agentleFS
Sign inStart free
MCamnerMCamner/mq-image-analyze/skills/json-contract-maintainer/SKILL.md

json-contract-maintainer

Skill1 starsChanged 22 days agoMITView on GitHub

Use when changing mq-image-analyze JSON output schemas, analysis result fields, compare output, UI analysis output, exhaustive mode, or stable integration contracts.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for any machine-readable output change.

    line 8
  2. Distinctive:

    Update tests for expected fields and modes.

    line 53
  3. Distinctive:

    Update MCP docs if tool responses change.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

JSON Contract Maintainer

Use this skill for any machine-readable output change.

Evals

Should trigger

  • "add a field to the analyze JSON output"
  • "change the compare output schema"
  • "stabilize the UI analysis contract"
  • "version the exhaustive-mode output"

Should not trigger

  • "change a CLI flag" → use cli-maintainer
  • "change MCP tool schemas" → use mcp-tools-maintainer
  • "update schema docs only" → use docs-maintainer

Core Files

  • docs/json-schema.md
  • docs/mcp-tools.md
  • examples/sample-analysis.json
  • examples/generated/*.json
  • mq_image_analyze/cli/analyze.py
  • mq_image_analyze/cli/compare.py
  • mq_image_analyze/cli/analyze_ui.py
  • mq_image_analyze/reasoning/comparison/comparator.py
  • mq_image_analyze/vision/ui/analyzer.py
  • tests/test_json_schema.py
  • tests/test_compare.py
  • tests/test_analyze_ui.py
  • tests/test_exhaustive.py

Stability Rules

  • Current schema version: mq-image.analysis.v1.
  • Additive fields are allowed in minor versions.
  • Field removal or incompatible type changes require a major version bump.
  • limitations must always be present in full analysis outputs.
  • Summary mode may dedupe; exhaustive mode must preserve raw detections.
  • JSON output must not include ANSI text or human-only formatting.

Change Workflow

  1. Update implementation.
  2. Update tests for expected fields and modes.
  3. Update docs/json-schema.md.
  4. Regenerate or update examples when output shape changes.
  5. Update MCP docs if tool responses change.

Verification

python -m pytest \
  tests/test_json_schema.py \
  tests/test_compare.py \
  tests/test_analyze_ui.py \
  tests/test_exhaustive.py \
  -q

Before release:

bash scripts/validate.sh

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.

Check your setup, free