MistakeyMistakey/simulink-automation-suite/.claude/skills/live-testing/SKILL.md

live-test

Skill9 starsChanged 8 months agoMITView on GitHub

Execute end-to-end functional testing on real MATLAB/Simulink hardware. Schema-driven discovery makes this version-agnostic — no updates needed when plugin actions change. Use when asked to "run live test", "test on real device", "实机测试", or "/live-test". Supports full, incremental, and targeted re-test modes.

3 other projects use a version of this.

Adopted by

Most recently taken up by

KadirHarmanc/nazar-skilltheir own version, first seen Nov 8, 2026
mindroom-ai/mindroomtheir own version, first seen Nov 1, 2026
leadgenjay/claude-skillstheir own version, first seen Jun 19, 2026

Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
mindroom-ai/mindroom★ 361same name
leadgenjay/claude-skills★ 22same name
KadirHarmanc/nazar-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- releaseSkill

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
When invoked, determine the test mode:
line 38
Very specific:
Read .claude/skills/live-testing/phases.md for detailed phase definitions before executing.
line 76

“Common” is measured: kept by at least 6 in 10 of the 3 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

Live Device Testing

End-to-end functional verification of the simulink-automation-suite plugin on real MATLAB/Simulink hardware. This skill tests the plugin as a user would — through its published interface, not its source code.

On-Demand References

.claude/skills/live-testing/phases.md — Detailed phase definitions, test case generation rules, pass/fail criteria, error handling. Read when starting test execution.
.claude/skills/live-testing/report-template.md — Report format, update rules, suggestions generation. Read when writing or updating the report (Phase 6).

Isolation Rules

PROHIBITED:
  - Read simulink_cli/ source code
  - Read tests/ unit tests

REQUIRED:
  - Discover available actions via: python -m simulink_cli --json '{"action":"schema"}'
  - Execute all tests via CLI commands
  - Generate test cases dynamically from schema output

ALLOWED:
  - Read skills/simulink_automation/SKILL.md (shipped skill — Phase 5 doc-accuracy target)
  - Read skills/simulink_automation/reference.md (shipped reference doc)
  - Read docs/reports/ (compare with previous reports)
  - Read git log (determine incremental scope)

Reading the shipped skill files is a deliberate, scoped exception — the purpose is to verify that documentation actually guides users to correct results.

Test Mode Selection

When invoked, determine the test mode:

Does docs/reports/LIVE-TEST-REPORT.md exist?
├─ No → FULL test (all phases, all actions)
└─ Yes → Read report, extract test_commit and schema snapshot
         Did user request "full"?
         ├─ Yes → FULL test
         └─ No → INCREMENTAL (see Incremental Logic below)

User specifies "retest FAIL-001" or "retest Phase 3"?
└─ TARGETED test (only specified items)

Incremental Logic

1. Read test_commit from existing report
2. Run: git log {test_commit}..HEAD --oneline
3. Run: python -m simulink_cli --json '{"action":"schema"}'
4. Compare schema output with Schema Snapshot section in report

Mandatory re-tests:
  - All items with status FAIL
  - All items with status BLOCKED (re-check environment)

AI-judged additions:
  - Commit messages reference specific actions → re-test those action's items
  - skills/simulink_automation/SKILL.md changed → re-test Phase 5
  - Schema output differs from snapshot → re-test Phase 1 + Phase 4
  - Optionally spot-check some PASS items for regression

If changes are large-scale (refactor, new actions added to schema):
  - Suggest full test to user, ask for confirmation

Execution Flow Overview

Read .claude/skills/live-testing/phases.md for detailed phase definitions before executing.

Phase	Name	Scope
0	Environment Check	MATLAB reachability (always runs)
1	Meta Layer	`schema`, `session`, `list_opened`
2	Read-Only Layer	`scan`, `find`, `connections`, `inspect`, `highlight`
3	Lifecycle & Write	`model_open`, `model_new`, `set_param`, `model_save`
4	Error Handling	Invalid inputs, error codes, rejection behavior
5	Documentation	SKILL.md accuracy, schema-behavior consistency
6	Report	Compile results → `docs/reports/LIVE-TEST-REPORT.md`

Action lists are illustrative for v2.2.0. When schema reveals unlisted actions, assign by characteristic: meta → Phase 1, read-only → Phase 2, lifecycle/write → Phase 3.

Incremental mode: skip unaffected phases, but Phase 0 always runs.

For report format and update rules, read .claude/skills/live-testing/report-template.md during Phase 6.

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