agentleFS
YulivuYulivu/debuffer-skills/skills/skills-codex-gemini-review/auto-review-loop/SKILL.md

auto-review-loop

Skill9 starsChanged 3 months agoMITView on GitHub

Prompt-only by default in the lightweight pack; Claude/Gemini reviewer transport is explicit opt-in. Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says \"auto review loop\", \"review until it passes\", or wants autonomous iterative improvement.

7 other projects use a version of this, 6 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

39 rules. 1 is common, 22 are distinctive, and 16 are very specific to this project.

  • 1

    Common

    Most of the 7 edited versions we read keep these.

  • 22

    Distinctive

    This author's own choices. Worth a look.

  • 16

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.

    line 14
  2. Distinctive:

    Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.

    line 16
  3. Very specific:

    Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the …

    line 18
  4. Distinctive:

    Keep heavy experiments AutoDL/HPC-gated and user-approved.

    line 20
  5. Common:

    If neither path exists: fresh start (normal case, identical to behavior before this feature existed)

    line 65
  6. Very specific:

    If it exists AND status is "completed": fresh start (previous loop finished normally)

    line 66
  7. Very specific:

    If it exists AND status is "in_progress" AND timestamp is older than 24 hours: fresh start (stale state from a killed/abandoned run — …

    line 67
  8. Very specific:

    If it exists AND status is "in_progress" AND timestamp is within 24 hours: resume

    line 68
  9. Very specific:

    Read the state file to recover round, thread_id, last_score, pending_experiments

    line 69
  10. Very specific:

    Read review-stage/AUTO_REVIEW.md to restore full context of prior rounds *(fall back to ./AUTO_REVIEW.md)*

    line 70
  11. Very specific:

    If pending_experiments is non-empty, check if they have completed (e.g., check screen sessions)

    line 71
  12. Distinctive:

    Read project narrative documents, memory files, and any prior review documents

    line 74
  13. Distinctive:

    Read recent experiment results (check output directories, logs)

    line 75
  14. Very specific:

    Create/update review-stage/AUTO_REVIEW.md with header and timestamp

    line 78
  15. Very specific:

    After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until …

    line 104
  16. Very specific:

    If this is round 2+, use mcp__gemini-review__review_reply_start with the saved completed threadId, then poll …

    line 106
  17. Distinctive:

    STOP CONDITION: If score >= 6 AND verdict ∈ {"ready", "almost"} (exact match — "not ready" does NOT qualify) → stop loop, document final …

    line 117
  18. Very specific:

    When HUMAN_CHECKPOINT = true, present the review results and wait for user input:

    line 123
  19. Distinctive:

    Wait for the user's response.

    line 146
  20. Very specific:

    After parsing the score, check if ~/.codex/feishu.json exists and mode is not "off":

    line 154
  21. Distinctive:

    If interactive mode and verdict is "almost": send as checkpoint, wait for user reply on whether to continue or stop

    line 156
  22. Distinctive:

    If config absent or mode off: skip entirely (no-op)

    line 157
  23. Distinctive:

    Code changes: Write/modify experiment scripts, model code, analysis scripts

    line 163
  24. Distinctive:

    Analysis: Run evaluation, collect results, update figures/tables

    line 167
  25. Distinctive:

    Documentation: Update project notes and review document

    line 168
  26. Distinctive:

    Prefer reframing/analysis over new experiments when both address the concern

    line 173
  27. Distinctive:

    Always implement metric additions (cheap, high impact)

    line 174
  28. Distinctive:

    If experiments were launched:

    line 178
  29. Distinctive:

    When loop ends (positive assessment or max rounds):

    line 220
  30. Very specific:

    Update review-stage/REVIEW_STATE.json with "status": "completed"

    line 222
  31. Very specific:

    Write final summary to review-stage/AUTO_REVIEW.md

    line 223
  32. Distinctive:

    Update project notes with conclusions

    line 224
  33. Distinctive:

    If stopped at max rounds without positive assessment:

    line 225
  34. Very specific:

    Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks.

    line 240
  35. Distinctive:

    Always ask the Gemini reviewer for strict, high-rigor feedback.

    line 242
  36. Distinctive:

    Do NOT hide weaknesses to game a positive score

    line 245
  37. Distinctive:

    If an experiment takes > 30 minutes, launch it and continue with other fixes while waiting

    line 247
  38. Distinctive:

    Document EVERYTHING — the review log should be self-contained

    line 248
  39. Distinctive:

    Update project notes after each round, not just at the end

    line 249

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Override for Codex users who want Gemini, not a second Codex agent, to act as the reviewer. Install this package after skills/skills-codex/*.

Customized Pack Defaults

This reviewer overlay is opt-in transport only. In the customized lightweight pack, default to prompt-only review unless the user explicitly asks to use this overlay reviewer backend:

  • Write the review prompt under review-prompts/ and ask the user to run it in a separate conversation with the relevant skills enabled.
  • Do not call Claude/Gemini reviewer MCP bridges, APIs, or follow-up status tools by default.
  • Use pasted review text as the external verdict, then write compact summaries such as REVIEW_SUMMARY.md, NEXT_ACTIONS.md, or the skill-specific log.
  • Keep heavy experiments AutoDL/HPC-gated and user-approved; local work stays at edits, tests, lint, dry-runs, and tiny smoke checks.

Auto Review Loop: Autonomous Research Improvement

Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.

Context: $ARGUMENTS

Constants

  • MAX_ROUNDS = 4
  • POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)
  • REVIEW_DOC: review-stage/AUTO_REVIEW.md (cumulative log) (fall back to ./AUTO_REVIEW.md for legacy projects)
  • OUTPUT_DIR = review-stage/ — Directory for review output files.
  • REVIEWER_MODEL = gemini-review — Gemini reviewer invoked through the local gemini-review MCP bridge. Set GEMINI_REVIEW_MODEL if you need a specific Gemini model override.
  • HUMAN_CHECKPOINT = false — When true, pause after each round's review (Phase B) and present the score + weaknesses to the user. Wait for user input before proceeding to Phase C. The user can: approve the suggested fixes, provide custom modification instructions, skip specific fixes, or stop the loop early. When false (default), the loop runs fully autonomously.

💡 Override: /auto-review-loop "topic" — human checkpoint: true

State Persistence (Compact Recovery)

Long-running loops may hit the context window limit, triggering automatic compaction. To survive this, persist state to review-stage/REVIEW_STATE.json after each round:

{
  "round": 2,
  "thread_id": "019cd392-...",
  "status": "in_progress",
  "last_score": 5.0,
  "last_verdict": "not ready",
  "pending_experiments": ["screen_name_1"],
  "timestamp": "2026-03-13T21:00:00"
}

Write this file at the end of every Phase E (after documenting the round). Overwrite each time — only the latest state matters.

On completion (positive assessment or max rounds), set "status": "completed" so future invocations don't accidentally resume a finished loop.

Workflow

Initialization

  1. Check for review-stage/REVIEW_STATE.json (fall back to ./REVIEW_STATE.json if not found — legacy path):
    • If neither path exists: fresh start (normal case, identical to behavior before this feature existed)
    • If it exists AND status is "completed": fresh start (previous loop finished normally)
    • If it exists AND status is "in_progress" AND timestamp is older than 24 hours: fresh start (stale state from a killed/abandoned run — delete the file and start over)
    • If it exists AND status is "in_progress" AND timestamp is within 24 hours: resume
      • Read the state file to recover round, thread_id, last_score, pending_experiments
      • Read review-stage/AUTO_REVIEW.md to restore full context of prior rounds (fall back to ./AUTO_REVIEW.md)
      • If pending_experiments is non-empty, check if they have completed (e.g., check screen sessions)
      • Resume from the next round (round = saved round + 1)
      • Log: "Recovered from context compaction. Resuming at Round N."
  2. Read project narrative documents, memory files, and any prior review documents
  3. Read recent experiment results (check output directories, logs)
  4. Identify current weaknesses and open TODOs from prior reviews
  5. Initialize round counter = 1 (unless recovered from state file)
  6. Create/update review-stage/AUTO_REVIEW.md with header and timestamp

Loop (repeat up to MAX_ROUNDS)

Phase A: Review

Send comprehensive context to the external reviewer:

mcp__gemini-review__review_start:
  prompt: |
    [Round N/MAX_ROUNDS of autonomous review loop]

    [Full research context: claims, methods, results, known weaknesses]
    [Changes since last round, if any]

    Please act as a senior ML reviewer (NeurIPS/ICML level).

    1. Score this work 1-10 for a top venue
    2. List remaining critical weaknesses (ranked by severity)
    3. For each weakness, specify the MINIMUM fix (experiment, analysis, or reframing)
    4. State clearly: is this READY for submission? Yes/No/Almost

    Be brutally honest. If the work is ready, say so clearly.

After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.

If this is round 2+, use mcp__gemini-review__review_reply_start with the saved completed threadId, then poll mcp__gemini-review__review_status with the returned jobId until done=true to maintain continuity.

Phase B: Parse Assessment

CRITICAL: Save the FULL raw response from the external reviewer verbatim (store in a variable for Phase E). Do NOT discard or summarize — the raw text is the primary record.

Then extract structured fields:

  • Score (numeric 1-10)
  • Verdict ("ready" / "almost" / "not ready")
  • Action items (ranked list of fixes)

STOP CONDITION: If score >= 6 AND verdict ∈ {"ready", "almost"} (exact match — "not ready" does NOT qualify) → stop loop, document final state.

Human Checkpoint (if enabled)

Skip this step entirely if HUMAN_CHECKPOINT = false.

When HUMAN_CHECKPOINT = true, present the review results and wait for user input:

📋 Round N/MAX_ROUNDS review complete.

Score: X/10 — [verdict]
Top weaknesses:
1. [weakness 1]
2. [weakness 2]
3. [weakness 3]

Suggested fixes:
1. [fix 1]
2. [fix 2]
3. [fix 3]

Options:
- Reply "go" or "continue" → implement all suggested fixes
- Reply with custom instructions → implement your modifications instead
- Reply "skip 2" → skip fix #2, implement the rest
- Reply "stop" → end the loop, document current state

Wait for the user's response. Parse their input:

  • Approval ("go", "continue", "ok", "proceed"): proceed to Phase C with all suggested fixes
  • Custom instructions (any other text): treat as additional/replacement guidance for Phase C. Merge with reviewer suggestions where appropriate
  • Skip specific fixes ("skip 1,3"): remove those fixes from the action list
  • Stop ("stop", "enough", "done"): terminate the loop, jump to Termination

Feishu Notification (if configured)

After parsing the score, check if ~/.codex/feishu.json exists and mode is not "off":

  • Send a review_scored notification: "Round N: X/10 — [verdict]" with top 3 weaknesses
  • If interactive mode and verdict is "almost": send as checkpoint, wait for user reply on whether to continue or stop
  • If config absent or mode off: skip entirely (no-op)

Phase C: Implement Fixes (if not stopping)

For each action item (highest priority first):

  1. Code changes: Write/modify experiment scripts, model code, analysis scripts
  2. Run experiments: for heavy compute, prepare an AutoDL/HPC handoff or invoke /experiment-bridge; do not deploy via SSH/screen/tmux unless the user explicitly approves that legacy path.
  3. Analysis: Run evaluation, collect results, update figures/tables
  4. Documentation: Update project notes and review document

Prioritization rules:

  • Skip fixes requiring excessive compute (flag for manual follow-up)
  • Skip fixes requiring external data/models not available
  • Prefer reframing/analysis over new experiments when both address the concern
  • Always implement metric additions (cheap, high impact)

Phase D: Wait for Results

If experiments were launched:

  • Monitor remote sessions for completion
  • Collect results from output files and logs

Phase E: Document Round

Append to review-stage/AUTO_REVIEW.md:

## Round N (timestamp)

### Assessment (Summary)
- Score: X/10
- Verdict: [ready/almost/not ready]
- Key criticisms: [bullet list]

### Reviewer Raw Response

<details>
<summary>Click to expand full reviewer response</summary>

[Paste the COMPLETE raw response from the external reviewer here — verbatim, unedited.
This is the authoritative record. Do NOT truncate or paraphrase.]

</details>

### Actions Taken
- [what was implemented/changed]

### Results
- [experiment outcomes, if any]

### Status
- [continuing to round N+1 / stopping]

Write review-stage/REVIEW_STATE.json with current round, agent id, score, verdict, and any pending experiments.

Increment round counter → back to Phase A.

Termination

When loop ends (positive assessment or max rounds):

  1. Update review-stage/REVIEW_STATE.json with "status": "completed"
  2. Write final summary to review-stage/AUTO_REVIEW.md
  3. Update project notes with conclusions
  4. If stopped at max rounds without positive assessment:
    • List remaining blockers
    • Estimate effort needed for each
    • Suggest whether to continue manually or pivot
  5. Feishu notification (if configured): Send pipeline_done with final score progression table

Output Protocols

Follow these shared protocols for all output files:

  • Output Versioning Protocol — write timestamped file first, then copy to fixed name
  • Output Manifest Protocol — log every output to docs/project/OUTPUT_MANIFEST.md
  • Output Language Protocol — respect the project's language setting

Key Rules

  • Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently.
  • Always ask the Gemini reviewer for strict, high-rigor feedback.
  • Save the completed threadId from the first mcp__gemini-review__review_status result, then use mcp__gemini-review__review_reply_start plus mcp__gemini-review__review_status for subsequent rounds
  • Be honest — include negative results and failed experiments
  • Do NOT hide weaknesses to game a positive score
  • Implement fixes BEFORE re-reviewing (don't just promise to fix)
  • If an experiment takes > 30 minutes, launch it and continue with other fixes while waiting
  • Document EVERYTHING — the review log should be self-contained
  • Update project notes after each round, not just at the end

Prompt Template for Round 2+

mcp__gemini-review__review_reply_start:
  threadId: [saved from round 1]
  prompt: |
    [Round N update]

    Since your last review, we have:
    1. [Action 1]: [result]
    2. [Action 2]: [result]
    3. [Action 3]: [result]

    Updated results table:
    [paste metrics]

    Please re-score and re-assess. Are the remaining concerns addressed?
    Same format: Score, Verdict, Remaining Weaknesses, Minimum Fixes.

After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.