Improve run-tests skill description

[Evangelink]

Improves the description using the prompt from Manish

[Copilot]

Pull request overview

Updates the run-tests skill frontmatter description to better align with the repository’s guidance for skill selection (what it does, when to use it, and when not to).

Changes:

• Rewrites the description frontmatter as a multi-line YAML scalar with explicit “use when…” and “do not use for…” guidance.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.

[github-actions]

Skill Validation Results

Skill	Scenario	Quality (Isolated)	Quality (Plugin)	Skills Loaded	Overfit	Verdict
run-tests	Run tests in a VSTest MSTest project	1.0/5 → 1.0/5	1.0/5 → 1.0/5	⚠️ NOT ACTIVATED / ⚠️ NOT ACTIVATED	✅ 0.19	❌ [1]
run-tests	Run tests with trx reporting on MTP project (SDK 9)	2.0/5 → 3.0/5 🟢	2.0/5 → 3.3/5 🟢	✅ run-tests; tools: skill / ✅ run-tests; tools: skill, glob	✅ 0.19	✅
run-tests	Run tests with blame-hang on MTP project (SDK 10)	1.0/5 → 1.0/5	1.0/5 → 1.0/5	⚠️ NOT ACTIVATED / ⚠️ NOT ACTIVATED	✅ 0.19	❌ [2]
run-tests	Run tests in a multi-TFM project targeting a specific framework	1.0/5 → 3.0/5 🟢	1.0/5 → 2.7/5 🟢	⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill, bash	✅ 0.19	✅
run-tests	Filter MSTest tests by category on VSTest	1.7/5 → 2.7/5 🟢	1.7/5 → 1.7/5 ⏰	✅ run-tests; tools: skill, glob / ✅ run-tests; tools: glob, skill, grep	✅ 0.19	✅
run-tests	Filter NUnit tests by class name on VSTest	2.0/5 → 1.7/5 🔴	2.0/5 → 2.0/5	✅ run-tests; tools: skill, bash / ✅ run-tests; tools: skill, glob, bash	✅ 0.19	❌ [3]
run-tests	Filter xUnit v3 tests by class on MTP	1.0/5 → 2.0/5 🟢	1.0/5 → 1.7/5 🟢	✅ run-tests; tools: skill, glob, bash / ✅ run-tests; tools: skill, bash	✅ 0.19	✅
run-tests	Filter xUnit v3 tests by trait on MTP	1.0/5 → 1.7/5 🟢	1.0/5 → 1.7/5 🟢	✅ run-tests; tools: skill, glob / ✅ run-tests; tools: skill, glob	✅ 0.19	✅
run-tests	Filter TUnit tests by class using treenode-filter	1.0/5 → 4.7/5 🟢	1.0/5 → 4.3/5 🟢	✅ run-tests; tools: skill, glob / ✅ run-tests; tools: skill, glob	✅ 0.19	✅
run-tests	Combine multiple filter criteria on VSTest MSTest	2.0/5 → 3.7/5 🟢	2.0/5 → 3.7/5 🟢	✅ run-tests; tools: skill, bash, glob / ✅ run-tests; tools: skill, task, glob, bash, grep	✅ 0.19	✅
run-tests	MTP project on SDK 9 must use -- separator for args	1.0/5 → 1.0/5	1.0/5 → 1.0/5	✅ run-tests; tools: bash, skill / ✅ run-tests; tools: bash, skill, glob	✅ 0.19	❌ [4]
run-tests	MTP project on SDK 10 passes args directly	1.0/5 → 1.0/5	1.0/5 → 1.0/5	✅ run-tests; tools: skill, glob / ✅ run-tests; tools: skill	✅ 0.19	❌ [5]
run-tests	Detect test platform from Directory.Build.props	1.3/5 → 4.0/5 🟢	1.3/5 → 4.0/5 🟢	✅ run-tests; tools: skill / ✅ run-tests; tools: skill	✅ 0.19	✅
run-tests	Negative test: do not use MTP syntax for a VSTest project	1.0/5 → 1.0/5	1.0/5 → 1.0/5	✅ run-tests; tools: skill / ✅ run-tests; tools: skill, glob	✅ 0.19	❌ [6]

[1] (Isolated) Quality unchanged but weighted score is -1.0% due to: time (16.5s → 21.2s)
[2] (Isolated) Quality unchanged but weighted score is -0.9% due to: tokens (35046 → 40891)
[3] (Plugin) Quality unchanged but weighted score is -6.7% due to: quality, tokens (35245 → 51755), tool calls (4 → 6)
[4] (Plugin) Quality unchanged but weighted score is -12.5% due to: tokens (27157 → 57243), quality, tool calls (2 → 5), time (15.1s → 28.2s)
[5] (Isolated) Quality unchanged but weighted score is -7.8% due to: tokens (34965 → 63407), tool calls (3 → 6), time (17.8s → 26.3s)
[6] (Isolated) Quality unchanged but weighted score is -8.5% due to: tokens (34929 → 68854), tool calls (3 → 6), time (15.1s → 22.0s)

⏰ timeout — run hit the scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output

Model: claude-opus-4.6 | Judge: claude-opus-4.6

Full results