Add source-backed pronounce-word skill 🤖🤖🤖

[anzy-renlab-ai]

Summary

Add a focused Agent Skill for a gap general models handle poorly: pronouncing non-obvious and contested developer names from spelling alone.

The skill:

• handles one short developer tool, AI model, acronym, or project name
• reads structured IPA, respelling, confidence, alternatives, and citations from a 1,900+ entry public dictionary
• plays curated local audio when the cross-platform say-it CLI is installed
• falls back to a public read-only JSON API without claiming an unknown reading is verified
• asks before installation and never pipes a remote script into a shell
• respects text-only and stop-audio requests

The canonical data and CLI are maintained in the public MIT-licensed Pronounce project.

Validation

• npm ci
• npm run skill:validate — all 416 skills valid
• npm run build — generated docs/README.skills.md
• live API smoke test for kubectl — word, IPA, and audio URL present
• git diff --check

bash eng/fix-line-endings.sh was also run. Its GNU sed syntax prints compatibility errors under macOS BSD sed; the added files are LF-only and the Linux CI job can run the repository script natively.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔒 PR Risk Scan Results

Scanned 1 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]

🔍 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	✅ pronounce-word (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/pronounce-word
✅ pronounce-word (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