autoresearch-finalize
- Repo stars 3
- Author updated Live
- Author repo FFT_nano
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @0-CYBERDYNE-SYSTEMS-0 · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: autoresearch-finalize
description: Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize au…
category: engineering
runtime: no special runtime
---
# autoresearch-finalize output preview
## PART A: Task fit
- Use case: Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review"..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Step 1 — Analyze and Propose Groups / Step 2 — Write groups.json and Run / Step 3 — Report” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".”.
- **02** When the source has headings, the agent prioritizes “Step 1 — Analyze and Propose Groups / Step 2 — Write groups.json and Run / Step 3 — Report” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/tmp`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Step 1 — Analyze and Propose Groups / Step 2 — Write groups.json and Run / Step 3 — Report”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: autoresearch-finalize
description: Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize au…
category: engineering
source: 0-CYBERDYNE-SYSTEMS-0/FFT_nano
---
# autoresearch-finalize
## When to use
- Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Step 1 — Analyze and Propose Groups / Step 2 — Write groups.json and Run / Step 3 — Report” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "autoresearch-finalize" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Step 1 — Analyze and Propose Groups / Step 2 — Write groups.json and Run / Step 3 — Report
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Finalize Autoresearch
Turn a noisy autoresearch branch into clean, independent branches — one per logical change, each starting from the merge-base.
Step 1 — Analyze and Propose Groups
- Read
autoresearch.jsonl. Filter to kept experiments only. - Read
autoresearch.mdfor context. - Expand all short commit hashes to full hashes:
git rev-parse <short_hash> - Get the merge-base:
git merge-base HEAD main - For each kept commit, get the diff stat (use
$BASE..<commit>for the first,<prev_kept>..<commit>for subsequent). - Group kept commits into logical changesets:
- Preserve application order. Group N comes before Group N+1.
- No two groups may touch the same file. Each branch is applied to merge-base independently — overlapping files would conflict. If two groups touch the same file, merge them into one group.
- Watch for cross-file dependencies. Each branch is independent, so if group 1 adds an API in
api.jsand group 2 calls it inparser.js, group 2's branch won't work in isolation. When proposing groups, flag dependencies: "group 2 depends on group 1 — review together." If the dependency is tight, merge the groups. - Keep each group small and focused. One idea, one theme per group.
- Don't hardcode a count. Could be 2, could be 15.
Present the proposed grouping to the user:
Proposed branches (each from merge-base, independent):
1. **Switch test runner to forks pool** (commits abc1234, def5678)
Files: vitest.config.ts, package.json
Metric: 42.3s → 38.1s (-9.9%)
2. **Tune worker count and timeouts** (commits ghi9012, jkl3456)
Files: test/setup.ts
Metric: 38.1s → 31.7s (-16.8%)
Wait for approval before proceeding.
Step 2 — Write groups.json and Run
Write groups.json:
{
"base": "<full merge-base hash>",
"trunk": "main",
"final_tree": "<full hash of current HEAD>",
"goal": "short-slug",
"groups": [
{
"title": "Switch to forks pool",
"body": "Why + what changed.\n\nExperiments: #3, #5\nMetric: total_time 42.3s → 38.1s (-9.9%)",
"last_commit": "<full hash of last kept commit in this group>",
"slug": "forks-pool"
}
]
}
Key rules:
last_commitmust be a full hash. Expand from jsonl short hashes withgit rev-parse.- No two groups may share a file. The script validates this and fails if violated.
Then run:
bash <SKILL_DIR>/finalize.sh /tmp/groups.json
The script creates one branch per group from the merge-base, verifies the union matches the original branch, and prints a summary with all branches, cleanup commands, and any ideas from autoresearch.ideas.md.
On creation failure: rolls back (deletes branches, restores original branch, pops stash). On verification failure: exits non-zero but leaves branches intact for inspection.
Step 3 — Report
After the script finishes, report to the user:
- Branches created and what each contains
- Overall metric improvement (baseline → best)
- Show the cleanup commands from the script's summary output
Edge Cases
- Only 1 kept experiment: One branch is fine — don't force splits.
- Overlapping files between groups: The script fails with an error naming the file. Merge the overlapping groups and retry.
- Non-experiment commits on the branch: Skip them — only process kept experiments from the jsonl.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review