intent-template
Skill4 starsChanged 30 days agoMITView on GitHub
Turn an idea, ticket or incident into this organization's intent.md format. Use when someone describes a problem or feature they want, asks to "write an intent", "capture this idea", or when a monitoring finding must be written up for triage.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- imsungbin/ai-native-sdlc-playbooktheir own version, first seen Sep 3, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- imsungbin/ai-native-sdlc-playbook★ 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- brand-guidelinesSkill
- compliance-policySkill
- intent-templateSkill
- secure-api-reviewSkill
- security-policySkill
- ux-standardsSkill
- brand-guidelinesSkill
- compliance-policySkill
- secure-api-reviewSkill
- security-policySkill
- ux-standardsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 22
Stop asking when the answers stop changing the document.
- Very specific: line 26
Create the folder intent/NNNN-short-slug/ using the next free number.
- Distinctive: line 27
Keep the originator's vocabulary.
- Distinctive: line 28
Put anything uncertain under Open questions, never as an assumption in another section.
- Very specific: line 33
Every section is filled or explicitly marked none.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing an intent.md
Owner: <product operations lead> · Source of truth: intent/0000-template/intent.md
An intent is a short proto-spec written in the originator's own words. It says what is wanted, why, and under which constraints. It does not design the solution.
Before writing
Interview the originator until you can fill every section. Ask one question at a time, the way an analyst would:
- Who is affected today, and what can't they do?
- What does "better" look like, and how would we notice it?
- What is explicitly out of scope?
- Which systems, data and teams are touched?
- Which constraints are fixed (regulation, budget, dates, existing auth, data classes)?
Stop asking when the answers stop changing the document.
Writing it
- Copy the structure of
intent/0000-template/intent.mdexactly; keep the frontmatter keys. - Create the folder
intent/NNNN-short-slug/using the next free number. - Keep the originator's vocabulary. Do not add solutions, estimates or technology choices.
- Put anything uncertain under Open questions, never as an assumption in another section.
- Set
source:toidea,ticket(withrecord_id) orincident(with the alert/incident id). - Show the draft to the originator and apply their corrections before anything is committed.
Done when
- Every section is filled or explicitly marked
none. - The originator confirmed the draft.
- It is committed (or opened as a PR) so the product owner can accept or close it.
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.