write-adr
Skill0 starsChanged 15 days agoMITView on GitHub
Write an architecture decision record for a choice that is hard to reverse. Use when you choose a stack, a vendor, a data model or a protocol.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- miruky/harness-sampletheir own version, first seen Nov 15, 2026
- connext-solutions/flowctltheir own version, first seen Nov 15, 2026
- LeonardoEnnes/ai-engineering-toolkittheir own version, first seen Nov 8, 2026
- adhamhaithameid/write-skillstheir own version, first seen Nov 8, 2026
- helmut-hoffer-von-ankershoffen/heinzeltheir own version, first seen Nov 8, 2026
- 0xdeafcafe/skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use code-review.
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.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- HexamindOrganisation/hexgate★ 25same name
- helmut-hoffer-von-ankershoffen/heinzel★ 2same name
- adhamhaithameid/write-skills★ 1same name
- connext-solutions/flowctl★ 1same name
- daniel-kindl/dkstack★ 1same name
- fabianmagrini/skills★ 1same name
- MaheshAwasare/claude-skills-pro★ 1same name
- tejastn10/workbench★ 1same name
- 0xdeafcafe/skills★ 0same name
- dr-zog/plumbline★ 0same name
5 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 repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- architecture-reviewSkill
- bootstrap-projectSkill
- capture-screenshotsSkill
- customizeSkill
- deliver-featureSkill
- design-reviewSkill
- docs-upkeepSkill
- fix-bugSkill
- handoffSkill
- implementSkill
- leadSkill
- log-decisionSkill
- refine-requirementsSkill
- release-readinessSkill
- reproduce-in-worktreeSkill
- security-auditSkill
- ship-prSkill
- start-taskSkill
- sync-branchSkill
- threat-modelSkill
- verify-featureSkill
- vet-dependencySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
4
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 17
Ask the owner: when the choice is a product or business trade-off: present the options with your recommendation first.
- Distinctive: line 20
Add a row to the Decision Log pointing to the ADR.
- Distinctive: line 21
Add the rules it implies to AGENTS.md.
- Distinctive: line 23
When superseding, mark the old ADR *Superseded by NNNN* without changing its body.
“Common” is measured: kept by at least 6 in 10 of the 14 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
Write an ADR
Playbook files named here: when the project has its own copy at
.playbook/local/<same path>, use that copy instead.
Decision: $ARGUMENTS
- Check it needs an ADR (
${CLAUDE_PLUGIN_ROOT}/principles/03-adrs-and-decisions.md). If it's easy to reverse, log it in the Decision Log instead (log-decision). - Read what exists:
docs/adr/(the next number, related ADRs, ones this supersedes), the Decision Log, and the PRD requirements involved. - Gather the forces: requirements with ids, constraints (platform, budget and free tiers, team, compliance), and what's already decided.
- Find at least two real options. For each, check the current docs and versions (not memory): maturity, adoption, licence, cost, lock-in, and fit with the stack. If the answer depends on numbers you don't have (performance, memory, cost), propose a time-boxed spike with what it will measure, and stop there.
- Ask the owner when the choice is a product or business trade-off: present the options with your recommendation first. Technical choices with a clear winner: recommend, and let the owner confirm in review.
- Write
docs/adr/NNNN-kebab-title.mdfrom${CLAUDE_PLUGIN_ROOT}/templates/adr.md. Status is Proposed until the owner accepts it; then Accepted with the date and who decided. - Follow through:
- Add a row to the Decision Log pointing to the ADR.
- Add the rules it implies to
AGENTS.md. - File tickets for the "now we must" consequences.
- When superseding, mark the old ADR Superseded by NNNN without changing its body.
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.

