.md, probe-target.md, probe-research.md) are NOT summarized — they are regenerated by the next pass.<package>/**/*.py — never a mechanical restatement of the signature; the why of an architectural decision lives in an ADR, not a docstring. Source only, never tests. Then run task lint-merge (ruff check --extend-select SIM,RUF . && ruff format .). Commit on dev as docs: regenerate docstrings + format..py docstrings. Run uv run python scripts/strip_docstrings.py $(find <package> tests -name '*.py' -type f) (many files, in place, line-range only; the glob skips .pyi). Commit on dev as chore: strip docstrings for next dev cycle.spec-regenerated=true, cache-summarized=true, docstrings-regenerated=true, docstrings-stripped=true.