product-spec
Skill0 starsChanged 6 days agoMITView on GitHub
Write a product requirements document (PRD) or feature spec. Use when the user describes a feature or product idea and asks for a spec, PRD, requirements, user stories, "scope this", or something to hand to engineers or designers.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- idaibin/skillstheir own version, first seen Nov 8, 2026
- fainir/agent-harnesstheir own version, first seen Nov 1, 2026
- edilson-silva/codridetheir own version, first seen Oct 15, 2026
- matiopala/skillstheir own version, first seen Oct 15, 2026
- arfar-x/agent-skillstheir own version, first seen Oct 13, 2026
- gonimar/claude-web-studiotheir own version, first seen Sep 27, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- firatcand/founder-skills★ 37same name
- Hassaan146/claude-skills★ 18same name
- arfar-x/agent-skills★ 14same name
- yasunori0418/skills★ 9same name
- idaibin/skills★ 6same name
- gonimar/claude-web-studio★ 4same name
- levinchang/productdesign-skills★ 4same name
- vndee/engineering-skills★ 3same name
- edilson-silva/codride★ 2same name
- matiopala/skills★ 2same name
3 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 repository24 other files it gives its agents.
- api-docsSkill
- changelogSkill
- ci-failure-fixSkill
- code-reviewSkill
- commit-messageSkill
- competitor-analysisSkill
- data-analystSkill
- debug-detectiveSkill
- dependency-upgradeSkill
- dockerizeSkill
- email-replierSkill
- eval-promptSkill
- incident-postmortemSkill
- meeting-notesSkill
- migration-safetySkill
- pr-descriptionSkill
- readme-writerSkill
- refactor-safelySkill
- research-briefSkill
- security-checkSkill
- seo-articleSkill
- sql-helperSkill
- support-replySkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Non-functional: only those that matter here: performance target, privacy/personal data, security, accessibility, localisation, analytics …
- Distinctive: line 39
No feature without a problem behind it.
- Distinctive: line 41
If the idea does not hold up (no clear user, problem already solved by an existing feature), say so before writing the spec.
“Common” is measured: kept by at least 6 in 10 of the 11 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 spec
1. Clarify (max 3 questions, only if the answer changes the spec)
Who has the problem, what triggers it, and what "done" looks like. If the user wants a draft now, proceed and mark guesses as assumptions.
2. Separate facts from assumptions
Everything the user told you or that is in provided docs is a fact. Everything else is (assumption). Never invent user research, quotes, usage numbers, revenue impact or baselines. A metric without a known baseline says "baseline: to measure".
3. Write one page
Problem: who has it, when, what it costs them today (time, money, errors). Evidence only if provided.
Users: primary user and the job they are trying to get done. Secondary users only if they act in the flow (admin, approver).
Solution (smallest version that solves the problem): user stories, "As a <user>, I can <action> so that <outcome>." 3-7 stories. Each story has acceptance criteria:
- Given
<state>, when<action>, then<observable result>.
Edge cases: empty states, errors, permissions (who cannot do this), limits (large inputs, many items), concurrent edits, undo/delete, existing data migration.
Non-functional: only those that matter here: performance target, privacy/personal data, security, accessibility, localisation, analytics events to track.
Out of scope: mandatory. What this version will not do, including obvious next features.
Success metric: one primary metric, target, time window, how it is measured. One guardrail metric that must not get worse.
Dependencies and risks: other teams, APIs, legal, data needed.
Open questions: each with a suggested owner.
Rough plan: milestones in order (e.g. internal beta -> 10% rollout -> GA). Dates only if the user gave a deadline.
Rules
- Describe behaviour, not implementation, unless the user asks for technical design.
- No feature without a problem behind it; if one appears, move it to Out of scope or Open questions.
- Plain language, no "seamless", "robust", "leverage".
- If the idea does not hold up (no clear user, problem already solved by an existing feature), say so before writing the spec.
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.