Skip to content
Back to search

product-skill-jev

A product management co-pilot that writes the documents, keeps the process honest, and leaves every decision to you. Plain language in, plain markdown out.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nhat-nguyet--product-skill-jev/badge.svg)](/listings/nhat-nguyet--product-skill-jev)

HTML

<a href="/listings/nhat-nguyet--product-skill-jev"><img src="/api/listings/nhat-nguyet--product-skill-jev/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You need Docker and one model API key. Claude gives the best documents; a free Groq key is enough to try it.

git clone https://github.com/Nhat-Nguyet/product-skill-jev.git my-pm-workspace
cd my-pm-workspace
cp .env.example .env      # set AI_PROVIDER and one key, plus TELEGRAM_BOT_TOKEN for the bot
bash setup.sh             # 1) Telegram bot  2) web portal  3) both

What you get:

- **Web portal** at `http://localhost` (options 2 and 3): chat on the left, the document being written on the right, plus Projects, Settings and an Audit Log of every change. A sample project is copied into `my-projects/` so there is something to open on day one. - **Telegram bot** (options 1 and 3): send `/start` to your bot, then `Show all projects`. - **Claude Code** without Docker: `cp AGENT.md CLAUDE.md`, then run `claude` in the folder. The skills in `.claude/skills/` load by themselves.

All three work on the same files, so you can start an idea on your phone and finish the PRD at your desk.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 190 lines
  1. <h1 align="center">Product Management Skill Jev</h1>
  2. <p align="center">
  3. <b>A product management co-pilot that writes the documents, keeps the process honest, and leaves every decision to you.</b><br>
  4. 21 skills from feature request to change request · PRDs frozen on approval, changes become new versions · conflicts between PRDs found by a deterministic tag scan · plain markdown in a folder you own · Telegram, web portal or Claude Code · Anthropic, OpenAI, Gemini, Groq or a local Ollama model · 170 tests
  5. </p>
  6. <p align="center">
  7. <b>English</b> · <a href="_readmes/README.vi.md">Tiếng Việt</a> · <a href="_readmes/README.zh-CN.md">中文</a> · <a href="_readmes/README.ja.md">日本語</a> · <a href="_readmes/README.fr.md">Français</a> · <a href="_readmes/README.es.md">Español</a>
  8. <br>
  9. <a href="#quick-start">Quick start</a> ·
  10. <a href="#example">Example</a> ·
  11. <a href="#skills">Skills</a> ·
  12. <a href="AGENT.md">Agent rules</a> ·
  13. <a href="examples/aipm-skills-project">Sample project</a>
  14. </p>
  15. <p align="center">
  16. <img alt="Python 3.12" src="https://img.shields.io/badge/Python-3.12-3776AB?style=flat-square&logo=python&logoColor=white">
  17. <img alt="Next.js 14" src="https://img.shields.io/badge/Next.js-14-000?style=flat-square&logo=next.js&logoColor=white">
  18. <img alt="Docker" src="https://img.shields.io/badge/Docker-compose-2496ED?style=flat-square&logo=docker&logoColor=white">
  19. <img alt="Tests: 170" src="https://img.shields.io/badge/tests-170-2f855a?style=flat-square">
  20. <a href="LICENSE"><img alt="License: CC BY-NC 4.0" src="https://img.shields.io/badge/license-CC_BY--NC_4.0-lightgrey?style=flat-square"></a>
  21. </p>
  22. ## Quick start
  23. You need Docker and one model API key. Claude gives the best documents; a free Groq key is enough to try it.
  24. ```bash
  25. git clone https://github.com/Nhat-Nguyet/product-skill-jev.git my-pm-workspace
  26. cd my-pm-workspace
  27. cp .env.example .env # set AI_PROVIDER and one key, plus TELEGRAM_BOT_TOKEN for the bot
  28. bash setup.sh # 1) Telegram bot 2) web portal 3) both
  29. ```
  30. What you get:
  31. - **Web portal** at `http://localhost` (options 2 and 3): chat on the left, the document being written on the right, plus Projects, Settings and an Audit Log of every change. A sample project is copied into `my-projects/` so there is something to open on day one.
  32. - **Telegram bot** (options 1 and 3): send `/start` to your bot, then `Show all projects`.
  33. - **Claude Code** without Docker: `cp AGENT.md CLAUDE.md`, then run `claude` in the folder. The skills in `.claude/skills/` load by themselves.
  34. All three work on the same files, so you can start an idea on your phone and finish the PRD at your desk.
  35. ## Example
  36. You write ordinary sentences. The co-pilot asks only for the facts it is missing, shows a draft, and writes nothing until you confirm.
  37. ```
  38. You Create a feature request for a Telegram bot so PMs can capture ideas on the go
  39. Jev Two questions. Who is asking for this, and what problem does it solve?
  40. You PM team. Ideas die in voice memos and never become documents.
  41. Jev Draft of FR-001 below. Say "save" to write it.
  42. You save
  43. Jev Saved to discovery/inbox/FR-001-telegram-bot.md
  44. Next: "Score FR-001 with RICE"
  45. ```
  46. From there the path is score, research, discovery gate, PRD, epics. Below is an excerpt of the epic at the end of that path in the [sample project](examples/aipm-skills-project), [`EP-001-v1.0.md`](examples/aipm-skills-project/epics/EP-001-telegram-bot/EP-001-v1.0.md):
  47. ```markdown
  48. ---
  49. doc-id: EP-001
  50. prd: PRD-001
  51. version: v1.0
  52. status: approved
  53. module: Bot
  54. sprint: S01
  55. ---
  56. ### US-001 - Send Feature Request
  57. **As a** Product Manager,
  58. **I want to** describe a feature in plain language to the bot,
  59. **So that** a structured FR document is created automatically.
  60. **Scenario 2 - Edge case: No active project set**
  61. Given: PM has not opened a project in this session
  62. When: PM sends "Create a feature request"
  63. Then: Bot asks "Which project is this for?" before proceeding
  64. ```
  65. Every document carries front matter that links it to the rest: FR to RICE score to PRD to epic, CR to the PRD version it produced.
  66. ## How it works
  67. ```mermaid
  68. graph LR
  69. FR[Feature request] --> RICE[RICE score]
  70. RICE --> Gate{Discovery gate}
  71. Gate -->|pass| PRD[PRD]
  72. Gate -->|gaps| FR
  73. PRD --> Epics[Epics with Given/When/Then]
  74. Epics --> Approve[Approved, frozen]
  75. Approve --> CR[Change request]
  76. CR --> Scan[Tag conflict scan]
  77. Scan --> V2[New PRD version]
  78. ```
  79. Three rules hold it together:
  80. 1. **It drafts, you decide.** Every skill ends by showing the draft and waiting for a yes.
  81. 2. **Approved means frozen.** A signed-off PRD is never edited. A change request produces v1.1 or v2.0, with the reason recorded in the changelog and in `VERSIONS.md`.
  82. 3. **The gate means something.** Features with RICE below 20 are steered towards a change request on an existing PRD. Research without a Security and Compliance section blocks the gate.
  83. Each project is one folder of markdown:
  84. ```
  85. my-projects/PROJ-002-checkout-redesign/
  86. PROJECT.md VERSIONS.md
  87. discovery/ inbox/ scoring/ research/ gate/
  88. prd/ PRD-004-one-tap-checkout/PRD-004-v1.0.md, PRD-004-v1.1.md, CHANGELOG.md
  89. epics/ cr/ stakeholders/ decisions/ sprints/ reviews/
  90. ```
  91. Open it in VS Code, Obsidian or any editor. Commit it to git and your PRD history becomes a readable diff.
  92. ## Why it is different
  93. | | This project | A PRD prompt in a chat assistant | Hosted AI PRD tools |
  94. |---|---|---|---|
  95. | Where documents live | Plain markdown in your folder | A chat transcript you copy out | The vendor's workspace |
  96. | Process | FR, RICE, gate, PRD, epic, CR, each skill suggests the next step | One document at a time | Mostly document drafting |
  97. | After approval | Frozen, changes become new linked versions | Not tracked | Depends on the tool |
  98. | Conflicts between PRDs | Python scan of shared module tags, then optional model ranking | Not covered | Depends on the tool |
  99. | Model | Your choice of five providers, including a local model | The assistant's model | The vendor's model |
  100. | Changing the behaviour | Edit a `SKILL.md` in plain English | Rewrite the prompt each time | Not possible |
  101. The conflict scan ([`bot/tags.py`](bot/tags.py)) is ordinary code: it lists every pair of PRDs sharing a module tag and reports untagged PRDs as "not checkable", which is not the same as "no conflicts". A model is only asked afterwards whether a shared tag is a real collision.
  102. The other rules (draft before write, frozen approvals, the gate) are instructions in the skills, carried out by the model. They are reliable with strong models and worth checking with weak ones.
  103. ## Skills
  104. Each skill is a folder under [`.claude/skills/`](.claude/skills) with one `SKILL.md`. Claude Code picks them up from their descriptions; the bot and the web backend find them through the index in [`AGENT.md`](AGENT.md).
  105. | Area | Skills |
  106. |------|--------|
  107. | Discovery | create-fr, score-feature, gate-review, deep-research |
  108. | PRD | to-prd, manage-epic, conflict-check, grill-prd, update-prd |
  109. | Project | create-project, find-project, project-status |
  110. | Change requests | intake-cr, assess-cr, approve-cr |
  111. | Stakeholders | add-stakeholder, draft-comms |
  112. | Platform | setup-workspace, new-sprint, version-doc, product-skill-jev |
  113. They are instructions, not code. Editing one changes how the co-pilot behaves.
  114. The agent has seven tools and no others: `read_file`, `write_file`, `list_files`, `search_files`, `move_file`, `scan_tags` and `judge` (see [`bot/agent.py`](bot/agent.py)).
  115. ## Models
  116. Set `AI_PROVIDER` in `.env`, or save several keys in the portal's Settings page and switch with a click. [`.env.example`](.env.example) has a ready block for each option.
  117. | Provider | Setting |
  118. |----------|---------|
  119. | Anthropic Claude (best document quality) | `AI_PROVIDER=anthropic` |
  120. | OpenAI | `AI_PROVIDER=openai` |
  121. | Groq (free tier, good for trying it out) | `AI_PROVIDER=openai` with the Groq base URL |
  122. | Google Gemini | `AI_PROVIDER=google` |
  123. | Ollama (runs on your own machine) | `AI_PROVIDER=openai` with a localhost base URL |
  124. ## Optional: Jev classifier
  125. Jev is a fast classifier from TypeSafe AI that returns labels with probabilities instead of prose. With `TYPESAFE_API_KEY` set, it suggests the type and urgency of stakeholder feedback, routes commands when the main provider is down, suggests a folder for uploaded files, and answers five typed question sets through the `judge` tool: `fr_triage`, `gate_review`, `rice_bands`, `cr_assessment`, `conflict_pair`.
  126. Jev never writes a file. With no key, a timeout or low confidence, every path falls back to the behaviour without Jev. Questions and thresholds live in [`bot/jev.py`](bot/jev.py); the portal can override thresholds and restore the defaults. Details: [`.claude/skills/product-skill-jev`](.claude/skills/product-skill-jev/SKILL.md).
  127. ## Commands and tests
  128. ```bash
  129. make start | stop | restart | logs | status | update # Telegram bot, from the repository root
  130. cd apps && make start | stop | logs | build # web portal
  131. ```
  132. ```bash
  133. pip install -r tests/requirements.txt -r apps/backend/requirements.txt -r bot/requirements.txt
  134. cd apps/backend && python3 -m pytest ../../tests/
  135. ```
  136. The suite has 170 tests in five files (installation 35, agent tools 26, backend API 26, Jev 61, tag scan 22). With a `.env` file in place (the Docker config checks read it) and no backend running, 144 pass and the 26 API tests skip themselves. No test calls a paid API.
  137. ## What it is not
  138. It does not talk to your customers and it does not tell you what to build. It writes well and forgets nothing, which is a different skill from judgment. The judgment stays yours.
  139. ## Credits and license
  140. Built on ideas from [mattpocock/skills](https://github.com/mattpocock/skills) (skill format), [RICE scoring](https://www.intercom.com/blog/rice-simple-prioritization-for-product-managers/) (Intercom), [Continuous Discovery Habits](https://www.producttalk.org/) (Teresa Torres), [Inspired](https://www.svpg.com/books/inspired-how-to-create-tech-products-customers-love-2nd-edition/) (Marty Cagan), [user stories](https://www.mountaingoatsoftware.com/agile/user-stories) (Mike Cohn) and [Architectural Decision Records](https://adr.github.io/).
  141. Maintained by [Nhat Nguyet](https://github.com/Nhat-Nguyet). Licensed under [CC BY-NC 4.0](LICENSE): free to use, share and adapt for non-commercial purposes with attribution.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.