define
Skill2 starsChanged 38 days agoMITView on GitHub
Turn an idea or a ticket into a spec ready to build, with the problem, the scope, the code it touches, acceptance criteria as Gherkin scenarios, and the decisions to make first. Use to define, spec, scope, refine or plan a feature, task or idea, or to write acceptance criteria before work starts.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- vladcheck/agentictheir own version, first seen Nov 8, 2026
- withpiper/pipekittheir own version, first seen Nov 8, 2026
- vladcheck/skillstheir own version, first seen Nov 1, 2026
- sorawit-w/agent-skillstheir own version, first seen Nov 1, 2026
- marcuskrogh/skillstheir own version, first seen Oct 13, 2026
- Trevoke/org-gtd.eltheir own version, first seen Oct 8, 2026
Used with
Projects with it also use build, verify and 1 more.
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.
Microsoft AzureSkillbuild
Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.
Also in 3 projects that use this
Microsoft AzureSkillverify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 3 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- Trevoke/org-gtd.el★ 485same name
- SensorsIot/Embedded-AI-Harness★ 235same name
- zz41354899/goodux-skills★ 30same name
- saleh-alhaddad/itqan-engineering★ 10same name
- withpiper/pipekit★ 6same name
- sorawit-w/agent-skills★ 2same name
- marcuskrogh/skills★ 1same name
- vladcheck/agentic★ 1same name
- vladcheck/skills★ 1same name
- Practice019/agent-skills★ 0same name
1 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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- atlassianSkill
- auditSkill
- code-qualitySkill
- commit-expertSkill
- create-issueSkill
- create-prSkill
- debugSkill
- deliverSkill
- final-reviewSkill
- gherkinSkill
- githubSkill
- handoffSkill
- plainSkill
- second-opinionSkill
- senior-technical-writerSkill
- testingSkill
- triageSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
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 22
Check it is new: Search the tracker, open and closed, and the code and docs: it may already be supported, planned or rejected.
- Distinctive: line 25
Specify: Write the acceptance criteria as Gherkin scenarios: the main path, then each edge and failure that matters.
“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
Define
A spec is the problem, scope, code, acceptance criteria and open decisions of one piece of work. It is done when someone who never saw the request could build it and know when it is finished.
Rules
- Follow project conventions. Take domain terms from the code and docs, and issue kinds and issue requirements from the tracker templates and contribution guidance.
- Start from the problem. Name who has the problem and what they cannot do today. A requested solution, such as "add a button", is one option, not the task.
- Read before you specify. Link every claim about the code at a commit. Mark what you could not check as an assumption.
- Ask, never pick. A choice that neither the request nor the code settles is a decision for the user or a maintainer: state the options and their trade-offs.
- Stop at the spec. Define does not build; it ends with a spec the user approves.
Flow
- Read the request whole, comments included. Read a ticket from a PM, client or support as triage: non-technical says.
- Check it is new. Search the tracker, open and closed, and the code and docs: it may already be supported, planned or rejected. If so, stop and report it. Skip what triage already checked.
- Note the gaps: what the request leaves open about the problem, who has it, scope and constraints. Build on stated assumptions, and keep the questions for the review.
- Map the code. Trace where the change lands: the entry points, the modules it touches, the nearby patterns to follow, and the behaviour that must not change. Assess design options with code-quality's design rules.
- Specify. Write the acceptance criteria as Gherkin scenarios: the main path, then each edge and failure that matters. List the non-goals, the risks and the open decisions.
- Size. One issue when the work is one outcome a reviewer can check. Otherwise split it at the size the user picks (create-issue: size), with a decision issue per open question; issues that reach one goal in order are a program (create-issue: programs).
- Review. Show the spec with its questions, and the issue drafts the caller asked for, written with create-issue. When the spec adds acceptance a ticket lacks, show the whole edited body in a scratch file outside the tree. Wait for one approval, then publish what the user approves through the tracker's skill.
Output
<title>
Problem: <who cannot do what today>
Scope: <what changes> Non-goals: <what does not>
Code: <entry points and modules, linked at a commit>
Acceptance:
```gherkin
<scenarios>
```
Risks: <what could go wrong> | none
Decisions: <question: options and trade-offs> | none
Assumptions: <claims not verified> | none
Size: one issue | <n> issues sized finding, pr or outcome | program of <n> issues sized finding, pr or outcomeDoes 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.

