agentleFS
encoreshaoencoreshao/encore-skills/skills/write-issue/SKILL.md

write-issue

Skill2 starsChanged 14 days agoMITView on GitHub

Turn a rough idea into a well-structured GitLab issue with clear problem statement, root cause, and testable acceptance criteria

8 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

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

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 4

    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:

    Use when you have a rough idea, bug report, or feature request that needs to become a trackable GitLab issue.

    line 14
  2. Distinctive:

    Before writing anything, ask:

    line 20
  3. Distinctive:

    Don't start drafting until you can answer these.

    line 26
  4. Distinctive:

    If not — improve the issue before creating it.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 8 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

Write Issue

Use when you have a rough idea, bug report, or feature request that needs to become a trackable GitLab issue.

Steps

1. Nail the problem first

Before writing anything, ask:

  • What is actually broken or missing? (the symptom)
  • Why does it happen? (the root cause — for bugs)
  • Who is affected and how often?
  • What does "fixed" look like?

Don't start drafting until you can answer these. A vague issue creates vague work.

2. Draft the issue

Title: Short, imperative, problem-focused.

  • Bug: Users cannot log in when email contains uppercase letters
  • Feature: Add CSV export to the reports page
  • No [Type] prefix — use labels for that.

Description:

## Problem
What is broken or missing? What is the root cause (for bugs)?
Be specific — include error messages, affected users, frequency.

## Expected behavior
What should happen instead?

## Acceptance Criteria
- [ ] <specific, testable outcome — not "it works">
- [ ] <regression test covers this case>
- [ ] <no related behavior is broken>

## Out of scope
What this issue does NOT cover. Prevents scope creep.

Labels: bug / feature / improvement + area (backend, frontend, design)

3. Sanity check before submitting

Ask yourself:

  • Could an engineer start working on this without asking you any questions?
  • Are the acceptance criteria specific enough to verify with a test?
  • Is the root cause identified (for bugs) or is it still a guess?

If not — improve the issue before creating it.

4. Create

# With glab
glab issue create --title "TITLE" --description "DESCRIPTION" --label "bug,backend"

# Without glab: copy the text and paste into GitLab

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.