agentleFS
SantiagoVqzSantiagoVqz/claude-skills/skills/support/brief/SKILL.md

brief

Skill2 starsChanged 11 days agoMITView on GitHub

Explain a ticket or any technical text in plain technical terms: what it asks, what to do, when it is done, and what it leaves unclear. Use when the user runs /brief, or asks what a ticket or a description means.

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, strategy and 9 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.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 6 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 4 projects that use this

  • aleksander-dytkoSkill

    decision

    Make a product decision with full context from the vault and available sources

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 5 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 7 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 5

    Distinctive

    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 the comments too, because they often change the scope.

    line 19
  2. Distinctive:

    Write "None" under Gaps when the text is complete.

    line 52
  3. Distinctive:

    When the text gives no acceptance criteria, infer them from the ask and mark each one "(inferred)".

    line 53
  4. Distinctive:

    When the text describes a system rather than asks for work, keep Problem, Terms and Gaps, and replace the middle sections with How it works.

    line 54
  5. Distinctive:

    Write in whole sentences, one idea per sentence, in active voice, with plain words.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 73 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

Brief

A brief tells the reader what a ticket asks, in plain technical words, so they can act on it. Print the brief in chat. The source stays as it is.

The reader is an engineer who knows the field but not this ticket's context. Keep the technical terms that carry meaning, such as "migration" or "race condition". Explain the project's own names.

1. Get the text

  • Pasted text: use it.
  • An issue number or a GitHub URL: run gh issue view <n> --comments.
  • Another tracker's key or URL: read it with that tracker's tool when one is connected. Otherwise ask the user to paste it.

Read the comments too, because they often change the scope.

Completion: you hold the full text and its comments.

2. Decode the terms

List each name the reader must decode: code names, system names, acronyms and team jargon. Find what each one does. Look in the text first, then in the code of the working directory when the term names something there. A term that stays unknown goes under Gaps.

Completion: each term has a plain definition or a line under Gaps.

3. Write the brief

Use this shape:

**Problem.** One sentence of 15 words or fewer.

**What to do.**
- Now: the current behavior.
- Wanted: the behavior after the change.
- The concrete changes, one per bullet, in order when order matters.

**Done when.**
- Each acceptance criterion as a check the reader can run.

**Terms.**
- `Name`: what it does, in one line.

**Gaps.**
- What the text leaves unclear, contradicts, or does not say.
  • Drop Terms when no term needed decoding.
  • Write "None" under Gaps when the text is complete.
  • When the text gives no acceptance criteria, infer them from the ask and mark each one "(inferred)".
  • When the text describes a system rather than asks for work, keep Problem, Terms and Gaps, and replace the middle sections with How it works.

Write in whole sentences, one idea per sentence, in active voice, with plain words. Each statement comes from the source or the code. Mark any other statement "(inferred)". The brief gets shorter by cutting repetition, history and filler. Each requirement stays.

Completion: each requirement of the source appears under What to do or Done when, and the brief is shorter than the source.

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.