product
Skill2 starsChanged 6 months agoMITView on GitHub
Feature design workflow — transform raw feature inputs (ideas, research, stakeholder requests, competitive analysis) into a structured PRD or feature brief. Applies product-manager role. Produces PRD, user stories, acceptance criteria, success metrics, and updates FEATURES.md. First step in the planning chain, precedes architecture skill and plan skill. Includes mandatory multi-reviewer feedback loop with product-manager, marketing-strategist, content-writer, and seo-engineer.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- mahirhacks/mstacktheir own version, first seen Nov 16, 2026
- fatihkan/baditheir own version, first seen Nov 16, 2026
- Mark-Life/agent-skillstheir own version, first seen Nov 10, 2026
- Astatide1337/Skillstheir own version, first seen Nov 8, 2026
- PeterPartridge/CooperativeAICodingtheir own version, first seen Nov 8, 2026
- gabros20/product-skilltheir own version, first seen Nov 1, 2026
Used with
Projects with it also use review and research.
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.
SentrySkillreview
Fixture review skill.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- nitinjain999/platform-skills★ 71same name
- fatihkan/badi★ 8same name
- malinskibeniamin/skills★ 4same name
- Mark-Life/agent-skills★ 4same name
- websublime/mister-anderson★ 3same name
- PeterPartridge/CooperativeAICoding★ 2same name
- tikhomirovv/agents-knowledge★ 2same name
- Astatide1337/Skills★ 1same name
- donatassimkus/claude-ai-skills★ 1same name
- gabros20/product-skill★ 1same name
6 more not listed
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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-skillsSkill
- analyze-localSkill
- analyze-prodSkill
- analyzeSkill
- architectureSkill
- asset-validationSkill
- blog-postSkill
- bugfixSkill
- cloud-platformsSkill
- code-reviewSkill
- content-creationSkill
- context-engineeringSkill
- create-prSkill
- deployment-proceduresSkill
- deploy-productionSkill
- deploy-stagingSkill
- docsSkill
- feature-devSkill
- geo-writerSkill
- humanizerSkill
- infra-changeSkill
- marketing-operationsSkill
- marketingSkill
- ml-pipelineSkill
- planSkill
- pre-commitSkill
- project-initSkill
- prompt-engineeringSkill
- qaSkill
- releaseSkill
- run-testsSkill
- security-scanSkill
- seo-reviewSkill
- social-media-managerSkill
- test-localSkill
- test-strategySkill
- ui-ux-designSkill
- worktree-isolationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read AGENTS.md at the project root to identify:
- Very specific: line 21
If the project has a FEATURES.md, read it for the current feature registry.
- Distinctive: line 28
Read every provided document thoroughly
- Distinctive: line 29
If the user provides a verbal description only — proceed to Step 2 to structure it through discovery
- Distinctive: line 44
If critical signals are missing (no clear problem statement, no target user) — ask before proceeding.
- Distinctive: line 56
If evidence is weak — flag this as a risk.
- Distinctive: line 62
Job-to-be-Done: When [situation], I want to [motivation], so I can [outcome]
- Distinctive: line 104
Only include categories relevant to this feature.
- Distinctive: line 108
Write acceptance criteria for every Must-have and Should-have requirement:
- Distinctive: line 110
Use Given/When/Then format for behavioral criteria
- Distinctive: line 258
After the PRD/brief is approved:
- Very specific: line 260
If FEATURES.md does not exist — create it at the project root
- Distinctive: line 261
Add or update the feature entry:
“Common” is measured: kept by at least 6 in 10 of the 14 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
Feature Design
Transform raw feature inputs into structured product documentation. This is the product design phase — no code, architecture, or engineering decisions are made here. Output feeds into the architecture skill for technical design and the plan skill for implementation planning.
Apply product-manager role for all steps below.
0. Gather Context
Read AGENTS.md at the project root to identify:
- Product description and domain
- Existing features and modules (to avoid duplication and understand scope)
- Tech stack constraints (affects feasibility assessment)
- Team structure (affects user story assignment)
If the project has a FEATURES.md, read it for the current feature registry.
1. Receive Feature Inputs
Gather all available resources describing the feature:
- Accepted inputs: idea brief, user research, customer feedback, support tickets, competitive analysis, stakeholder request, verbal description, market data, analytics report
- Read every provided document thoroughly
- If the user provides a verbal description only — proceed to Step 2 to structure it through discovery
Extract Raw Signals
From the provided inputs, extract and organize:
| Signal | Source | Notes |
| Problem | [what pain exists, for whom] | [evidence or assumption] |
| Opportunity | [what business value] | [data points] |
| User segments | [who needs this] | [ICP/persona indicators] |
| Competitive context | [how others solve it] | [differentiation angle] |
| Constraints | [timeline, budget, technical, regulatory] | [hard vs soft] |
| Existing assets | [related features, prior art, dependencies] | [links/refs] |
If critical signals are missing (no clear problem statement, no target user) — ask before proceeding. Do not invent user needs.
2. Discovery and Framing
2a. Problem Validation
Define the problem with precision:
- Problem statement: One paragraph — who has the problem, what the problem is, why it matters now
- Evidence: Data points supporting the problem (usage metrics, support volume, churn correlation, user quotes, competitive pressure)
- Impact of inaction: What happens if we do nothing
If evidence is weak — flag this as a risk. Do not fabricate data.
2b. Target Users
Apply JTBD and ICP frameworks from Agent(product-manager):
- Job-to-be-Done: When [situation], I want to [motivation], so I can [outcome]
- ICP segments: Which customer profiles benefit most. Include triggers, buying signals, objections
- Personas (if useful): Name, role, goal, frustration. Keep lightweight — max 2 personas
2c. Scope Decision
Based on complexity, decide the deliverable type:
| Complexity | Signals | Deliverable |
| Small | Single service, < 1 week effort, clear solution | Feature Brief (abbreviated PRD) |
| Medium | Multi-component, 1–4 weeks, some unknowns | Full PRD |
| Large | Multi-service, 4+ weeks, significant unknowns, new capabilities | Full PRD + Spike/Discovery tasks |
| AI/Agent | LLM-powered, autonomous behavior, trust/safety concerns | Full PRD + Agent Contract + Eval Strategy |
Present the scope decision to the user for confirmation before proceeding.
3. Requirements Definition
3a. Functional Requirements
List requirements prioritized using MoSCoW:
- Must have: Core functionality — feature is useless without these
- Should have: Important but not blocking launch
- Could have: Nice-to-have, defer if constrained
- Won't have (this iteration): Explicitly excluded — prevents scope creep
Each requirement: one sentence, testable, outcome-focused. Never specify implementation — describe what, not how.
3b. Non-Functional Requirements
Identify relevant NFRs:
| Category | Requirement | Target |
| Performance | [e.g., response time] | [e.g., < 200ms p95] |
| Security | [e.g., auth, data protection] | [e.g., RBAC, PII encrypted] |
| Scalability | [e.g., concurrent users] | [e.g., 10K concurrent] |
| Accessibility | [e.g., WCAG level] | [e.g., WCAG 2.2 AA] |
| Compliance | [e.g., GDPR, SOC2] | [specific requirements] |
Only include categories relevant to this feature.
3c. Acceptance Criteria
Write acceptance criteria for every Must-have and Should-have requirement:
- Use Given/When/Then format for behavioral criteria
- Include happy path, edge cases, error states
- Include operational criteria: "no new errors in logs", "latency < Xms p95"
- Include security criteria: "unauthorized users receive 403", "PII not logged"
- Each criterion is independently testable
4. Success Metrics
Define how to measure feature success:
4a. Metric Framework
| Metric Type | Metric | Target | Measurement Method |
| Primary (North Star) | [e.g., activation rate] | [target value] | [how to measure] |
| Leading | [e.g., feature adoption D7] | [target value] | [how to measure] |
| Guardrail | [e.g., error rate, latency] | [must not exceed] | [how to measure] |
4b. Instrumentation Plan
- Events to track (name, properties, trigger)
- Dashboards to create or update
- Alerts to configure (guardrail breaches)
5. Risk Assessment
| Risk | Type | Impact | Likelihood | Mitigation |
| [description] | Technical / Business / Security / Compliance | High/Med/Low | High/Med/Low | [strategy] |
Mandatory risk categories to evaluate:
- Security threats (apply OWASP Top 10; add LLM Top 10 for AI features)
- Data handling risks (PII, secrets, retention)
- Backward compatibility and migration
- Dependency on external systems or teams
- User abuse scenarios
6. AI/Agent Addendum
Include this section only for AI-powered or agent features. Skip for standard features.
<agent_contract>
- Autonomy level: Assist (human decides) → Semi-auto (agent proposes, human approves) → Auto (agent acts independently)
- Allowed tools and permissions: Least privilege. List every tool/API the agent can access
- Confirmation gates: Which actions require human approval
- Failure modes: What happens when the agent fails, hallucinates, or exceeds scope
- Cost budget: Token/compute/API limits per operation
- Context pipeline: Consult
context-engineeringskill for context stack design, RAG pipeline, memory architecture, agent harness patterns, and production checklists - Eval strategy: Offline eval set (fixtures, synthetic + real cases), online monitoring (drift, failure rates) </agent_contract>
7. Compile Deliverable
Full PRD
Compile all sections into a structured PRD:
# PRD: [Feature Name]
## Problem Statement
[From Step 2a]
## Target Users
[From Step 2b — JTBD, ICP, personas]
## Scope and Non-Goals
[From Step 2c — what's in, what's explicitly out]
## Requirements
[From Step 3a — MoSCoW prioritized]
## Non-Functional Requirements
[From Step 3b]
## Acceptance Criteria
[From Step 3c]
## Success Metrics
[From Step 4]
## Risks and Mitigations
[From Step 5]
## Agent Contract
[From Step 6 — only for AI features]
## Rollout Strategy
- Phase 1: Internal / dogfood
- Phase 2: Beta (limited users, feature flag)
- Phase 3: GA (all users)
- Backward compatibility notes
- Feature flag name and configFeature Brief (for small scope)
Abbreviated format — single document:
# Feature Brief: [Feature Name]
**Problem**: [1–2 sentences]
**Users**: [target segment]
**JTBD**: When [situation], I want to [motivation], so I can [outcome]
## Requirements
[Must-have list only — max 5 items]
## Acceptance Criteria
[Given/When/Then for each requirement]
## Success Metric
[Single primary metric + target]
## Risks
[Top 1–3 risks with mitigations]Present the compiled deliverable to the user for review.
8. Multi-Reviewer Feedback Loop
The PRD or Feature Brief MUST pass a mandatory multi-reviewer cycle before handoff. Do not update FEATURES.md or hand off to the architecture skill / plan skill until every reviewer returns approved.
Reviewer Panel
Apply each role below in sequence, treating each as an independent reviewer with its own pass over the deliverable:
product-managerrole — problem framing, scope, requirements clarity, acceptance criteria testability, success metrics, risk coveragemarketing-strategistrole — positioning, target audience alignment, messaging, GTM fit, competitive differentiationcontent-writerrole — structure, terminology consistency, clarity, readabilityseo-engineerrole — feature naming searchability, keyword alignment, AI citability (GEO/AEO), discoverability hooks for public-facing surfaces
Cycle
- For each role, produce a findings report: Critical (must fix), Major (should fix, justify if waived), Minor (optional), plus an explicit verdict:
approved/approved-with-changes/rejected. Keep reports separate per role - Collect all four reports before editing
- Apply all actionable findings. Resolve conflicts with priority Critical > Major > Minor; on ties, product-manager > content-writer > marketing-strategist > seo-engineer. Record waivers with a one-line rationale
- Re-run the same four reviewer passes against the updated deliverable
- Loop until every reviewer returns
approvedwith zero remaining critical/major findings
Termination: pass when all four are approved. On divergence (findings not shrinking, mutually exclusive asks) — pause and ask the user to arbitrate. Max 5 cycles before escalation.
Record the review history at the bottom of the deliverable as a ## Review History section listing each cycle's reviewer verdicts and open issue counts.
9. Update FEATURES.md
After the PRD/brief is approved:
- If
FEATURES.mddoes not exist — create it at the project root - Add or update the feature entry:
- Name, one-line description
- Status:
planned - Link to PRD/brief in
features/directory
- Save the PRD/brief to
features/[feature-name].md(kebab-case)
10. Handoff
Guide the next step based on feature complexity:
| Complexity | Next Step |
| Small (brief) | Run plan skill directly — architecture is implicit |
| Medium (PRD) | Run architecture skill for technical design, then plan skill |
| Large (PRD + spikes) | Execute spikes first, then architecture skill → plan skill |
| AI/Agent (PRD + contract) | Run architecture skill with agent contract as input → plan skill |
Integration
- Input: Raw feature resources (ideas, research, feedback, stakeholder requests)
- Followed by:
architectureskill (technical design),planskill (work decomposition) - Roles:
product-managerrole (primary — owns PRD),marketing-strategist+content-writer+seo-engineerroles (Step 8 reviewers),solution-architectrole (consulted for feasibility) - Skills:
context-engineeringskill (context pipeline design, RAG, memory, agent harness — for AI/Agent features, Step 6) - Updates:
FEATURES.md,features/directory - Enables: Full planning chain:
productskill →architectureskill →planskill →feature-devskill
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.

