Add Chinese product decision agent skill 🤖🤖🤖

[atdy]

What

Adds product-decision-agent, a Chinese-first Agent Skill for product managers and product operations teams working in mainland China's internet-product context.

The skill diagnoses the real problem, current stage, dominant bottleneck, constraints, stakeholders, and evidence quality before recommending the highest-leverage next action. It covers product planning, requirement prioritization, growth, retention, conversion, operations, data anomalies, experiments, delivery, and cross-team coordination.

Why this belongs here

The catalog already has useful single-purpose skills for PRD generation, epic breakdown, GTM workflows, and scored impediment ranking. This contribution fills a different gap: it is a decision engine for ambiguous, cross-functional product situations where the user first needs to determine what the actual problem is and what not to do.

Its reasoning design is distilled from a complete reading of On Practice, On Contradiction, and related methodology in Volume I of the referenced anthology. The default user experience deliberately translates that foundation into modern product language: no source quotations, political framing, historical exposition, or philosophy lessons unless a maintainer explicitly audits the methodology reference.

The long Chinese description is intentional. It provides native-language triggers for real mainland-China workflows instead of relying on English-only PM terminology.

Included

• A self-contained SKILL.md with Chinese triggers, silent diagnostic workflow, output contract, and guardrails
• Four progressively loaded references:
  • reasoning engine
  • 36 product playbooks
  • response examples
  • methodology/source audit
• Optional, standard-library-only Python quality gate and regression tests
• MIT license and upstream repository attribution
• Generated docs/README.skills.md entry

The skill has no network calls, package installation steps, write actions, or required external runtime. The Python scripts are optional maintenance checks and only read supplied text files.

Validation

• npm run skill:validate: all 372 skills passed
• npm start: generated skill index updated successfully
• Microsoft Vally lint: 2/2 checks passed
  • spec compliance passed
  • all file references resolved
• Quality-gate regression suite: 8/8 passed
• Three representative Chinese product-answer samples passed the quality gate
• git diff --check: passed
• Local PR risk scan: 0 high findings
  • one medium finding comes from an existing generated npx entry elsewhere in docs/README.skills.md
  • two informational findings note the optional Python scripts

Source project: https://github.com/atdy/maoxuan-product-agent

[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 9 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	1
ℹ️ Info	2

Severity	Rule	File	Line	Match
🟠	package-exec-command	docs/README.skills.md	31	| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` | Run the AgentRC readiness assessment on the curre
ℹ️	skill-script-touched	skills/product-decision-agent/scripts/quality_gate.py	1	skills/product-decision-agent/scripts/quality_gate.py
ℹ️	skill-script-touched	skills/product-decision-agent/scripts/test_quality_gate.py	1	skills/product-decision-agent/scripts/test_quality_gate.py

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	npm warn EBADENGINE Unsupported engine {
ℹ️	npm warn EBADENGINE package: 'commander@15.0.0',
ℹ️	npm warn EBADENGINE required: { node: '>=22.12.0' },
ℹ️	npm warn EBADENGINE current: { node: 'v20.20.2', npm: '10.8.2' }
ℹ️	npm warn EBADENGINE }
ℹ️	npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
ℹ️	✅ product-decision-agent (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.

Full linter output

### Linting skills/product-decision-agent
npm warn EBADENGINE Unsupported engine {
npm warn EBADENGINE   package: 'commander@15.0.0',
npm warn EBADENGINE   required: { node: '>=22.12.0' },
npm warn EBADENGINE   current: { node: 'v20.20.2', npm: '10.8.2' }
npm warn EBADENGINE }
npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
✅ product-decision-agent (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]

This doesn't fit with this repo.