Skip to content
Back to skills

Issue Tracker Ingestion

ASecurity

Pull issue/PR/ticket details from Jira, GitHub Issues, Linear, or Azure Boards via MCP into `01-spec.md` `## Source`. Use at the start of `/spec` whenever the user references an external ticket.

  • 62 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
developmentgoazuregitdevops

Works with

  • mcp

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add loiane/specs-driven-development-spring-angular --skill issue-tracker-ingestion --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Issue Tracker Ingestion?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Issue Tracker Ingestion
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/loiane-issue-tracker-ingestion/badge)](https://www.skillsdirectory.com/skills/loiane-issue-tracker-ingestion)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: issue-tracker-ingestion
description: Pull issue/PR/ticket details from Jira, GitHub Issues, Linear, or Azure Boards via MCP into `01-spec.md` `## Source`. Use at the start of `/spec` whenever the user references an external ticket.
when_to_use:
  - Phase 1 (Specify) — converting a tracker ID into a spec.
  - Verifying that a spec's `## Source` accurately reflects the ticket.
authoritative_references:
  - docs/platform-mapping.md (MCP wiring)
  - .claude/templates/spec.template.md
---

# Issue tracker ingestion

## Supported sources

| Source | MCP server | Identifier shape |
|---|---|---|
| Jira (Atlassian) | `atlassian` | `SHOP-1422` |
| GitHub Issues | `github` | `owner/repo#42` or URL |
| GitHub Pull Requests | `github` | `owner/repo!42` or URL |
| Linear | `linear` | `ENG-123` |
| Azure Boards | `azure-devops` | `AB#54321` |

If no MCP is configured, fall back to user-provided text. Never invent a ticket.

## Recipe (per source)

1. Resolve identifier → MCP fetch.
2. Capture: title, description, status, labels, assignee, comments (last 10), attachments (filenames only), URL, fetched-at timestamp.
3. Write a verbatim block in `01-spec.md`:

   ```markdown
   ## Source

   - **System:** Jira
   - **ID:** SHOP-1422
   - **URL:** https://example.atlassian.net/browse/SHOP-1422
   - **Title:** Apply gift card at checkout
   - **Status:** In Progress
   - **Fetched:** 2026-04-18T10:00:00Z

   ### Description (verbatim)
   > Users should be able to apply a gift card during checkout. It should reduce the order total. If the card has been used, show an error.

   ### Comments (last N, verbatim)
   > [PM, 2026-04-15]: Confirmed only authenticated buyers in scope.
   > [Eng lead, 2026-04-16]: Use existing error envelope.
   ```

4. Extract candidate ACs **only from the verbatim text**. Do not paraphrase requirements; quote the source line and put your AC under it. If a candidate AC has no source line, it goes to `## Open Questions` as a `Q-NNN`.

## No-invention enforcement

If a source field is missing (e.g. no acceptance criteria in the ticket), the agent does **not** fill it from imagination. It writes:

```markdown
- Q-001: Source ticket has no explicit acceptance criteria. Need user to confirm AC list before proceeding to AC drafting.
```

`/spec` then halts and asks the user.

## Updating after the ticket changes

If the user re-runs `/spec` and the ticket has changed:

- Re-fetch.
- Diff old vs new in `## Out-of-Band Inputs` ("ticket updated 2026-04-19; description gained paragraph about partial redemption").
- Add `Q-NNN` for any new requirement not yet in AC.

## Anti-patterns

- "The ticket says X" without quoting it.
- Summarizing comments instead of quoting.
- Pulling AC from the ticket title alone.
- Silently ignoring an unread comment that contradicts the description.
- Assuming the ticket assignee = the spec author.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.