agentleFS
Sign inStart free
EndikaEndika/eskills/skills/spec-intake/SKILL.md

spec-intake

Skill0 starsChanged 57 days agoMITView on GitHub

Use when starting from a task described in Jira, Linear, a URL, or free text and you need it normalized into a spec (objective, acceptance criteria, constraints, definition of done) before planning.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. cperler/sous★ 1same name
    2. stardustai/stardust-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository14 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Pull the source: Read the ticket/URL/message.

    line 16
  2. Distinctive:

    Resolve ambiguity now: If the objective or a success condition is unclear, ask the few questions that change the work — before writing the …

    line 18
  3. Very specific:

    Keep the spec outside the repo (see eskills:standards) — it's an internal doc.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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-intake

Overview

Turn a task from anywhere — a Jira/Linear ticket, a URL, a Slack message, a vague sentence — into one normalized spec, before any planning. Usable standalone, and the entry point of eskills:task-flow Phase 1.

Steps

  1. Pull the source. Read the ticket/URL/message. Quote the real wording; don't paraphrase away a constraint.
  2. Resolve ambiguity now. If the objective or a success condition is unclear, ask the few questions that change the work — before writing the spec, not after.
  3. Normalize into the shape below.
  4. Classify for the flow (this is what task-flow consumes next).

Output shape

## Objective

<one or two sentences: the outcome, in the user's terms>

## Acceptance criteria

- [ ] <observable, checkable condition>
- [ ] …

## Constraints

- <tech, data, deadline, compatibility, non-goals>

## Definition of done

- <tests, docs, review, deploy — what "finished" requires>

## Classification

- Project shape: greenfield | brownfield
- Hard-tech challenge: yes (algorithm / performance) | no

Notes

  • Acceptance criteria must be observable — "X is faster" is not a criterion; "p95 < 200ms on N=10k" is.
  • The classification drives task-flow: brownfield → feature-dev:code-explorer; hard-tech → the SPIKE sub-phase.
  • Keep the spec outside the repo (see eskills:standards) — it's an internal doc.

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