product-brief
Skill1 starsChanged 6 months agoMITView on GitHub
Generate a product-oriented summary of a project or initiative from GitHub data. Covers the problem, solution, complexity, user value, what's shipped, what's in progress, and what needs product attention. Use when ramping up a PM, presenting to leadership, or creating a shareable project overview.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- Job-Yang/jobbyang-ai-skillstheir own version, first seen Nov 6, 2026
- Job-Yang/jobyang-ai-skillstheir own version, first seen Nov 6, 2026
- MarkTripoli/skillstheir own version, first seen Nov 1, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
- rterakedis/leanwheel-skillstheir own version, first seen Oct 17, 2026
- emotixco/claude-skills-foundertheir own version, first seen Oct 7, 2026
Used with
Projects with it also use decision-log.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nandanosqlSkilldecision-log
Document product decisions with context, alternatives considered, rationale, and revisit criteria. Creates institutional memory that prevents re-litigating settled decisions.
Also in 3 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- emotixco/claude-skills-founder★ 796same name
- davekilleen/Dex★ 509same name
- Job-Yang/jobbyang-ai-skills★ 100same name
- Job-Yang/jobyang-ai-skills★ 100same name
- lglucas/ai-dev-operating-system★ 12same name
- MarkTripoli/skills★ 2same name
- rterakedis/leanwheel-skills★ 2same name
- tolgalogy/agentic-development-framework★ 2same name
- erik-kroon/skills★ 1same name
- vindreshsingh/engineering-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- setupSkill
- enrich-prsSkill
- epic-cleanupSkill
- epic-overviewSkill
- oncall-reviewSkill
- sprint-managementSkill
- sprint-statusSkill
- team-activitySkill
- team-data-syncSkill
- direct-report-prepSkill
- interview-analysisSkill
- interview-prepSkill
- peer-prepSkill
- project-statusSkill
- team-analysisSkill
- today-prioritiesSkill
- weekly-snippetSkill
- bus-factorSkill
- contribution-velocitySkill
- nine-boxSkill
- project-people-mapSkill
- review-cardsSkill
- review-cyclesSkill
- review-networkSkill
- team-health-reportSkill
- task-rolloverSkill
- context-checkSkill
- prep-my-daySkill
- initiative-breakdownSkill
- technical-deep-diveSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
When onboarding a PM or stakeholder to an existing initiative
- Distinctive: line 19
When you need a shareable doc that explains a project beyond the engineering details
- Very specific: line 44
Check Projects/ for existing project files, breakdowns, or ADRs
- Distinctive: line 45
Check recent dailies and People files for context, decisions, and discussion notes
- Distinctive: line 58
Don't lead with the solution.
- Distinctive: line 84
Keep it grounded in real use cases, not abstract "better security"
- Distinctive: line 133
Assume the reader has no context: Don't reference internal shorthand without explaining it.
- Distinctive: line 134
Be honest about complexity: Don't minimize hard problems.
- Distinctive: line 135
Separate "what's done" from "what's claimed.": If an issue says "shipped" but you can't find the PR, note that.
- Distinctive: line 137
Include real links: Every claim should have a traceable reference (issue, PR, discussion, code path).
- Distinctive: line 141
No speculation presented as fact: If you're inferring something, say so.
- Distinctive: line 142
Credit people: Use @mentions for who built what.
- Distinctive: line 144
Flag conflicts: If the issue description says one thing and the code says another, call it out.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Brief
Generate a product-oriented summary of a project or initiative. Designed to give someone with zero context a clear understanding of what the project does, why it's hard, what's shipped, and what still needs work. Written for a product or leadership audience, not a purely engineering one.
When to use
- "Write a product brief for [project]", "summarize [project] for my PM", "create a project overview"
- When onboarding a PM or stakeholder to an existing initiative
- When you need a shareable doc that explains a project beyond the engineering details
Prerequisites
- A GitHub issue, epic, or initiative tracking the project
- GitHub CLI (
gh) authenticated with org access - Vault project files (if any exist) for additional context
Process
Step 1: Gather raw material
From GitHub:
# The main tracking issue/epic
gh issue view {number} --repo {org}/{repo} --json title,body,comments,labels,assignees,createdAt
# Sub-issues and linked work
gh search issues --repo {org}/{repo} --json number,title,state,labels,assignees "label:{project-label}"
# Recent PRs related to the project
gh search prs --owner={org} --json number,title,repository,state,mergedAt "{project keyword}"From the vault:
- Check
Projects/for existing project files, breakdowns, or ADRs - Check recent dailies and People files for context, decisions, and discussion notes
From code (if deeper understanding needed):
- Launch explore agents to read relevant code, schema, and architecture
- Focus on: how does it actually work today? What's the real complexity?
Step 2: Organize into sections
Build the brief in this order:
The Problem
What's broken, missing, or inadequate today? Explain it so someone outside the team understands why this matters. Be concrete: "here's what happens today" → "here's why that's bad."
Don't lead with the solution. Start with the pain.
What [Project] Does
The solution, explained clearly. What changes? How does it work at a high level? Avoid implementation details here; save those for the technical deep dive.
Why It's Complicated
The honest version. What makes this harder than it sounds? Multiple code paths? Scale constraints? Cross-team dependencies? Design decisions that aren't settled? This section builds credibility and sets expectations.
Include sub-sections for distinct sources of complexity if needed.
What's Already Shipped
Concrete deliverables that are done. For each:
- What it is (one line)
- Why it mattered
- Current status (GA, staff-only, behind flag, etc.)
What's In Progress Now
Active work. For each workstream:
- What's being built and by whom
- Current state (PR links, issue links)
- Key decisions still open
Why This Matters to Users
Translate engineering work into user value. Group by audience:
- Persona 1: what they get, why they care
- Persona 2: different angle
- Keep it grounded in real use cases, not abstract "better security"
The Product Story
What's the narrative for announcing this? Not marketing copy, but the kernel of the story. What would a blog post headline say? What's the "before/after" that resonates?
What Needs Product Work
Explicitly call out where product decisions are needed:
- Naming and positioning
- Rollout strategy
- Public vs. internal scope
- UX decisions
- Pricing or packaging implications
Step 3: Add references
End with a structured references section:
## References
### Tracking
- [Initiative](url) — top-level epic
- [Sub-epic 1](url) — description
### Key Milestones
**Done:**
- [Issue/PR](url) — what it delivered
**Outstanding:**
- [Issue](url) — what's left, current status
### Design & Documentation
- [ADR](url) — topic (last updated: YYYY-MM-DD)
- [Discussion](url) — topicFlag stale docs (>6 months since last update) so the reader knows what might be outdated.
Step 4: Save and present
Save to the vault's Projects directory (or a Breakdowns subdirectory if the team uses one).
Present a summary to the user highlighting:
- Key narrative choices you made
- Anything you're uncertain about (conflicting info, stale sources)
- Gaps where you couldn't find data
Writing guidelines
- Assume the reader has no context. Don't reference internal shorthand without explaining it.
- Be honest about complexity. Don't minimize hard problems. The brief builds trust by showing you understand what's actually hard.
- Separate "what's done" from "what's claimed." If an issue says "shipped" but you can't find the PR, note that.
- Use plain language. This isn't an RFC. Write it like you're explaining to a smart person over coffee.
- Include real links. Every claim should have a traceable reference (issue, PR, discussion, code path).
Rules
- No speculation presented as fact. If you're inferring something, say so.
- Credit people. Use @mentions for who built what.
- Don't editorialize the product story. Present the narrative options; let the PM choose.
- Flag conflicts. If the issue description says one thing and the code says another, call it out.
- This is a living doc. Note the generation date and suggest when it should be refreshed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

