agentleFS
MacroMan5MacroMan5/autotrain-yolo/.claude/skills/review-annotations/SKILL.md

review-annotations

Skill8 starsChanged 8 months agoMITView on GitHub

AI-assisted annotation review — uses YOLO inference + Claude vision to auto-approve, correct, or flag images for human review in CVAT.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read yolo-project.yaml for classes, model path.

    line 15
  2. Very specific:

    Create: review_output/approved/, needs_review/, rejected/

    line 18
  3. Very specific:

    Run YOLO at low confidence: python scripts/multi_pass_annotate.py --image <path> --model <model> --conf 0.15

    line 22
  4. Very specific:

    Write review_output/review_report.md with counts, corrections, common issues.

    line 28
  5. Distinctive:

    Never auto-approve if uncertain

    line 32
  6. Distinctive:

    When uncertain → needs_review

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Review Annotations

Multi-pass annotation review: YOLO precision + Claude intelligence.

STATUS: EXPERIMENTAL

Workflow

1. Setup

Read yolo-project.yaml for classes, model path. Get review folder from user.

2. Prepare Output

Create: review_output/approved/, needs_review/, rejected/

3. Process Images (batches of 5-10)

For each image:

  1. Run YOLO at low confidence: python scripts/multi_pass_annotate.py --image <path> --model <model> --conf 0.15
  2. Draw existing annotations: python scripts/draw_annotations.py
  3. Claude reads annotated image (multimodal)
  4. Judge: AUTO-APPROVE / AUTO-CORRECT / NEEDS HUMAN / REJECT

4. Generate Report

Write review_output/review_report.md with counts, corrections, common issues.

Guardrails

  • Batch size 5-10 to avoid context overflow
  • Never auto-approve if uncertain
  • When uncertain → needs_review
  • Generate CVAT export command for needs_review

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.