agentleFS
darrenCWJdarrenCWJ/agent-skills-scaffold/.claude/skills/design-decisions/SKILL.md

design-decisions

Skill0 starsChanged 3 months agoMITView on GitHub

Record design/architecture decisions as lightweight ADRs at the moment they are made. Use whenever choosing between viable alternatives, abandoning an approach, accepting a trade-off, amending a plan, or when anyone would later ask why is it done this way. I'll-document-it-later is a protocol violation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Every ADR gets a memory entry pointing at it (memory skill), so recall works even before the file is found.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Design decisions

Any choice a future reader would ask "why?" about gets a record — at the moment of the decision, not at the end. "I'll document it later" is a protocol violation; later, the alternatives you rejected are forgotten and the record is worthless.

Triggers

  • Choosing between 2+ viable approaches (tech, structure, method, format, source).
  • Abandoning an approach (record WHY it failed — this is the highest-value record of all).
  • Amending a plan in a way that changes direction.
  • Accepting a trade-off, constraint, or known limitation.
  • Overriding a convention or an earlier decision.

Format

docs/decisions/NNNN-<slug>.md, sequential numbering, using templates/decision.md. One decision per file. Keep it under a page — an ADR nobody reads is an ADR that doesn't exist.

Required fields: Status (proposed/accepted/superseded by NNNN), Context (the forces at play), Decision (one sentence, active voice), Alternatives rejected (each with the reason for rejection), Consequences (what gets easier, what gets harder, what future work this creates).

Rules

  • Rejection reasons are the payload. "We chose X" is weak; "we rejected Y because Z" is what saves the next person a week.
  • Decisions are immutable once accepted. Changed your mind? New ADR that supersedes the old one; update the old one's Status line only.
  • Every ADR gets a memory entry pointing at it (memory skill), so recall works even before the file is found.
  • At orient time (Phase 0), scan the decisions index — contradicting a recorded decision without superseding it is a defect.

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.