agentleFS
nshopiknshopik/dream-team/skills/scope-spec/SKILL.md

scope-spec

Skill2 starsChanged 19 days agoMITView on GitHub

Writes a project spec in the repo's specs folder: a date and status header, then context, decision, consequences, design and open items. Use when asked to write the spec, the v1 design, a design doc, or a cross-cutting design change. Not for feature work (file an issue with `scope-issue`) or cutting milestones from a spec (use `cut-milestones`).

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Read spec-template.md before writing.

    line 13
  2. Distinctive:

    Write the answers into the spec.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

spec-style

  • Read spec-template.md before writing; follow its section order.
  • Path and filename: what <base directory>/../../references/repo-conventions.md resolves.
  • Terms: follow <base directory>/../../references/glossary.md.
  • Source: the conversation so far, plus any repo files or notes it names; never re-ask what it settles.
  • A question the source leaves open → ask it with AskUserQuestion before writing; never guess.
  • Write the answers into the spec.
  • A Decision or Design point settled in an issue, MR or comment → end it with a link to it.
  • A question the user cannot answer yet (needs research, a lab run, someone else) → an ## Open items entry.
  • Work that fits one issue → no spec.
  • Its decision passes the test in <base directory>/../build-issue/reference/decision-record.md → a decision record, in its own docs MR, via scope-issue Decisions.
  • Its decision fails that test → write it into the issue with scope-issue.
  • The date goes in the header, never the filename.
  • Header: **Date:** and **Status:** lines. No branch name.
  • Status: Draft, then Accepted, which is terminal; or Superseded by <spec-file>.
  • File lists, test cases, rejected options and milestones → issues, topic docs, decision records or the ROADMAP; never the spec.
  • Length: aim for about 1,500 words, counted with wc -w.
  • Draft over 2,000 words → ask with AskUserQuestion which Design subsections to move to a topic doc, one option per subsection.

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.