requirements
Skill423 starsChanged 3 months agoMITView on GitHub
Writes the product requirements document (PRD) in root REQUIREMENTS.md as user stories with checkable outcomes. Use for a new product or a change to what it should do.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- Jakeschincariol/whale-skilltheir own version, first seen Nov 8, 2026
- marcusbelz/di2-starter-kittheir own version, first seen Oct 31, 2026
- jvalin17/agent-toolkittheir own version, first seen Oct 12, 2026
- ngthluu/my-ba-skillstheir own version, first seen Oct 9, 2026
- rizsotto/Beartheir own version, first seen Oct 8, 2026
- dewil/ai-toolkittheir own version, first seen Aug 25, 2026
Used with
Projects with it also use agent-browser.
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.
VercelSkillagent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
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
- rizsotto/Bear★ 6.5ksame name
- ptsilivis/autonomousguy★ 33same name
- Jakeschincariol/whale-skill★ 15same name
- aborroy/aiup-alfresco★ 14same name
- dewil/ai-toolkit★ 9same name
- dewil/claude-toolkit★ 9same name
- saitarrun/Devforge-ai★ 4same name
- digitaldreams/tuhin★ 3same name
- websublime/mister-anderson★ 3same name
- jvalin17/agent-toolkit★ 2same 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-reviewSkill
- architectureSkill
- codex-issue-coordinatorSkill
- html-docSkill
- improveSkill
- planSkill
- reviewSkill
- specSkill
- task-to-prSkill
- testSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Read the request, the existing REQUIREMENTS.md, and any research the user gave you.
- Distinctive: line 16
Ask the user about each product decision that is missing.
- Very specific: line 17
Write one user story for each thing a user needs to do, with a REQ-n ID and at least one "Done when" a person could check.
- Distinctive: line 18
Stop when the document is ready for review.
- Very specific: line 70
Keep existing REQ-n IDs. Never reuse or renumber them.
- Distinctive: line 71
Write from the user's side.
“Common” is measured: kept by at least 6 in 10 of the 12 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
Requirements
Fill in this template in root REQUIREMENTS.md. It is the PRD for the whole product; keep it current. One feature goes in a spec, technical decisions in architecture.
Process
- Read the request, the existing
REQUIREMENTS.md, and any research the user gave you. - Ask the user about each product decision that is missing. Give your recommended answer with each question. Look up facts in the repository instead of asking.
- Write one user story for each thing a user needs to do, with a
REQ-nID and at least one "Done when" a person could check. Include what the user sees when something fails or is denied. - Stop when the document is ready for review.
Template
# <Product> requirements
Status: Proposed | Accepted
## Problem and users
<Who has the problem, what goes wrong for them today, and the outcome they need.
Name each type of user once; the stories below use these names.>
## User stories
### REQ-1: <Short name>
As a <user>, I want to <action>, so that <benefit>.
Done when:
- <Observable result a person could check>
- <What the user sees when it fails or is denied>
### REQ-2: <Short name>
...
## Business rules
<Rules that hold across stories: permissions, limits, states, and what must never happen.>
## Constraints
<Required security, privacy, compatibility, and performance limits. Use numbers when known.
Mark unknown targets as open decisions.>
## Out of scope
<What this product does not do yet.>
## Success measures
<How to judge value after release, when there is evidence for a measure. Otherwise "None yet".>
## Open decisions
<Each unanswered question, your recommended answer, and what it blocks.>Rules
- Keep existing
REQ-nIDs. Never reuse or renumber them. - Write from the user's side. Leave out how it will be built, unless a technology is required.
- Label assumptions. Never invent research, targets, or rules.
Return
Report the path, the decisions made, and any blocking question.
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.

