spartanlabsxyz/simmer-sdk/autoresearch-finalize

Claude Code and agent skill by spartanlabsxyz/simmer-sdk

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".

Install

npx vskill@latest install spartanlabsxyz/simmer-sdk/autoresearch-finalize

SKILL.md

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

  1. Read autoresearch.jsonl. Filter to kept experiments only.
  2. Read autoresearch.md for context.
  3. Expand all short commit hashes to full hashes: git rev-parse <short_hash>
  4. Get the merge-base: git merge-base HEAD main
  5. For each kept commit, get the diff stat.
  6. 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. If group 1 adds an API in api.js and group 2 calls it in parser.js, group 2's branch won't work in isolation. Flag dependencies.
  • Keep each group small and focused. One idea, one theme per group.

Present the proposed grouping:

Proposed branches (each from merge-base, independent):
1. **<description>** (commits abc1234, def5678)
Files: file1.py, file2.py
Metric: 42.3 → 38.1 (-9.9%)
2. **<description>** (commits ghi9012)
Files: config.json
Metric: 38.1 → 31.7 (-16.8%)

Wait for approval before proceeding.

Step 2 — Create branches

For each approved group:

bash
BASE=$(git merge-base HEAD main)
git checkout -b autoresearch/final/<group-name> $BASE
git cherry-pick <commit1> <commit2> ...

If cherry-pick conflicts, resolve by taking the experiment's version (the whole point is to preserve the improvement).

Step 3 — Verify each branch

For each branch:

  1. Run the skill command to verify it still works
  2. Check that the metric improvement holds
  3. If it doesn't, flag it — the improvement may have depended on another group's changes

Step 4 — Report

Finalized branches:
1. autoresearch/final/<name> — <metric improvement>, ready to merge
2. autoresearch/final/<name> — <metric improvement>, depends on branch 1

The user can now review and merge each branch independently (or together if there are dependencies).

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/spartanlabsxyz/simmer-sdk/autoresearch-finalize/badge)](https://verified-skill.com/skills/spartanlabsxyz/simmer-sdk/autoresearch-finalize)

Something wrong with this skill or its page? Tell us.