agentleFS
seancabalseseancabalse/agentic-playbook/skills/write-adr/SKILL.md

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

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.
  • GoogleSkill

    code-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

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
  1. Distinctive:

    Ask the owner: when the choice is a product or business trade-off: present the options with your recommendation first.

    line 17
  2. Distinctive:

    Add a row to the Decision Log pointing to the ADR.

    line 20
  3. Distinctive:

    Add the rules it implies to AGENTS.md.

    line 21
  4. Distinctive:

    When superseding, mark the old ADR *Superseded by NNNN* without changing its body.

    line 23

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. 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).
  2. Read what exists: docs/adr/ (the next number, related ADRs, ones this supersedes), the Decision Log, and the PRD requirements involved.
  3. Gather the forces: requirements with ids, constraints (platform, budget and free tiers, team, compliance), and what's already decided.
  4. 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.
  5. 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.
  6. Write docs/adr/NNNN-kebab-title.md from ${CLAUDE_PLUGIN_ROOT}/templates/adr.md. Status is Proposed until the owner accepts it; then Accepted with the date and who decided.
  7. 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.