experiment-git-ops
Git commit and revert patterns for autoresearch experiments. Use when keeping or discarding experiment results to manage git state correctly.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Git commit and revert patterns for autoresearch experiments. Use when keeping or discarding experiment results to manage git state correctly.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when reviewing a completed implementation holistically - a finished branch, a completed plan step, or a diff before PR. Reviews every changed line against the implementation plan (if one exists) and high engineering standards across seven dimensions, verifies tests by deliberately breaking crucial code, and emits severity-classified findings with a PASS/FAIL verdict.
Use when performing a holistic code review of an implementation - routes to codex:rescue or falls back to a direct subagent, both running the house-style:holistic-review skill
ALWAYS use before any implementation work, review, or planning: designing, writing, editing, refactoring, debugging, reviewing, or generating source code, tests, scripts, config-as-code, or behavior-affecting files. This is a baseline engineering skill and should be invoked even when a more specific language, framework, testing, or database skill also applies.
Use when asked to write, draft, file, or open a GitHub issue - mandates exploring the relevant code to understand the whole problem space, reasoning any proposed solution, and structuring the issue with summary, what/why, references, nuances, open questions, and acceptance criteria. Adds professionalism and no-sensitive-info discipline for public repos.
Use when creating, editing, triaging, or cleaning up GitHub issues - a mechanical pass that verifies the title is accurate and current, labels/assignees/milestone are correct, and the body is valid, well-formed markdown, all via the gh CLI. Does not judge content quality.
Use when running Python, installing Python packages, creating virtualenvs, or executing Python CLI tools - mandates uv/uvx over direct python/pip/pipx/venv calls when uv is installed, and gives the drop-in command mappings
| name | experiment-git-ops |
| description | Git commit and revert patterns for autoresearch experiments. Use when keeping or discarding experiment results to manage git state correctly. |
| user-invocable | false |
Manages git state during the autoresearch loop. Successful experiments are committed with structured metadata. Failed experiments are reverted while preserving autoresearch state files.
These files are never reverted, regardless of experiment outcome:
autoresearch.jsonlautoresearch.mdautoresearch.ideas.mdautoresearch.shautoresearch.checks.shkeep — CommitWhen an experiment improves the primary metric:
git add -Agit diff --cached --quiet (exit code 1 = changes exist)<description>
Result: {"status":"keep","<metric_name>":<value>,<secondary_metrics>}
The Result: trailer is a JSON object containing:
status: always "keep"Example commit message:
Inline hot loop in render phase
Result: {"status":"keep","total_µs":14600,"compile_µs":4100,"render_µs":9500}
discard, crash, or checks_failed — RevertWhen an experiment fails or doesn't improve:
git add autoresearch.jsonl autoresearch.md autoresearch.ideas.md autoresearch.sh autoresearch.checks.sh 2>/dev/null || true
git stash push -- autoresearch.jsonl autoresearch.md autoresearch.ideas.md autoresearch.sh autoresearch.checks.sh 2>/dev/null || true
git checkout -- .
git clean -fd 2>/dev/null
git stash pop 2>/dev/null || true
This restores the working tree to the last committed state while keeping all autoresearch state files intact.
autoresearch/<goal>-<YYYY-MM-DD> from current HEAD.Discarded and crashed experiments are completely erased from the working tree. The only surviving record is the description and ASI in autoresearch.jsonl. This is why heavy annotation of failures is critical — without it, future iterations will re-discover the same dead ends.