Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.
SkillScore95Maintained
Automatic
◆QA & Test Engineering pack
Last verified 9/2/2026
What it changes
Passed 21 of 22 test cases with the skill, and 18 of 22 without it.
Prohibits reporting degraded or skipped test runs as full validation.
Requires storing an explicit fallback record detailing why a check was skipped.
3 fixed18 passed either way1 still failing0 broke
Pass-rate lift
+14 pp
Tokens
+6%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 9/2/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
Our repository currently has fragmented test scripts across package.json, Makefiles, and GitHub Actions, making it hard for developers and automated tools to know what to run. Could you analyze our repository structure and design a comprehensive validation harness strategy? Please provide a markdown document that maps out our existing checks, outlines a matrix pairing specific change types with their minimum validation and escalation rules, details a unified command interface, specifies structured report formats for both humans and CI, outlines CI pipeline gates, and defines policies for handling skips or fallback environments.
What was checked, without and with the skill
Checked
Without skill
With skill
Includes a Change-Type Matrix table with columns "Change type", "Minimum check", and "Escalation".
Passed
Passed
Assigns fast static or linting verification as the minimum gate for documentation changes.
Prohibits reporting degraded or skipped test runs as full validation.
Missed
Passed
case-01 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md83 lines3 files
Validation Harness Design
Overview
Define the smallest repeatable command surface that proves repository changes are safe enough for review.
This skill turns scattered checks into commands agents can run, CI can reuse, and failures can diagnose. For shared harness terms, see ../../references/harness-patterns.md; when validation commands are absent, use references/build-when-missing.md. For setup probes and CI-safe fallbacks, see references/environment-bootstrap.md.
When To Use
The user wants check_repo_harness.py, doctor.py, a test matrix, or CI gates.
Existing validation commands are scattered and agents do not know what to run for docs-only, interface, service, logic, or runtime changes.
JSON, JUnit, or artifact output is needed.
Inputs Needed
Project shape, main surfaces, existing test commands, and CI configuration.
Change types and the minimum gate for each type.
Whether runtime, packaged-environment, external-dependency, or manual checks are needed.
Execution Order
First: Inventory existing commands and CI to confirm what already works.
Then: Design a layered validation matrix and unified entrypoint.
Finally: Output the command table, report formats, CI wiring, and fallback rules.
Step-by-Step Process
Search package.json, Makefile, scripts, CI workflows, test directories, and docs.
Split validation into repo/docs, contracts, unit/type/lint, runtime, and external-dependency layers.
If there is no shared validation entrypoint, bootstrap the minimum command surface from references/build-when-missing.md.
For each change type, choose the minimum command and escalation condition.
Design a unified entrypoint: check_repo_harness or doctor handles environment/structure, while focused commands test behavior.
Design report output: stdout for humans, JSON/JUnit for CI and artifacts.
Require skip/fallback reasons; do not describe degraded validation as full validation.
Checks
Runnable: commands work in a clean checkout or documented setup.
Layered: docs-only work does not require heavy runtime checks, and runtime changes do not stop at static checks.
Retrieve a vehicle history report from a VIN using the CarsXE API. Use this when a user wants to know a car's history — past owners, accidents, title status, odometer readings, or whether it's been in a crash.