codex-autoresearch
Run repeated code experiments toward a numeric target, keeping improvements in Git and rolling back failures. A control script handles measurement, commits, and experiment history, with commands for checking progress and generating reports.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
원문원문 설명 보기
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
실행 점수 미검증
설치 방법 보기이럴 때 유용합니다
- Optimize a repository toward a numeric target
- Resume experiments using recorded history
- Review experiment progress and results
- Export experiment history or generate an HTML report
포함된 파일(39)
- SKILL.md2.5 KB
- .github/workflows/ci.yml1.0 KB
- .gitignore63 B
- agents/openai.yaml301 B
- CITATION.cff527 B
- CONTRIBUTING.md3.0 KB
- docs/EXAMPLES.md4.6 KB
- docs/GUIDE.md7.9 KB
- docs/i18n/README_DE.md3.9 KB
- docs/i18n/README_ES.md3.8 KB
- docs/i18n/README_FR.md4.0 KB
- docs/i18n/README_JA.md4.1 KB
- docs/i18n/README_KO.md3.9 KB
- docs/i18n/README_PT.md3.7 KB
- docs/i18n/README_RU.md5.7 KB
- docs/i18n/README_ZH.md3.6 KB
- docs/INSTALL.md2.1 KB
- image/autoresearch-report.png116.0 KB
- image/banner.png2.3 MB
- LICENSE1.0 KB
- README.md9.1 KB
- references/background.md2.2 KB
- references/workflow.md7.3 KB
- scripts/autoresearch_core.py46.1 KB
- scripts/autoresearch_report.py22.6 KB
- scripts/autoresearch.py56.4 KB
- scripts/run_contributor_gate.sh608 B
- scripts/run_skill_e2e.sh11.5 KB
- scripts/validate_skill_structure.sh198 B
- tests/e2e-fixtures/counter_reduction/.gitignore31 B
- tests/e2e-fixtures/counter_reduction/scripts/score.py97 B
- tests/e2e-fixtures/counter_reduction/src/value.txt2 B
- tests/e2e-fixtures/interactive_unittest_fix/.gitignore50 B
- tests/e2e-fixtures/interactive_unittest_fix/prompt.txt104 B
- tests/e2e-fixtures/interactive_unittest_fix/scripts/score.py373 B
- tests/e2e-fixtures/interactive_unittest_fix/src/math_utils.py49 B
- tests/e2e-fixtures/interactive_unittest_fix/tests/test_math_utils.py325 B
- tests/test_autoresearch.py38.8 KB
- tests/test_structure.py2.0 KB
SKILL.md(원문)
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Codex Autoresearch
Improve a repository through repeated, reversible experiments:
hypothesize -> change -> measure -> learn -> keep or revert -> repeat
Codex chooses hypotheses and makes code changes. The control script owns measurement, commits, rollback, and the event history.
Respond To The Request
Resolve <control> to this skill's own scripts/autoresearch.py; do not assume it is installed in the target repository.
For a status or results request, run the corresponding command directly:
| Request | Command |
|---|---|
| Status | python3 <control> status --repo <repo> |
| History | python3 <control> history --repo <repo> |
| TSV export | python3 <control> history --repo <repo> --format tsv |
| HTML report | python3 <control> report --repo <repo> |
Report the requested result without starting or resuming experiments. Return the generated path for an HTML report.
Before starting or resuming an experiment, read the applicable workflow unless it is already in context:
- Workflow: starting, continuing, resuming, or changing an experiment.
- Background: launching or controlling a detached run.
Experiment Boundary
- One run owns one Git repository, one numeric metric, one confirmed target, and approved path scopes.
- For a new foreground run, initialize successfully before creating its Goal; the Goal identifies the returned run id. If initialization reports
complete, no Goal is needed. - Use
finishto finalize each coherent experiment. Do not manually commit, revert, or edit run artifacts during an active run. - Only a verified target can mean
complete; an iteration limit, error, or external blocker has its own status. - Validate state through the control script on entry or resume. Use recorded experiments rather than guessing from conversation.
- Surface command and state errors with their diagnostic paths. Never bypass validation, fabricate metrics, or reconstruct missing events.
Foreground continuation belongs to the official Codex Goal. Background continuation belongs to the detached controller. An already launched background worker follows its supplied experiment contract, without starting a new launch flow.
리뷰
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
댓글
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.