agentleFS
metratonmetraton/gaia/skills/ticket-writing/SKILL.md

ticket-writing

Skill4 starsChanged 5 months agoMITView on GitHub

Use when creating or drafting a ticket or issue, or standardizing ticket output for a project -- "ármame un ticket", "escribe el issue", "necesito una tarea para Jira", "create a ticket", "draft an issue".

  • Commits and pushes

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Move all evidence to the first comment: After the ticket is created, post a comment with: commit hashes, commands run verbatim, output …

    line 54
  2. Distinctive:

    Adapt to the project's board conventions: Do not create Epics if the team does not use them.

    line 59
  3. Distinctive:

    Consolidate, do not inflate: Prefer fewer well-scoped tickets over many granular ones.

    line 64
  4. Distinctive:

    No implementation detail in the description.

    line 73

≈ “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

Ticket Writing

The formula for tickets humans can read in ~15 seconds. The what and why go at the top; the how and evidence go in a comment. One Story per brief or theme; consolidate rather than inflate. The register is human-register's; this skill owns the ticket's shape.

Core principle

A Story is readable by a non-technical stakeholder in 15 seconds. This means: plain English, active voice, value-oriented title, high-level description. All implementation detail and verification evidence lands in the first comment -- never in the description -- so the description reads clean.

Story template

Title: verb + outcome, plain English, no jargon, 80 chars max.

Description fields:

FieldContent
Objective1-2 sentences: what it achieves and why (high level) -- the plain register of technical-explanation: consequence over artifact, common nouns, no identifiers.
What it covers3-5 bullets of scope -- what, not how.
Acceptance criteriaChecklist "Done when..." -- verifiable, not vague.
LinksBrief slug / repo if applicable.

Evidence -- first comment only, never in description: commit hashes, verbatim commands, anything reproducible.

Subtask template

Title: short action phrase, plain English. Description: one line -- what it is / done when X.

Process

  1. Map to a brief or theme. One Story = one brief or coherent chunk of work. If the work spans multiple unrelated concerns, split into separate Stories. If it is one theme with sequential steps, use Subtasks.
  2. Write the title last. Draft the Objective and What-it-covers first; the title compresses naturally from those. If the title needs jargon to be precise, the description is missing context.
  3. Write the Acceptance Criteria as done-when checks. Each AC is a checkbox that a person (not a CI system) can verify. Vague ACs get pushed back: "migrated" means what? "History intact" means no commit lost.
  4. Move all evidence to the first comment. After the ticket is created, post a comment with: commit hashes, commands run verbatim, output snippets. This keeps the description clean for stakeholders and the evidence auditable for engineers.
  5. Adapt to the project's board conventions. Do not create Epics if the team does not use them. Respect the active Sprint. Use existing Labels and Components, not invented ones. Check 2-3 existing tickets before creating the first one.
  6. Consolidate, do not inflate. Prefer fewer well-scoped tickets over many granular ones. If two Subtasks share all context, make one Subtask. If a Story has one Subtask, fold the Subtask into the Story.

Style rules

  • Plain English, active voice. Write "Move repositories to Bitbucket" not "Repository migration to Bitbucket platform will be performed."
  • Title is value-oriented: what the user or team gains, not the mechanism.
  • No implementation detail in the description. "Configure DNS records" belongs in a Subtask description or the evidence comment, not the Story Objective.
  • Subtasks are ultra-light: one-line description, action-phrase title.
  • Fields: Assignee, Status (To Do / Done), Sprint -- set these before saving.

See examples.md for real tickets from the AOS migration project.

Anti-patterns

  • Evidence in the description -- pollutes the readable summary; goes in the first comment instead.
  • Title is the mechanism, not the outcome -- "Run git push for all repos" is a task; "Migrate AOS repositories to Bitbucket" is a Story.
  • One Subtask per command -- over-granular; group related steps into one Subtask with a multi-step description.
  • Inventing Epics or Labels -- inconsistency with the team's board adds noise. Adapt to what is already there.
  • Vague Acceptance Criteria -- "Works correctly" is not verifiable. "History intact" is verifiable only when it means "no commit missing from git log --oneline."

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.