agentleFS
helmut-hoffer-von-ankershoffenhelmut-hoffer-von-ankershoffen/heinzel/.claude/skills/write-adr/SKILL.md

write-adr

Skill2 starsChanged 16 days agoMITView on GitHub

Record an architecture decision for Heinzelmännchen as an ADR in docs/adr. Use before a structural change (new module kind, let kind, head, dependency, process change), when a change contradicts an existing ADR, or when asked to document a decision.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-audit, handoff 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.
  • CloudflareSkill

    security-audit

    Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

  • 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

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 0

    Distinctive

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read docs/adr/README.md and the ADRs related to the decision.

    line 10
  2. Very specific:

    Do not edit the index table of docs/adr/README.md: it is generated.

    line 31

“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

The format is a trimmed MADR 4; docs/adr/0000-template.md is the source of truth.

  1. Read docs/adr/README.md and the ADRs related to the decision; ask the architect agent if unsure.
  2. Copy docs/adr/0000-template.md to docs/adr/NNNN-title-in-kebab-case.md with the next number; the title is # NNNN: Title that states the decision. Delete the template's comment.
  3. Front matter, flat key: value only: status: proposed, date: YYYY-MM-DD, optional decision-makers (roles, never names), supersedes / amends when the decision replaces or changes another ADR, and related for ADRs it builds on without changing them. For each ADR it amends or supersedes, add amends-NNNN: what it changes (a few words, no : or # inside); the index and both pages show it. Set implementation: planned; it becomes partial or built as code lands. Once a pull request builds the decision, add implemented-by: 123, 145 (PR numbers of the code, never the PR that only wrote the record); leave it out until then.
  4. Fill in, keeping it to a page or two:
    • Context and Problem Statement: forces and verified facts, sources linked.
    • Decision Drivers (optional).
    • Considered Options: the chosen one marked (chosen), each other one with why not. Never invent options.
    • Decision Outcome: one line Chosen option: **...**, because ..., then checkable statements.
    • Consequences (good and bad) and Confirmation: the enforcing mechanism in two sentences, no file lists (the test, lint rule, import-linter contract or CI job that fails when the decision is broken — grep that it exists), or "review only".
    • More Information (optional): related ADRs, research, open questions.
  5. Superseding or amending: set superseded-by: NNNN and status: superseded (or amended-by: NNNN) on the old ADR. Front matter is the only part of an accepted ADR that may change, plus a dated amendment note ("Amended YYYY-MM-DD: ...") at the end of More Information.
  6. Do not edit the index table of docs/adr/README.md: it is generated. Run make docs (in Heinzelmännchen) and commit the result; uv run pytest tests/unit/documentation_test.py checks template, index and links.
  7. Status stays proposed until a maintainer accepts it. Commit with docs(adr): ....

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.