[arez-xd]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, workflow, or canvas extension file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, workflow, or canvas extension with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the main branch for this pull request.

---

Description

Checks whether a skill, an instructions file, a prompt or an MCP server changes what the agent does. It builds a fictional target with planted problems and traps (legitimate decisions that look like mistakes), writes the answer key before any run, runs the same request with and without the customization in isolated agents, grades the outputs without knowing which arm wrote them and reports what the numbers can honestly claim.

It has two levels: a quick check by default, and the full test with calibration and normalization when the numbers go public. Useful to anyone writing skills or instructions for Copilot before they publish them. The repository includes a test of the skill with its own method.

No paid service or account needed. Source, MIT: https://github.com/arez-xd/blind-test

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• New canvas extension.
• Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.
• Other (please specify):

---

Additional Notes

Bundled scripts, Node 18+, no dependencies, network calls or installs:

• score.mjs, refcheck.mjs, blind-labels.mjs work on local files: scoring grades against the key, checking that a rewrite kept every file and line, copying results under random labels.
• target-server.mjs serves the test folder on 127.0.0.1; any request other than GET or HEAD gets 405 and is logged.

agents/claude.yaml and agents/openai.yaml are display metadata for agents that read them. npm run skill:validate and npx @microsoft/vally-cli lint pass.

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

🤖 Generated with Claude Code

[github-actions]

🔒 PR Risk Scan Results

Scanned 17 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	4

Severity	Rule	File	Line	Match
ℹ️	skill-script-touched	skills/blind-test/scripts/blind-labels.mjs	1	skills/blind-test/scripts/blind-labels.mjs
ℹ️	skill-script-touched	skills/blind-test/scripts/refcheck.mjs	1	skills/blind-test/scripts/refcheck.mjs
ℹ️	skill-script-touched	skills/blind-test/scripts/score.mjs	1	skills/blind-test/scripts/score.mjs
ℹ️	skill-script-touched	skills/blind-test/scripts/target-server.mjs	1	skills/blind-test/scripts/target-server.mjs

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🚦 Submission status: 👀 Ready for review

Risk tier: merge-risk:high — Privileged execution, automation, or review-policy change
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access, including a maintainer with admin or maintain permission.

Why this tier

• skills/blind-test/scripts/blind-labels.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
• skills/blind-test/scripts/refcheck.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
• skills/blind-test/scripts/score.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)
• skills/blind-test/scripts/target-server.mjs is a high-risk path (automation, scripts, MCP config, hooks, or review policy)

Automated checks

Check	Status	Details
Line endings	✅ Passed	Passed · logs
Spelling	✅ Passed	Passed · logs
Generated README consistency	✅ Passed	Passed · logs
Skill validation	✅ Passed	Passed · logs
Skill lint (vally)	✅ Passed	Passed · logs
Risk scan	✅ Passed	Passed · logs
Contributor reputation	✅ Passed	Passed · logs
Duplicate resource scan	✅ Passed	Passed · logs
PR quality signal	⏭️ Skipped	Skipped by its workflow · logs

Review

• Approvals: 0/1
• Assigned reviewer: not assigned yet — comment /request-review to ask for one
• Review target date: not set
• Still needed: 1 more approval(s); an approval from a maintainer with admin or maintain permission
• The core-maintainers pool is not staffed yet; an approver with admin or maintain permission is required instead.

Commands

Command	Who	What it does
/rerun-checks	PR author, maintainers	Re-runs failed or incomplete checks and re-evaluates this gate
/request-review	PR author, maintainers	Asks the review rotation to assign a reviewer (adds needs-reviewer)

_{Updated for 552dd12 · gate run · This comment is maintained automatically — see submission gate docs.}

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	✅ blind-test (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️	✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️	1 skill(s) linted, 1 passed

Full linter output

### Linting skills/blind-test
✅ blind-test (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

[aaronpowell]

The upstream README for the linked source repository routes readers to Agensi referral links for Design Taste Pro and an Agensi edition of Blind Test. That creates the same free-skill-to-paid-companion promotion path identified in the reviews of #6230 and #6231, so we can’t accept this contribution in the catalog.