adr-writing
Skill19 starsChanged 4 days agoApache-2.0View on GitHub
Use when the user asks for an ADR, or wants to record, revise, or replace an architecture decision.
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 3 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 8
Read ADR-FORMAT.md first. It holds the bar, the template, and the numbering.
- Distinctive: line 16
Start from the template: one to three sentences of context, choice, and reason.
- Distinctive: line 24
When new work contradicts an existing ADR, say so explicitly ("Contradicts ADR-0007, but worth reopening because…") rather than silently …
“Common” is measured: kept by at least 6 in 10 of the 3 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
ADR Writing
Read ADR-FORMAT.md first. It holds the bar, the template, and the numbering.
1. Decide
Test the decision against the three conditions in ADR-FORMAT.md: hard to reverse, surprising without context, the result of a real trade-off. Even when the user asked for an ADR, if any test fails, name the failed test and recommend no ADR. Write one only when all three pass or the user insists.
2. Write
Start from the template: one to three sentences of context, choice, and reason. Add an optional section only when it carries something a future reader needs.
Name a rejected alternative by its idea and why it lost, never by its interface. An agent that later finds a signature like undo_operation(id) in an ADR reads it as something to build.
3. Amend or supersede
Leave the old ADR's body as written. Set its Status to superseded by ADR-NNNN, and when only part of it changed, add one line under the title that says what still holds. Then search the other docs (specs, AGENTS.md, README) for the replaced names and update them.
When new work contradicts an existing ADR, say so explicitly ("Contradicts ADR-0007, but worth reopening because…") rather than silently overriding it.
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- marmelab/atomic-crm★ 1.4ksame name
- KhaledSaeed18/dotclaude★ 5same name
- Diviner-Dojo/agent_framework_template★ 4same 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 repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/on-demand/vercel-composition-patterns/AGENTS.mdAGENTS.md
- codebase-designSkill
- code-reviewSkill
- crwlSkill
- dev-browserSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- git-commitSkill
- grillingSkill
- implementSkill
- librarianSkill
- liteparseSkill
- prototypeSkill
- prSkill
- researchSkill
- simple-englishSkill
- skill-dietSkill
- tddSkill
- wizardSkill
- writing-for-agentsSkill
- architecture-scanSkill
- brandkitSkill
- broSkill
- cavemanSkill
- coding-standardsSkill
- design-taste-frontendSkill
- diagram-designSkill
- fable-safe-promptSkill
- grill-for-unknownsSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- high-end-visual-designSkill
- humanizerSkill
- i-have-adhdSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- implementation-orchestratorSkill
- improve-codebase-architectureSkill
- marpSkill
- minimalist-uiSkill
- oss-repo-reviewSkill
- pretty-mermaidSkill
- redesign-existing-projectsSkill
- reducing-entropySkill
- retroSkill
- rpiSkill
- sentrySkill
- setup-matt-pocock-skillsSkill
- setup-ts-deep-modulesSkill
- show-meSkill
- suggest-skillsSkill
- supervisorSkill
- teachSkill
- tech-specSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- The first 60 shown.
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.

