— No reviews yet
0 installs
5 views
0.0% view→install
Install
$ agentstack add skill-donkeyking01-nev-product-search-kit-nev-product-research ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Are you the author of Nev Product Research? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claimAbout
NEV Product Research
按“先证据,后判断”的顺序推进研究。不要从零散搜索结果直接跳到产品结论。
执行顺序
按以下顺序阅读和执行 workflow:
workflows/01_define_scope.mdworkflows/02_collect_evidence.mdworkflows/03_normalize_evidence.mdworkflows/04_build_product_model.mdworkflows/05_build_user_model.mdworkflows/06_diagnose_opportunity.mdworkflows/07_generate_deliverables.md
除非用户明确只要其中一个阶段,否则不要跳步。后续阶段必须引用前序产物。
先读什么
- 先读当前 workflow。
- 需要统一口径时,再读
references/evidence-rules.md。 - 需要确认交付结构时,再读
references/deliverables.md。 - 需要导出 PDF 时,使用
scripts/md_to_pdf.py。
核心约束
- 区分
Evidence、Inference、Assumption、Evidence Gap。 - 不要把用户原话直接写成产品结论。
- 不要把参数事实直接写成产品优势。
- 不要在证据不足时给出确定性判断。
- 不要从原始搜索结果直接生成 PRD。
- 默认用中文输出;仅在用户明确要求英文时切换。
文件约定
在研究输出目录中按顺序产出:
01_research_scope.md
02_evidence_collection.md
03_normalized_evidence_pack.md
04_product_model.md
05_user_model.md
06_opportunity_cards.md
07_market_brief.md
08_competitor_matrix.md
09_user_insight_report.md
10_prd_draft.md
11_final_report.md
final_report.pdf
如果用户只要部分交付物,仍然保持编号和证据链完整。
质量门槛
- 让每条关键判断都能追溯到来源。
- 明确写出缺失信息和待验证假设。
- 优先服务产品经理决策,而不是写成泛行业综述。
- 在最终报告中保留证据附录、关键假设和证据缺口。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DonkeyKing01
- Source: DonkeyKing01/nev-product-search-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.