agentleFS
Sign inStart free
Luis85Luis85/agentic-workflow/.claude/skills/new-adr/SKILL.md

new-adr

Skill0 starsChanged 6 months agoMITView on GitHub

Create a new Architecture Decision Record under docs/adr/ from templates/adr-template.md, with the next free four‑digit number, the right filename, and the frontmatter pre‑filled. Use this skill when invoked via /adr:new "<title>" or whenever a non‑trivial, irreversible architectural decision needs to be recorded. For background on what counts as ADR‑worthy and how ADRs are governed, see docs/adr/README.md, templates/adr-template.md, and Article VIII — Plain Language of the constitution. On success, report: If a prior ADR was superseded, name it explicitly.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use new-spec and release.

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.
  • eugenelimSkill

    new-spec

    Use this skill when the user wants to start a new feature with a spec, or wants to write a spec for something they're about to build. Triggers on "new spec", "write a spec for X", "let's spec this out", "start a feature for…". Spec-driven development; the spec drives implementation. Do NOT use for cross-cutting proposals (use `new-rfc`) or recording decisions (use `new-adr`).

    Also in 5 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a new Architecture Decision Record under docs/adr/ from templates/adr-template.md, with the next free four‑digit number, the right …

    line 5
  2. Very specific:

    Use this skill when invoked via /adr:new "<title>" or whenever a non‑trivial, irreversible architectural decision needs to be recorded.

    line 7
  3. Distinctive:

    If this ADR supersedes a prior one,: update the prior ADR's frontmatter — only those two fields — in the same PR.

    line 37
  4. Very specific:

    Update docs/adr/README.md: if it maintains an index of ADRs.

    line 39
  5. Distinctive:

    If a prior ADR was superseded, name it explicitly.

    line 52
  6. Distinctive:

    Do not number an ADR by guessing — always derive from the directory listing.

    line 56
  7. Distinctive:

    Do not edit the body of any existing ADR.

    line 57
  8. Very specific:

    Do not mark a new ADR accepted without explicit human approval.

    line 58
  9. Distinctive:

    Do not delete superseded ADRs.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 12 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

new-adr — scaffold a new ADR

Purpose

Create a new Architecture Decision Record under docs/adr/ from templates/adr-template.md, with the next free four‑digit number, the right filename, and the frontmatter pre‑filled.

Use this skill when invoked via /adr:new "<title>" or whenever a non‑trivial, irreversible architectural decision needs to be recorded.

For background on what counts as ADR‑worthy and how ADRs are governed, see docs/adr/README.md, templates/adr-template.md, and Article VIII — Plain Language of the constitution.

How to use

  1. Check the next free number. ADRs are numbered NNNN from 0001. Find the highest existing number under docs/adr/ and add 1.

    ls docs/adr/[0-9]*.md 2>/dev/null \
  | sed -E 's@.*/([0-9]{4}).*@\1@' \
  | sort -n \
  | tail -1
  2. Slugify the title to kebab‑case: lowercase, alphanumerics and hyphens only, no leading/trailing hyphens.
  3. Compose the filename: docs/adr/<NNNN>-<slug>.md.
  4. Copy templates/adr-template.md to that path and fill in:
    • id: ADR-<NNNN>
    • title: "<title>"
    • status: proposed
    • date: <today's UTC date, YYYY-MM-DD>
    • supersedes: [] (unless this ADR replaces a prior one)
    • superseded-by: null
    • Body sections (Context / Decision / Consequences) — leave the headings; fill the prose.
  5. Do NOT touch existing ADR bodies. ADR bodies are immutable per the constitution's Article VIII. The only fields ever updated on an existing ADR are status and superseded-by.
  6. If this ADR supersedes a prior one, update the prior ADR's frontmatter — only those two fields — in the same PR.
  7. Update docs/adr/README.md if it maintains an index of ADRs.

Reporting

On success, report:

Created ADR-<NNNN>: <title>
  path: docs/adr/<NNNN>-<slug>.md
  status: proposed
  supersedes: <list or none>

If a prior ADR was superseded, name it explicitly.

Do not

  • Do not number an ADR by guessing — always derive from the directory listing. Two ADRs with the same number is a worse failure than a slow scan.
  • Do not edit the body of any existing ADR. To change a decision, supersede it.
  • Do not mark a new ADR accepted without explicit human approval. New ADRs start proposed.
  • Do not delete superseded ADRs. They remain as historical record.

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.

Check your setup, free