product-analyst
Skill30 starsChanged 4 days agoApache-2.0View on GitHub
Analyzes ambiguous feature requests, clarifies business rules, and authors ultra-concise Product Requirements Documents (docs/<feature-name>/prd.md <= 70 lines) with standard User Stories (US-XX) and testable Acceptance Criteria (AC-XX).
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
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 14
SKIP: when the user prompt already defines clear scope/stories, or for bugfixes, refactors, chores, documentation updates, and purely …
- Distinctive: line 20
If business rules or boundaries remain genuinely ambiguous, ask concise option-based questions with clear trade-offs (never vague …
- Very specific: line 23
Create docs/<feature-name>/ and write docs/<feature-name>/prd.md (<= 70 lines hard cap) using the exact 4-section template in …
- Very specific: line 39
Antigravity: Use view_file/grep_search, align via ask_question when needed, and write docs/<feature-name>/prd.md.
“Common” is measured: kept by at least 6 in 10 of the 4 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 Analyst Skill
Overview
This skill converts underspecified feature requests into crisp, directly testable product specifications stored in docs/<feature-name>/prd.md (strictly capped at <= 70 lines, zero filler prose). Every PRD follows a fixed 4-section standard (Objective, Scope, User Stories, Acceptance Criteria & Edge Cases) so engineering and QA have exact US-XX -> AC-XX traceability.
When to Use
Capability-Gated Trigger Rules
- INVOKE ONLY IF business scope, user stories, or acceptance criteria are ambiguous or missing.
- SKIP when the user prompt already defines clear scope/stories, or for bugfixes, refactors, chores, documentation updates, and purely technical CLIs.
- Delegate Elsewhere: System schemas & ADRs ->
senior-architect-engineering; UI tokens & screens ->ui-ux-designer; TDD coding ->code-implementer.
Process
Phase 1: Context Check & Targeted Clarification
- Inspect existing routes, models, and
docs/(docs/specifications/if present) to avoid asking questions already answered by the codebase. - If business rules or boundaries remain genuinely ambiguous, ask concise option-based questions with clear trade-offs (never vague open-ended prompts).
Phase 2: Author Concise Standard PRD (docs/<feature-name>/prd.md, <= 70 lines)
Create docs/<feature-name>/ and write docs/<feature-name>/prd.md (<= 70 lines hard cap) using the exact 4-section template in references/prd-template.md:
## 1. Objective: 2–4 lines stating the concrete problem and measurable business outcome.## 2. Scope: CrispIn-ScopeandOut-of-Scopebullets preventing scope creep.## 3. User Stories: NumberedUS-01,US-02in strict standard format:- As a
<role>, I want<action>, so that<outcome>(or Como<rol>, quiero<acción>, para<beneficio>).
- As a
## 4. Acceptance Criteria & Edge Cases: NumberedAC-01,AC-02explicitly mapped toUS-XX(AC-01 (US-01)), written as directly testable Given/When/Then or crisp bullets covering validation, permissions, and boundary/failure cases.
Global Sync: If the workspace maintains docs/specifications/ or a global requirements index, update its links to keep documentation synchronized.
Usage
Example Prompts
- "Clarify scope boundaries for workspace invitations and write a concise
docs/workspace-invites/prd.md(<= 70 lines)." - "Extract
US-XXuser stories and testableAC-XXacceptance criteria for CSV report exports."
Host Execution
- Claude Code: Inspect context via
Read/Grep, clarify genuine gaps, and writedocs/<feature-name>/prd.md. - Antigravity: Use
view_file/grep_search, align viaask_questionwhen needed, and writedocs/<feature-name>/prd.md.
Red Flags
- ❌ Writing bloated PRDs (
> 70 lines), executive-summary fluff, or multi-page tables for straightforward features. - ❌ Invoking PRD authoring on bugfixes, refactors, chores, or prompts that already specify clear acceptance criteria.
- ❌ Writing untestable criteria ("must be fast and intuitive") or omitting
US-XX/AC-XXidentifiers andOut-of-Scopebullets. - ❌ Asking obvious questions answerable from repository code, or writing production source code directly.
Verification
docs/<feature-name>/prd.mdexists, is strictly<= 70 lines, and contains zero filler prose.- Uses the exact 4 sections from references/prd-template.md:
1. Objective,2. Scope,3. User Stories,4. Acceptance Criteria & Edge Cases. - Every story (
US-XX) uses As a / I want / so that (Como / quiero / para) format, and everyAC-XXmaps to aUS-XXwith testable validation/permission/edge rules. - Existing
docs/specifications/indexes synchronized if present.
References
- Concise Standard PRD Template (
<= 45 lines): references/prd-template.md
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- ncklrs/startup-os-skills★ 51same name
- RizwanZafaris/product-manager-OS★ 4same name
- notdaran/pd-agent-skills★ 1same name
- gsulamanidzebdoge/product-analyst★ 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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-challengerSkill
- agent-metricsSkill
- bigquery-query-optimizationSkill
- blackbox-testerSkill
- build-and-ci-gatesSkill
- cdc-scd-patternsSkill
- code-criticSkill
- code-implementerSkill
- code-smells-expertSkill
- commit-expertSkill
- compliance-verifierSkill
- context-captureSkill
- context-restoreSkill
- database-migration-expertSkill
- design-spec-expertSkill
- documentation-expertSkill
- flutter-architecture-decisionsSkill
- flutter-performance-profilingSkill
- flutter-release-engineeringSkill
- flutter-review-checklistSkill
- flutter-senior-orchestrationSkill
- flutter-test-strategySkill
- flutter-upgrade-migrationSkill
- gcp-data-engineeringSkill
- guidelines-karpathySkill
- loop-engineeringSkill
- performance-scalabilitySkill
- pull-request-expertSkill
- python-expertSkill
- qa-testerSkill
- refactoring-code-expertSkill
- repo-researchSkill
- security-auditSkill
- senior-architect-engineeringSkill
- senior-dev-orchestratorSkill
- sql-query-optimizationSkill
- test-driven-developmentSkill
- testing-expertSkill
- ui-ux-designerSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

