Skills product-decision-agent
📦

product-decision-agent

v1.0.3 Content revision r2 Safe 🌐 Network access📁 Filesystem access⚙️ External commands

Diagnose Product Decisions in Chinese

Product teams often mistake symptoms for root causes and spread resources across weak priorities. This skill identifies the main blocker and recommends measurable next actions.

Supports: Claude Codex Code(CC)
🥇 84 Gold

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "product-decision-agent" from https://skillstore.io/skills/atdy-product-decision-agent.md and its manifest at https://skillstore.io/api/skills/atdy-product-decision-agent/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/atdy-product-decision-agent.md Signed manifest GET /api/skills/atdy-product-decision-agent/manifest Signed lockfile GET /api/skills/atdy-product-decision-agent/lockfile

Test it

Using "product-decision-agent". D7 retention fell after a new onboarding release. Should we redesign onboarding or increase acquisition?

Expected outcome:

  • 问题判断：先确认版本变更是否破坏新用户首次价值路径。
  • 行动建议：今天按版本和渠道拆分 D7 留存，并核对关键埋点。
  • 决策规则：若新版本显著下降，先灰度回滚；否则继续检查渠道结构。

Using "product-decision-agent". A key stakeholder added an urgent feature and the release is now delayed.

Expected outcome:

  • 问题判断：当前是资源取舍和决策权问题，不是单纯执行变慢。
  • 行动建议：列出插入需求造成的延期、被挤出范围和风险，请结果负责人当天拍板。
  • 风险提醒：不要让团队静默吸收新增范围。

Security Audit

Safe
v3 • 7/23/2026 Open versioned report

All 18 static findings are false positives. The URLs are comments, test fixtures, or repository metadata, and the backticks are Markdown code spans. Temporary directories support isolated tests, while entropy signals reflect plain UTF-8 Chinese text rather than encoded payloads.

9
Files scanned
2,070
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

🌐 Network access (3)
scripts/quality_gate.py:143 scripts/test_quality_gate.py:54 SKILL.md:7
📁 Filesystem access (2)
scripts/test_quality_gate.py:7 scripts/test_quality_gate.py:61
⚙️ External commands (5)
SKILL.md:61 SKILL.md:62 SKILL.md:63 SKILL.md:64 SKILL.md:65
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/atdy-product-decision-agent/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/atdy-product-decision-agent/security.svg)](https://skillstore.io/skills/atdy-product-decision-agent?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/atdy-product-decision-agent?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/atdy-product-decision-agent/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/atdy-product-decision-agent.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

atdy. (2026). product-decision-agent security audit report (audit version 3) [Author version 1.0.3]. Skillstore. https://skillstore.io/skills/atdy-product-decision-agent/audits/3

BibTeX citation

@techreport{atdy-atdy-product-decision-agent-2026, author = {atdy}, title = {product-decision-agent security audit report (audit version 3)}, institution = {Skillstore}, year = {2026}, number = {3}, url = {https://skillstore.io/skills/atdy-product-decision-agent/audits/3}, note = {Author version 1.0.3} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "product-decision-agent security audit report (audit version 3)" version: "1.0.3" type: report authors: - name: "atdy" date-released: "2026-07-23" url: "https://skillstore.io/skills/atdy-product-decision-agent/audits/3" identifiers: - type: other value: "skillstore:atdy-product-decision-agent:audit:3" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
68
Architecture
100
Maintainability
87
Content
67
Community
91
Spec Compliance

What You Can Build

Prioritize a Product Roadmap

Compare competing requests by product stage, expected outcome, constraints, evidence, and opportunity cost.

Diagnose Growth Decline

Locate the weakest acquisition, activation, retention, conversion, or channel segment before increasing spend.

Unblock Cross-Team Delivery

Map decision rights, dependencies, tradeoffs, and escalation needs for delayed or unstable projects.

Try These Prompts

Find the Main Blocker 
Diagnose this product problem: [problem]. State the main blocker, the next action, and what we should stop doing.
Investigate a Metric Change 
Our [metric] changed from [baseline] to [current] after [event]. Identify likely causes, minimum checks, and a decision rule.
Choose Roadmap Priorities 
Rank these initiatives: [list]. Use our stage, goal, team capacity, evidence, dependencies, and deadlines. Name the excluded work and tradeoffs.
Design a Decision Plan 
Assess [complex problem] using facts, assumptions, stakeholders, constraints, and risks. Propose one main action, one validation step, and clear change conditions.

Best Practices

  • Provide the target outcome, baseline metrics, recent changes, available resources, and hard deadlines.
  • Separate observed facts from team assumptions and requested solutions.
  • Return with experiment results or new evidence so the recommendation can adapt.

Avoid

  • Do not ask for a long list of equal recommendations without a primary choice.
  • Do not omit user segments, metric definitions, or the time window behind a reported change.
  • Do not treat the response as verified legal, compliance, security, or financial advice.

Frequently Asked Questions

What language does the skill use?
It responds in Chinese by default while preserving common product abbreviations such as CAC, LTV, ROI, and MVP.
What information produces the best diagnosis?
Provide the desired outcome, current metrics, affected users, recent changes, constraints, stakeholders, and previous attempts.
Can it create a complete PRD?
It can clarify the problem, scope, priority, metrics, and decision logic. Detailed specifications still require product and technical validation.
Does it access live company data?
No. It reasons from information supplied in the conversation and does not retrieve live dashboards or production records.
Does the skill send data over the network?
The included files contain no network request logic. Data handling still depends on the host platform and selected model.
Must I run the included Python script?
No. The script is an optional local quality gate for maintainers checking sample responses.

Developer Details

Author

atdy

License

MIT

Author version

v1.0.3

Skillstore revision

r2

Repository

https://github.com/atdy/maoxuan-product-agent/tree/main/product-decision-agent/

Ref

89edfdc710d0846129dcee6a929477b04f08052c

Maintenance freshness

7/24/2026

Usage

4 downloads · 0 views

File structure

📁 agents/

📄 openai.yaml

📄 LICENSE

📁 references/

📄 methodology-basis.md

📄 product-playbooks.md

📄 reasoning-engine.md

📄 response-examples.md

📁 scripts/

📄 quality_gate.py

📄 test_quality_gate.py

📄 SKILL.md

Related Skills

View all