How do I install the Refine Ticket skill?

Run npx skillmds@latest add diegocortes15/refine-ticket in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Refine Ticket safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Refine Ticket?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Refine Ticket free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Refine Ticket?

Diegocortes15 (@diegocortes15) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Refine Ticket by diegocortes15 — Agent Skill

Name: Refine Ticket
Author: Diegocortes15

Refine Ticket

Iteratively harden a Jira automation ticket against a "bulletproof" rubric — grounded in existing automation, app docs, and user-supplied sources — then write the refined acceptance criteria back to the ticket on approval, so /from-issue has nothing left to guess.

Diegocortes15 de0b458 5 files · 22.4 KB Updated Sep 17, 2026

File contents

refine-ticket

Given a Jira issue key (e.g. SW-123), this skill reads the ticket via the Atlassian MCP, scores it against the refinement rubric, and loops — auto-resolving gaps from existing automation + docs and asking you (or a source you point it at) for the rest — until the ticket is unambiguous. On your approval it writes a ## Refined Acceptance Criteria block back to the ticket. It does NOT generate tests; run /from-issue after. See ADR-0013.

How to use it

Tell Claude what you want:

Use the refine-ticket skill on SW-123.

Or to preview without writing to Jira:

Use the refine-ticket skill on SW-123 with dry-run.

During the loop, when asked about a gap you can either answer directly or point the skill at a source ("it's in Confluence page X", a URL, a doc path). The skill ingests it and continues. It does NOT inspect a running app — it's shift-left, so it works even before the feature is built. It stops when the ticket has no open gaps, then asks before writing anything back.

Workflow

The full procedural workflow is in references/workflow.md. Read that file before executing the skill.

Setup note: the Atlassian MCP must be connected (OAuth) with write scope for the Step 7 description update — defined at project scope in .mcp.json. Its read + write tools are pre-authorized in allowed-tools above so the loop doesn't prompt each call. Write-back happens only on your explicit approval (per ADR-0013).

References

references/workflow.md — the procedural loop
references/rubric.md — the "bulletproof" checklist (definition of done)
references/sources.md — source catalog + user-supplied-source protocol
references/writeback-template.md — the ## Refined Acceptance Criteria block + idempotent-update rule

Composition

This skill pairs with /from-issue: refine first, then generate. It reuses the /from-issue skill's references/bucket-classification.md and references/qa-analysis.md for the rubric's coverage/automatable judgment.

---name: refine-ticketdescription: Iteratively harden a Jira automation ticket against a "bulletproof" rubric — grounded in existing automation, app docs, and user-supplied sources — then write the refined acceptance criteria back to the ticket on approval, so /from-issue has nothing left to guess.---# refine-ticketGiven a Jira issue key (e.g. `SW-123`), this skill reads the ticket via the Atlassian MCP, scores it against the refinement rubric, and loops — auto-resolving gaps from existing automation + docs and asking you (or a source you point it at) for the rest — until the ticket is unambiguous. On your approval it writes a `## Refined Acceptance Criteria` block back to the ticket. It does NOT generate tests; run `/from-issue` after. See ADR-0013.## How to use itTell Claude what you want:> Use the refine-ticket skill on SW-123.Or to preview without writing to Jira:> Use the refine-ticket skill on SW-123 with dry-run.During the loop, when asked about a gap you can either answer directly or point the skill at a source ("it's in Confluence page X", a URL, a doc path). The skill ingests it and continues. It does NOT inspect a running app — it's shift-left, so it works even before the feature is built. It stops when the ticket has no open gaps, then asks before writing anything back.## WorkflowThe full procedural workflow is in [`references/workflow.md`](references/workflow.md). Read that file before executing the skill.> **Setup note:** the Atlassian MCP must be connected (OAuth) with **write** scope for the Step 7 description update — defined at project scope in `.mcp.json`. Its read + write tools are pre-authorized in `allowed-tools` above so the loop doesn't prompt each call. Write-back happens only on your explicit approval (per ADR-0013).## References- [`references/workflow.md`](references/workflow.md) — the procedural loop- [`references/rubric.md`](references/rubric.md) — the "bulletproof" checklist (definition of done)- [`references/sources.md`](references/sources.md) — source catalog + user-supplied-source protocol- [`references/writeback-template.md`](references/writeback-template.md) — the `## Refined Acceptance Criteria` block + idempotent-update rule## CompositionThis skill pairs with `/from-issue`: refine first, then generate. It reuses the `/from-issue` skill's `references/bucket-classification.md` and `references/qa-analysis.md` for the rubric's coverage/automatable judgment.## See also- `docs/refine-ticket.md` — learning guide with a worked example- ADR-0008 — why custom skills follow this layout- [ADR index (origin repo)](https://github.com/Diegocortes15/playwright-ai-framework/tree/main/docs/adr) — rationale for every `ADR-NNNN` cited above. Paths like `docs/…` and `src/…` are relative to that repo, not to this skill.

Frequently asked questions