agentleFS
ianshankianshank/Agents/.agents/skills/merge-gate-auditor/SKILL.md

merge-gate-auditor

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Sample unlabelled PR records from merge-gate-data, prepare structured Audit Verdict Cards, and stage human verdicts. Use whenever sampling unlabelled audit candidates, conducting merge-gate audit triage, or reviewing pull-request outcomes against the calibrated merge gate.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Zero Synthetic Audits: Never synthesize or fabricate HUMAN_AUDIT records.

    line 12
  2. Very specific:

    Plumbing Store Sync: All reads and writes to merge-gate-data operate through agent_core.store_sync plumbing (mktree, commit-tree), never …

    line 14
  3. Distinctive:

    Verify if any post-merge revert or fix-up was committed within the 7-day observation window.

    line 44
  4. Distinctive:

    Check behavioral regression test status:

    line 45
  5. Distinctive:

    After human maintainer executes verdicts:

    line 62
  6. Distinctive:

    No synthetic records are generated.

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Merge Gate Auditor — Human Audit Triage Skill

The merge-gate-auditor automates the sampling of unlabelled pull request records from origin/merge-gate-data, formats detailed diff and behavioral contexts, and constructs Audit Verdict Cards for review by the human merge owner (@ianshank).

Core Invariants

  1. Zero Synthetic Audits: Never synthesize or fabricate HUMAN_AUDIT records. The calibrated auto-merge gate requires genuine human audit evidence ($N \ge 200, ECE \le 0.05, AUROC \ge 0.65$).
  2. Cold-Start Floor: The audit sampler enforces AuditConfig.per_domain_floor (default 30, workflow override 3) before a domain can exit cold-start.
  3. Plumbing Store Sync: All reads and writes to merge-gate-data operate through agent_core.store_sync plumbing (mktree, commit-tree), never touching working trees or triggering CI ([skip ci]).

Procedure

1. Pull Latest Store Records

python -m agent_core.store_sync pull --repo-dir . --store data/merge_outcomes.jsonl

2. Inspect Soak Progress

python -m agent_core.store_sync stats --store data/merge_outcomes.jsonl --soak-progress --audit-floor 3

Verify:

  • Total records in store ($N$)
  • Number of human audits accumulated per domain
  • Cold-start status per domain
  • Shortfall vs soak target

3. Sample Unlabelled Candidates

python -m agent_core.audit_sampler --store data/merge_outcomes.jsonl select --per-domain-floor 3 --with-propensity

4. Generate Audit Verdict Card

For each sampled candidate change ID:

  1. Inspect git log and diff of the change:
    git show <change_id>
  2. Verify if any post-merge revert or fix-up was committed within the 7-day observation window.
  3. Check behavioral regression test status:
    python -m pytest behavioral-regression/tests/
  4. Render the Audit Verdict Card:
    ### Audit Verdict Card: `<change_id>`
    - **Domain**: `<domain>`
    - **Merged At**: `<timestamp>`
    - **Merge Gate Confidence**: `<raw_confidence>`
    - **Revert / Fixup Observed**: None / Commit `<sha>`
    - **Maintainer Actions**:
      - Confirm Correct: `python scripts/record_audit_verdict.py --store data/merge_outcomes.jsonl --change-id <change_id> --actor @ianshank --correct`
      - Confirm Regressed: `python scripts/record_audit_verdict.py --store data/merge_outcomes.jsonl --change-id <change_id> --actor @ianshank --incorrect`

5. Sync Human Verdicts to Remote Store

After human maintainer executes verdicts:

python -m agent_core.store_sync push --repo-dir . --store data/merge_outcomes.jsonl --actor @ianshank

Definition of Done

  • Unlabelled candidates are sampled strictly according to the domain cold-start floor.
  • Verdict cards provide complete commit, diff, and revert context.
  • No synthetic records are generated.
  • Updated store records pass agent_core.store_sync stats validation.

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.