agentleFS
brayandiazcbrayandiazc/project-starter-template-en-ai/.claude/skills/new-adr/SKILL.md

new-adr

Skill2 starsChanged 2 months agoMITView on GitHub

Scaffolds a new Architecture Decision Record (ADR) by copying the ADR template into the next-numbered file and registering it in the decisions index. Use this when the user wants to record an architecture decision, create/add an ADR, or document a technical choice (e.g. "write an ADR for switching the database", "add a decision record").

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    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 ADR for the decision titled in $ARGUMENTS.

    line 7
  2. Very specific:

    Read docs/decisions/README.md to learn the numbering scheme, file-name convention, and how the index is maintained.

    line 9
  3. Distinctive:

    Leave Context / Decision / Consequences as guided prompts for the author to complete.

    line 16
  4. Very specific:

    Add a link to the new ADR in the index inside docs/decisions/README.md, in number order.

    line 17
  5. Very specific:

    Do NOT mark the ADR Accepted yourself, do NOT edit or supersede existing ADRs, and do NOT invent content for sections the author must …

    line 22

“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

Create a new ADR for the decision titled in $ARGUMENTS.

  1. Read docs/decisions/README.md to learn the numbering scheme, file-name convention, and how the index is maintained. Follow that doc if it differs from the steps below.
  2. Find the highest existing NNNN-*.md in docs/decisions/ and compute the next zero-padded number (e.g. 0007).
  3. Copy docs/decisions/0000-template.md to docs/decisions/<NNNN>-<kebab-title>.md, where <kebab-title> is the slugified $ARGUMENTS (lowercase, hyphen-separated).
  4. In the new file, fill in:
    • Title (the human-readable form of $ARGUMENTS)
    • Status: Proposed
    • Date: today's date (YYYY-MM-DD)
    • Leave Context / Decision / Consequences as guided prompts for the author to complete.
  5. Add a link to the new ADR in the index inside docs/decisions/README.md, in number order.
  6. Report the created file path and remind the author to fill in Context, Decision, and Consequences.

Example: /new-adr use server-side rendering → docs/decisions/0007-use-server-side-rendering.md.

Do NOT mark the ADR Accepted yourself, do NOT edit or supersede existing ADRs, and do NOT invent content for sections the author must decide.

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.