CCPM Project Management
automazeio/ccpm
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.
Extract a product idea through guided questions and generate a PRD.
$ npx skills add davekilleen/Dex --skill product-brief -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install davekilleen/Dex product-brief --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/product-brief .claude/skills/product-brief && rm -rf skills-srcUse ~/.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/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .claude/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-briefType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add davekilleen/Dex --skill product-brief -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install davekilleen/Dex product-brief --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/product-brief .agents/skills/product-brief && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .agents/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davekilleen/Dex --skill product-brief -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install davekilleen/Dex product-brief --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/product-brief .cursor/skills/product-brief && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .cursor/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/davekilleen/Dex.git --path .agents/skills/product-brief--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add davekilleen/Dex --skill product-brief -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install davekilleen/Dex product-brief --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/product-brief .gemini/skills/product-brief && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .gemini/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install davekilleen/Dex product-briefInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add davekilleen/Dex --skill product-brief -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/product-brief .github/skills/product-brief && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .github/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davekilleen/Dex --skill product-brief -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install davekilleen/Dex product-brief --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davekilleen/Dex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/product-brief .opencode/skills/product-brief && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "product-brief" agent skill from https://github.com/davekilleen/Dex/tree/main/.agents/skills/product-brief into .opencode/skills/product-brief/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "product-brief", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
product-briefExtract a product idea through guided questions and generate a PRD.
Product Brief is an agent skill from davekilleen/Dex. Extract a product idea through guided questions and generate a PRD. Use when the user says 'write a PRD', 'spec this feature', 'turn this idea into a brief'. Not for a non-product initiative like hiring or partnerships (use initiative-kickoff once shipped); not for checking existing projects' status (use project-health).
Its SKILL.md is about 4.3k 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. The repository describes itself as: Your AI Chief of Staff — a personal operating system starter kit that adapts to your role. No coding required. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d0ffc6b. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Product Brief loads about 4.3k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 989 words of instructions outside code blocks.
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.
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.
The full file from davekilleen/Dex at commit d0ffc6b, republished under its MIT licence (© davekilleen). 989 words, ~4,290 tokens.
.claude/skills/product-brief/SKILL.md (or your agent's skills folder).<!-- Generated from `.claude/skills/product-brief/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->
Extract product ideas from your head through guided questioning, then generate a detailed Product Requirements Document (PRD). Designed for product people who have a vision but need help articulating it clearly.
You have an idea for a product or feature in your mind, but struggle to explain it comprehensively. This command acts as your product thought partner — asking the right questions to extract what you're envisioning, then structuring it into a PRD ready for a team to execute.
/product-brief [initial idea]Examples:
/product-brief Add a notification system to our app/product-brief Build a customer feedback portal/product-brief Create an onboarding flow for new users/product-brief (prompts you for the idea)If no idea is provided: Ask: "What product or feature are you thinking about?"
If idea is provided: Start with whatever the user provides:
Display:
## Initial Idea
[User's description]
---
**Next:** I'll ask a few questions to understand this better.Important: Ask questions conversationally, not as a survey. 2-3 questions at a time, then wait for answers before asking more.
Question Strategy:
Round 1 (Critical Context):
Round 2 (Constraints & Scope): Based on Round 1 answers, ask about:
Round 3 (User Experience):
Round 4 (Success & Validation):
Adaptive questioning: If user mentions stakeholders, budget, or other context early, adjust questions accordingly. Don't ask what you already know.
After each round, acknowledge answers briefly and transition naturally:
"Got it. That helps me understand [X]. A few more questions about [Y]..."
Before moving forward, confirm you captured the vision correctly:
## What I Heard
**The Problem:**
[Synthesized problem statement]
**Target Users:**
[Who this is for]
**Core Value:**
[The main benefit/outcome]
**Key Constraints:**
[Timeline, technical, scope boundaries]
**Assumptions to Validate:**
[Things we're assuming but should test]
---
**Does this capture your vision? Type "yes" to continue or correct anything above.**If user corrects, update and re-confirm.
User triggers with: spec doc or create spec
Generate structured product spec:
# Product Spec: [Feature/Product Name]
**Date:** YYYY-MM-DD
**Owner:** [User's name]
**Status:** Draft
---
## Executive Summary
[2-3 sentence pitch: what this is and why it matters]
---
## Problem Statement
### Current Situation
[What exists today]
### Pain Points
- [Specific pain 1]
- [Specific pain 2]
- [Specific pain 3]
### Impact of Inaction
[What happens if we don't build this]
---
## Target Audience
### Primary Users
[Who will use this most]
### Secondary Users
[Who else benefits]
### User Characteristics
- [Key trait 1]
- [Key trait 2]
- [Key trait 3]
---
## Solution Overview
[High-level description of what we're building]
---
## Key Features & Functionality
### Must Have (MVP)
1. **[Feature 1]**
- Description
- Why it's critical
2. **[Feature 2]**
- Description
- Why it's critical
### Should Have (Phase 2)
1. **[Feature 3]**
- Description
- Why it's valuable
### Nice to Have (Future)
1. **[Feature 4]**
- Description
- Why it's desirable
---
## Success Metrics
### Primary Metric
[The one number that matters most]
### Secondary Metrics
- [Metric 2]
- [Metric 3]
### Leading Indicators
[Early signals of success/failure]
---
## Assumptions & Risks
### Key Assumptions
1. [Assumption 1]
- How to validate: [Test method]
2. [Assumption 2]
- How to validate: [Test method]
### Risks
1. **[Risk 1]** — [Mitigation strategy]
2. **[Risk 2]** — [Mitigation strategy]
---
## Dependencies
### Technical
- [System/API/service dependency]
### Team
- [Who needs to be involved]
### External
- [Third-party dependencies]
---
## Out of Scope
Explicitly not included:
- [Thing 1]
- [Thing 2]
- [Thing 3]
---
## Open Questions
- [ ] [Question 1]
- [ ] [Question 2]
- [ ] [Question 3]
---
**Next Steps:**
- Type `prioritize` to rank features by effort/impact
- Type `design flows` to create detailed user flows
- Type `create prd` to generate final PRD
- Type `back` to revise anything aboveUser triggers with: prioritize
Create effort/impact matrix:
## Feature Prioritization
| Feature | Impact | Effort | Priority | Rationale |
|---------|--------|--------|----------|-----------|
| [Feature 1] | High | Low | P0 | [Why] |
| [Feature 2] | High | Medium | P0 | [Why] |
| [Feature 3] | Medium | Low | P1 | [Why] |
| [Feature 4] | Low | High | P2 | [Why] |
### Recommended MVP Scope
Based on high impact + reasonable effort:
1. [Feature 1]
2. [Feature 2]
3. [Feature 3]
**Estimated Effort:** [X weeks/sprints]
---
**Next:**
- Type `design flows` to create user flows
- Type `create prd` to generate final PRD
- Type `back` to revise specUser triggers with: design flows
Create detailed user flows and screen specs:
## User Flows & Screen Specifications
### Flow 1: [Primary User Journey]
**Entry Point:** [How user arrives]
**Steps:**
#### Step 1: [Screen Name]
**Layout:**
- [Header elements]
- [Main content area]
- [Actions/buttons]
**User Actions:**
- Click [X] → [Outcome]
- Enter [Y] → [Validation rules]
- Cancel → [State change]
**Navigation:**
- Success → [Next screen]
- Error → [Error state]
- Back → [Previous screen]
**Validation Rules:**
- [Field 1]: [Rules]
- [Field 2]: [Rules]
**States:**
- Default: [Description]
- Loading: [What user sees]
- Error: [Error message]
- Success: [Confirmation]
---
#### Step 2: [Next Screen]
[Same structure as Step 1]
---
### Flow 2: [Secondary Journey]
[Same structure as Flow 1]
---
**Next:**
- Type `create prd` to generate final PRD
- Type `back` to revise flowsUser triggers with: create prd or generate prd
Generate comprehensive PRD combining all previous phases:
# Product Requirements Document
## [Product/Feature Name]
**Author:** [User name]
**Date:** YYYY-MM-DD
**Status:** Draft
**Last Updated:** YYYY-MM-DD
---
## Document Control
| Version | Date | Author | Changes |
|---------|------|--------|---------|
| 0.1 | YYYY-MM-DD | [Name] | Initial draft |
---
## Executive Summary
[2-3 paragraphs covering: what, why, who, success]
---
## Background & Context
### Current State
[What exists today]
### Problem Statement
[The problem we're solving]
### Opportunity
[Why now, why us]
---
## Goals & Success Metrics
### Primary Objective
[The main goal]
### Success Metrics
**Primary:**
- [Metric 1]: [Target]
**Secondary:**
- [Metric 2]: [Target]
- [Metric 3]: [Target]
**Leading Indicators:**
- [Early signal 1]
- [Early signal 2]
---
## Target Users
### Primary Audience
[Detailed description]
### Use Cases
1. **[Use Case 1]**
- As a [user type]
- I want to [action]
- So that [benefit]
2. **[Use Case 2]**
- As a [user type]
- I want to [action]
- So that [benefit]
---
## Solution Overview
[Comprehensive description of what we're building]
---
## Functional Requirements
### Must Have (P0)
#### Requirement 1: [Name]
- **Description:** [What it does]
- **Acceptance Criteria:**
- [ ] [Criterion 1]
- [ ] [Criterion 2]
- [ ] [Criterion 3]
- **User Story:** As a [X], I want [Y], so that [Z]
#### Requirement 2: [Name]
[Same structure]
### Should Have (P1)
[Same structure as Must Have]
### Nice to Have (P2)
[Same structure as Must Have]
---
## User Experience
### User Flows
[Reference to flows from Phase 6, or create if skipped]
### Key Screens
[High-level screen descriptions]
### Interaction Patterns
[How users interact with the feature]
---
## Technical Requirements
### Performance
- [Requirement 1]
- [Requirement 2]
### Security
- [Requirement 1]
- [Requirement 2]
### Integration Points
- [System 1]: [What needs to connect]
- [System 2]: [What needs to connect]
### Data Requirements
- [What data is collected]
- [Where it's stored]
- [How it's used]
---
## Design Requirements
### Visual Design
- [Style guide compliance]
- [Responsive requirements]
- [Accessibility standards]
### Content Requirements
- [Copy needs]
- [Translation needs]
- [Asset requirements]
---
## Dependencies & Constraints
### Dependencies
- **Technical:** [List]
- **Team:** [Who needs to be involved]
- **External:** [Third parties]
### Constraints
- **Timeline:** [Dates/milestones]
- **Budget:** [If applicable]
- **Technical:** [Platform limitations]
---
## Assumptions & Risks
### Assumptions
1. [Assumption 1]
- **Validation method:** [How to test]
- **Impact if wrong:** [Consequence]
2. [Assumption 2]
- **Validation method:** [How to test]
- **Impact if wrong:** [Consequence]
### Risks
| Risk | Likelihood | Impact | Mitigation |
|------|------------|--------|------------|
| [Risk 1] | High/Med/Low | High/Med/Low | [Strategy] |
| [Risk 2] | High/Med/Low | High/Med/Low | [Strategy] |
---
## Out of Scope
Explicitly not included in this version:
- [Item 1] — [Why/when it might be included]
- [Item 2] — [Why/when it might be included]
- [Item 3] — [Why/when it might be included]
---
## Open Questions
- [ ] [Question 1] — Owner: [Name], Due: [Date]
- [ ] [Question 2] — Owner: [Name], Due: [Date]
- [ ] [Question 3] — Owner: [Name], Due: [Date]
---
## Timeline & Milestones
| Milestone | Target Date | Status |
|-----------|-------------|--------|
| PRD Complete | [Date] | In Progress |
| Design Complete | [Date] | Not Started |
| Dev Complete | [Date] | Not Started |
| QA Complete | [Date] | Not Started |
| Launch | [Date] | Not Started |
---
## Stakeholders
| Name | Role | Involvement |
|------|------|-------------|
| [Name] | [Role] | [What they do] |
| [Name] | [Role] | [What they do] |
---
## Appendix
### Research
[Link to user research, competitive analysis, etc.]
### Design Mockups
[Links to designs when available]
### Technical Specs
[Links to technical documentation]
---
**Document Status:** Ready for Review
**Next Actions:**
- [ ] Review with stakeholders
- [ ] Refine based on feedback
- [ ] Get approval to proceed
- [ ] Hand off to design/engineering
---
*This PRD was generated using the /product-brief command. Update as needed.*After generating the PRD:
Save the document:
04-Projects/[Product Name]/04-Projects/[Product Name]/PRD.mdCreate person pages (if stakeholders mentioned):
People/Internal/ or People/External/Link to 03-Tasks/Tasks.md:
Confirm completion:
## ✅ PRD Created
**Saved to:** `04-Projects/[Product Name]/PRD.md`
**Next Steps:**
1. Review and refine the PRD
2. Share with stakeholders for feedback
3. Use `/project-health` to track progress
4. Create tasks in 03-Tasks/Tasks.md when ready to execute
**Want to:**
- Revise any section → Just tell me what to change
- Create tasks from this PRD → Say "create tasks"
- Share with stakeholders → I can draft an emailAt any phase, users can:
back or previous — Return to previous phaseskip to prd — Jump directly to final PRDrevise [section] — Edit specific sectionstart over — Begin from scratchsave — Save current progressGood:
"Interesting. If this is for enterprise customers, how do we handle single sign-on? Or is that something we're punting to Phase 2?"
Bad:
"Question 7: Please describe your authentication strategy."
User: /product-brief Add notifications to our app
Dex:
## Initial Idea
Add notifications to our app
---
Great, let's flesh this out. A few questions to start:
1. What type of notifications are we talking about — push notifications, in-app alerts, email, or all three?
2. What specific events should trigger notifications?
3. Who are these notifications for — all users, or specific roles?User: "Push notifications for now. We want to notify sales reps when a lead takes an action in the product."
Dex:
Got it — push notifications for sales reps when leads are active. That helps narrow it.
A few more questions:
1. What actions count as notification-worthy? (e.g., login, feature usage, upgrade intent)
2. Should there be any filtering or preferences? Like "only notify me about my accounts"?
3. What's the business outcome we're driving here — faster response time, more engagement, closing deals faster?[Conversation continues through phases until PRD is complete]
Use /product-brief when:
Don't use it for:
The PRD isn't set in stone. After creation:
Dex will update the PRD file directly and maintain version history.
Before finalizing the PRD, verify:
If any are missing, prompt user to fill gaps before finalizing.
Call the mark_feature_used tool on the dex-analytics MCP server with product-brief. This ticks the feature's box in System/usage_log.md, which is what /dex-level-up reads to recommend features that have not been tried. It writes locally and sends nothing, so it runs whether or not analytics is enabled.
Analytics (Silent):
Call track_event with event_name product_brief_created.
This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".
© davekilleen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/product-brief of davekilleen/Dex.
Open the folder on GitHubat commit d0ffc6b
Product Brief 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Product Brief this skilldavekilleen/Dex | 494 | — | ~4.3k | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ralph Tui Create Beadssubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Trellis Brainstormanjiemo/SunnyBeach | 178 | 7 repos | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Ralph Tui Create Beads Rustsubsy/ralph-tui | 2.5k | 1 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Ralph Tui Create JSONsubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT |
automazeio/ccpm
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.
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
subsy/ralph-tui
Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.
jamesrochabrun/skills
Generate comprehensive Product Requirements Documents (PRDs) for product managers.
davekilleen/Dex
This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications.
davekilleen/Dex
Adopt a full published Heydex profile by handle ('set me up like @davekilleen').
davekilleen/Dex
Package one workflow — how you use Dex for a specific job — into a shareable DexDiff methodology doc.
davekilleen/Dex
Expert guidance for creating, writing, and refining Claude Code Skills.
davekilleen/Dex
Report a Dex bug to the Dex team with zero homework — Dex investigates locally, builds a privacy-safe report, shows it to you (or auto-sends if you've chosen that), and tracks the ticket until it's…
davekilleen/Dex
This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style.
Categories
Extract a product idea through guided questions and generate a PRD. Product Brief is an agent skill from davekilleen/Dex. Extract a product idea through guided questions and generate a PRD.
Product Brief fits situations like: the user says write a PRD; spec this feature; turn this idea into a brief.
Run `npx skills add davekilleen/Dex --skill product-brief -a claude-code`. Or copy the skill folder (.agents/skills/product-brief in davekilleen/Dex) into .claude/skills/product-brief in your project. Claude Code loads it when a task matches its description.
Run `npx skills add davekilleen/Dex --skill product-brief -a codex`. Or copy the skill folder (.agents/skills/product-brief in davekilleen/Dex) into .agents/skills/product-brief in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davekilleen/Dex --skill product-brief -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-brief, .gemini/skills/product-brief, .github/skills/product-brief and .opencode/skills/product-brief in your project.
SKILL.md names no scripts, command-line tools or credentials: Product Brief is instructions for the agent only.
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.
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.
Product Brief is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Product Brief: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
davekilleen (a GitHub user) maintains it in davekilleen/Dex, which has 494 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on October 9, 2026.
Source: davekilleen/Dex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.