Add listening-script skill for source-preserving narration 🤖🤖🤖

[GODGOD126]

Description

Technical reports often rely on tables, visual references and qualifications that are easy to lose when adapting them for listening. This adds an instruction-only listening-script skill that preserves sample sizes, units, baselines, exceptions, attribution and uncertainty, while separating spoken narration from source and editorial notes.

The bundled fictional twelve-device example demonstrates why a lower median does not establish universal improvement, battery savings or user preference. The skill also distinguishes source adaptation from summarization and research, and respects proofreading-only requests.

Pull Request Checklist

• Read and followed CONTRIBUTING.md and the guidance for submissions involving paid services.
• Added the skill and its referenced example in the correct directory, with matching names and quoted description.
• Tested with GitHub Copilot, as described below.
• Ran npm run skill:validate successfully (427 skills).
• Ran npm run build (the implementation of npm start) and verified the generated skill index entry. The generator updated docs/README.skills.md; the root README needed no change.
• Ran bash eng/fix-line-endings.sh and git diff --check.
• Targeting main.

Type of Contribution

• New skill file.

Validation and limits

Tested in GitHub.com Copilot Free by pasting the skill instructions and a fictional table into a chat, requesting Chinese narration and separate notes. Copilot retained the fictional status, twelve-device sample, ten/eight-second medians, three devices favoring A, and the absence of battery measurements, user surveys and confidence intervals. The exact single-run-per-version detail appeared in the notes rather than narration. No audio was generated or listened to, and this was a prompt-inlined test, not a VS Code/CLI installation or automatic skill-discovery test.

The resource contains no executable scripts, account access, network calls, speech generation, required services or product recommendations. Source text still needs human verification; instruction following is not guaranteed.

Attribution

I am Ryan Zhu, author of the MIT-licensed source resource and developer of 「自听」MyListen. This contribution was prepared with AI assistance. No app or commercial service is needed to use it, and the skill and narration example contain no product advertising or sales links.

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

[github-actions]

🔒 PR Risk Scan Results

Scanned 2 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

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

[github-actions]

🚦 Submission status: ⏳ Awaiting automation

Risk tier: merge-risk:medium — New or substantially changed resource without privileged execution
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access.

Why this tier

• Adds 2 file(s), e.g. skills/listening-script/SKILL.md
• Changes 68 lines (low-risk limit is 40)

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
Contributor risk signal	🔧 Infrastructure failure	The contributor check succeeded but its result artifact was missing, unreadable, or for another commit · logs

Action needed

• 🔧 Contributor risk signal hit an automation problem that is not caused by your contribution. Comment /rerun-checks to retry; maintainers are notified if it keeps failing.

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)
• No staffed reviewer pool owns these files yet; any reviewer with write access counts as the domain reviewer.

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 7b0a855 · 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	✅ listening-script (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/listening-script
✅ listening-script (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