Agent skill

Generate Prd

by huytieu in huytieu/COG-second-brain

Generate product requirements documents with optional publishing to Confluence or other wiki platforms

MITAuto-check passedProduct & Project Management

Install Generate Prd

skills CLI
$ npx skills add huytieu/COG-second-brain --skill generate-prd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huytieu/COG-second-brain generate-prd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/generate-prd .claude/skills/generate-prd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
generate-prd
GitHub stars
1.3k
Token cost
~2.4k tokens
SKILL.md length
466 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Generate product requirements documents with optional publishing to Confluence or other wiki platforms

  • Works in 6 steps: Gather Requirements → Context Gathering → Generate PRD → …
  • Tasks that involve PRD writing
  • SKILL.md covers When to Invoke, Agent Mode Awareness, Command: /generate-prd and Pre-Flight Check, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Generate Prd is an agent skill from huytieu/COG-second-brain. Generate product requirements documents with optional publishing to Confluence or other wiki platforms

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering PRD writing. It works with Confluence. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.

When your agent uses it

  • Tasks that involve PRD writing

Example prompts

  • “/generate-prd”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather Requirements
  2. Context Gathering
  3. Generate PRD
  4. Review Gate
  5. Save to Vault
  6. Publish (Optional, requires approval)

What it can do on your machine

Read from SKILL.md and the folder at commit 36ac9d7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Generate Prd loads about 2.4k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 466 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 466 words, ~2,354 tokens.

Download SKILL.mdSave it as .claude/skills/generate-prd/SKILL.md (or your agent's skills folder).
name
generate-prd
description
Generate product requirements documents with optional publishing to Confluence or other wiki platforms
roles
product-manager, engineering-lead, founder
integrations
confluence, notion, hackmd

COG Generate PRD Skill

When to Invoke

  • User wants to create a PRD, product spec, or requirements document
  • User says "generate PRD", "write PRD", "product requirements", "spec doc", "feature spec"
  • User has a feature or project that needs formal documentation before development

Agent Mode Awareness

Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:

  • If agent_mode: team — use parallel agents to gather context from multiple sources (existing PRDs, related issues, competitive research) while drafting
  • If agent_mode: solo — gather context and draft sequentially in the main conversation

Command: /generate-prd

Pre-Flight Check

  1. Read 00-inbox/MY-INTEGRATIONS.md to determine publishing options:

    • Confluence — can publish PRD to team wiki
    • Notion — can publish PRD to Notion workspace
    • HackMD — can publish PRD as shared markdown doc
    • If none active, PRD stays in the vault only (still fully useful)
  2. Read 00-inbox/MY-PROFILE.md for:

    • Active projects
    • User's name and role (for PRD author field)
  3. Get current timestamp: Run date '+%Y-%m-%d %H:%M' using Bash for the created: frontmatter field


Execution Strategy

Phase 1: Gather Requirements

Ask the user for the following (skip what they've already provided):

Required:

  • Feature/product name
  • Problem statement — what problem are we solving?
  • Target users — who is this for?
  • High-level solution — what are we building?

Optional (will generate reasonable defaults if not provided):

  • Success metrics — how do we measure success?
  • Constraints — technical, time, budget, or regulatory constraints
  • Dependencies — what does this depend on?
  • Related documents — links to designs, research, prior art
  • Target timeline — when does this need to ship?
Phase 2: Context Gathering
Team Mode (parallel agents)

Launch context-gathering agents using the Task tool with run_in_background: true:

Agent: "existing-prd-scanner"

Scan the vault for existing PRDs and related documents.

1. Glob for PRDs: 04-projects/*/PRDs/*.md
2. Glob for related project files: 04-projects/[project]/**/*.md
3. Read recent PRDs to understand the user's preferred format and level of detail
4. Look for any existing docs related to the feature being specified

Return: relevant existing content, user's PRD style preferences, and any related docs

Agent: "issue-context-gatherer"

Gather related issues and feature requests from active trackers.

Check 00-inbox/MY-INTEGRATIONS.md for active trackers, then:

If Linear is active:
1. Use ToolSearch to load Linear tools
2. Search for issues related to [feature keywords]
3. Check current initiatives and projects for context

If GitHub is active:
1. gh search issues "[feature keywords]" --repo [CUSTOMIZE: your-org/your-repo] --json number,title,body,labels --limit 15
2. Check for related discussions or feature requests

Return: related issues, existing feature requests, and any prior discussion context
Solo Mode

Run the same context gathering sequentially.

Phase 3: Generate PRD

Create the PRD using this template:

markdown
---
type: prd
project: [project-name]
feature: [feature-name]
status: draft
author: [user name]
created: [YYYY-MM-DD HH:MM]
last_updated: [YYYY-MM-DD]
version: "1.0"
approvers: [CUSTOMIZE: list of approvers]
tags: ["#prd", "#product", "#[project-name]"]
---

# PRD: [Feature Name]

## Overview

| Field | Value |
|-------|-------|
| **Author** | [Name] |
| **Status** | Draft |
| **Created** | [Date] |
| **Target Release** | [Timeline or TBD] |
| **Priority** | [High/Medium/Low] |

---

## 1. Problem Statement

[Clear description of the problem being solved. Include data or evidence where available.]

### Who is affected?
[Target users and how they're impacted]

### What is the current experience?
[How users currently deal with this problem]

### Why now?
[Why this is important to solve at this time]

---

## 2. Goals & Success Metrics

### Goals
1. [Primary goal]
2. [Secondary goal]
3. [Tertiary goal]

### Success Metrics
| Metric | Current Baseline | Target | Measurement Method |
|--------|-----------------|--------|-------------------|
| [Metric 1] | [Current] | [Target] | [How to measure] |
| [Metric 2] | [Current] | [Target] | [How to measure] |

### Non-Goals
- [What this project explicitly does NOT aim to solve]
- [Scope boundaries]

---

## 3. User Stories

### Primary User: [User Type]

**Story 1:** As a [user type], I want [goal] so that [benefit].

**Story 2:** As a [user type], I want [goal] so that [benefit].

### Secondary User: [User Type] (if applicable)

**Story 3:** As a [user type], I want [goal] so that [benefit].

---

## 4. Proposed Solution

### 4.1 Solution Overview
[High-level description of the proposed solution]

### 4.2 Key Features
1. **[Feature 1]** — [Description]
2. **[Feature 2]** — [Description]
3. **[Feature 3]** — [Description]

### 4.3 User Flow
[Step-by-step description of the primary user flow]

1. User [action]
2. System [response]
3. User [action]
4. System [response]

### 4.4 Edge Cases & Error Handling
| Scenario | Expected Behavior |
|----------|------------------|
| [Edge case 1] | [How the system handles it] |
| [Edge case 2] | [How the system handles it] |

---

## 5. Technical Considerations

### Architecture Impact
[How this fits into the existing system architecture]

### Dependencies
- [Dependency 1] — [Status: available/needs work]
- [Dependency 2] — [Status: available/needs work]

### Technical Risks
| Risk | Likelihood | Impact | Mitigation |
|------|-----------|--------|------------|
| [Risk 1] | [H/M/L] | [H/M/L] | [Mitigation plan] |

### Performance Requirements
- [Performance requirement 1]
- [Performance requirement 2]

---

## 6. Design & UX

[Link to designs or describe UX requirements]

### Key UX Principles
- [Principle 1]
- [Principle 2]

### Accessibility Requirements
- [Requirement 1]
- [Requirement 2]

---

## 7. Release Strategy

### Rollout Plan
- **Phase 1:** [Description] — [Timeline]
- **Phase 2:** [Description] — [Timeline]

### Feature Flags
- [Feature flag 1] — [Purpose]

### Rollback Plan
[How to roll back if issues arise]

---

## 8. Open Questions

- [ ] [Question 1] — Owner: [Name]
- [ ] [Question 2] — Owner: [Name]
- [ ] [Question 3] — Owner: [Name]

---

## 9. References

- [Link to related PRDs]
- [Link to designs]
- [Link to research]
- [Link to related issues/tickets]

---

## Changelog

| Version | Date | Author | Changes |
|---------|------|--------|---------|
| 1.0 | [Date] | [Author] | Initial draft |
Show full SKILL.md (187 more words)Show less
Phase 4: Review Gate

Present the generated PRD to the user:

PRD draft is ready for review.

Sections generated:
1. Problem Statement
2. Goals & Success Metrics
3. User Stories
4. Proposed Solution
5. Technical Considerations
6. Design & UX
7. Release Strategy
8. Open Questions
9. References

Would you like to:
a) Review the full PRD (I'll display it)
b) Save as-is to the vault
c) Make changes to specific sections
d) Publish to [active wiki platform] (requires your approval)

NEVER auto-publish. Always wait for explicit user approval.

Phase 5: Save to Vault

Save the PRD to: 04-projects/[project]/PRDs/prd-[feature-slug]-YYYY-MM-DD.md

Create the directory structure if it doesn't exist:

bash
mkdir -p "04-projects/[project]/PRDs"
Phase 6: Publish (Optional, requires approval)

Only proceed if the user explicitly approves publishing.

Confluence
Use WebFetch to publish via Confluence REST API:
- POST /wiki/rest/api/content
- Space: [CUSTOMIZE: YOUR-SPACE-KEY]
- Parent page: [CUSTOMIZE: PRDs-parent-page-id]
- Title: "PRD: [Feature Name]"
- Body: [converted to Confluence storage format]

Note: Convert markdown to Confluence XHTML storage format before publishing.
Notion
1. Use ToolSearch to load Notion tools
2. Use mcp__claude_ai_Notion__notion-create-pages to create the PRD page
3. Place under [CUSTOMIZE: PRDs database or parent page]
HackMD
Use WebFetch to publish via HackMD API:
- POST to create a new note
- Set permissions as configured

After publishing, update the vault copy with the published URL:

markdown
published_url: [URL]
published_at: [timestamp]

Fallback Behavior

ScenarioBehavior
No wiki platform activeSave to vault only — PRD is still fully useful as a local document
Publishing API failsSave to vault, provide the formatted content for manual publishing
User doesn't specify projectList active projects from MY-PROFILE.md and ask
Minimal input providedGenerate a skeleton PRD with [TODO] markers for the user to fill in
Existing PRD found for same featureAsk if this is an update/revision or a new PRD

Error Handling

  • Context overflow: If gathering too much context from existing docs, summarize rather than include full text
  • API failures: Always save to vault first, then attempt publishing as a separate step
  • Large PRDs: If the PRD exceeds typical wiki page limits, suggest splitting into sub-pages

© huytieu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/generate-prd of huytieu/COG-second-brain.

Open the folder on GitHubat commit 36ac9d7

Compare with similar skills

Generate Prd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Generate Prd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Generate Prd this skillhuytieu/COG-second-brain1.3k—~2.4kAutomated safety check: PassMIT
Plan Architecturecoleam00/skills674—~2.4kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Plan Architecture

    coleam00/skills

    Interactively explore HOW to approach an intent (a PRD, epic, brief, or free-form idea) and decide the high-level architecture — the approach, stack, libraries, data shape, and risks the intent left…

    674 GitHub stars~2.4k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed
  • Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

More from huytieu/COG-second-brain

All 37 skills in this repo
  • Voice Baseline

    huytieu/COG-second-brain

    Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.

    1.3k GitHub stars~957 tokensUpdated 7 days ago
    Auto-check passed
  • Daily Journal

    huytieu/COG-second-brain

    A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.

    1.3k GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed
  • Editorial Illustrations

    huytieu/COG-second-brain

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.

    1.3k GitHub stars~2.4k tokensUpdated 7 days ago
    Auto-check passed
  • Loop Engineering

    huytieu/COG-second-brain

    Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

    1.3k GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Release Video

    huytieu/COG-second-brain

    Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…

    1.3k GitHub stars~1.7k tokensUpdated 7 days ago
    Auto-check passed
  • Onboarding

    huytieu/COG-second-brain

    Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed

Works with

Questions about Generate Prd

What does Generate Prd do?

Generate product requirements documents with optional publishing to Confluence or other wiki platforms. Generate Prd is an agent skill from huytieu/COG-second-brain.

When should I use Generate Prd?

Generate Prd fits situations like: tasks that involve PRD writing.

How do I install Generate Prd in Claude Code?

Run `npx skills add huytieu/COG-second-brain --skill generate-prd -a claude-code`. Or copy the skill folder (skills/generate-prd in huytieu/COG-second-brain) into .claude/skills/generate-prd in your project. Claude Code loads it when a task matches its description.

How do I install Generate Prd in Codex?

Run `npx skills add huytieu/COG-second-brain --skill generate-prd -a codex`. Or copy the skill folder (skills/generate-prd in huytieu/COG-second-brain) into .agents/skills/generate-prd in your project. Codex loads it when a task matches its description.

Can I use Generate Prd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huytieu/COG-second-brain --skill generate-prd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-prd, .gemini/skills/generate-prd, .github/skills/generate-prd and .opencode/skills/generate-prd in your project.

What does Generate Prd need to run?

SKILL.md names no scripts, command-line tools or credentials: Generate Prd is instructions for the agent only.

Does Generate Prd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Generate Prd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Generate Prd use?

Generate Prd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Generate Prd use?

About 2.4k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Generate Prd?

Skills that share tags, products or a category with Generate Prd: Plan Architecture (coleam00/skills, 674 stars), CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars) and Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate Prd?

huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,267 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: huytieu/COG-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.