Agent issue tracker setup

Skill queen-of-code/AI-DLC/skills/agents/agent-issue-tracker-setup

Onboards AIDLC issue-tracker choice for a consumer repo: fills AGENTS.md Issue tracker (AIDLC) table, checklists for GitHub vs Linear vs Jira paths, and links to ISSUE-TRACKER-PORTABILITY docs. Does not run external APIs; guides humans through wiring.From its SKILL.md

Install

npx -y skills add queen-of-code/AI-DLC --skill agent-issue-tracker-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.0 KB, as published. Nobody here has run it

agent-issue-tracker-setup

Role

You help a consumer repository adopt AIDLC in a way that is issue-tracker-agnostic for phase skills: the repo declares which system holds Feature work, and you leave a durable record in AGENTS.md.

Ground truth (read first)

docs/ISSUE-TRACKER-PORTABILITY.md in the AI-DLC library (or the same doc linked from the marketplace install) — AGENTS.md template, invariants vs pluggable transport.
skills/work-tracking/SKILL.md — parent/child patterns; GitHub and Linear platform mapping. Jira: no table in that skill yet — the AGENTS.md contract is the extension point.

When invoked

User says we use Linear, GitHub only, Jira, switch from GitHub to X, or set up the tracker for AIDLC.

Behavior

Ask which system is the source of truth for Feature-level work: github-issues, github-projects-v2, github-projects-classic, linear, jira, or other (name it).
For github-projects-v2 (recommended headless Cursor queue), point to GITHUB-AIDLC-QUEUE.md — copy queue workflow templates, configure Projects v2 field AIDLC phase, secrets/vars, Cursor AIDLC_GH_CALLBACK_TOKEN.
For github-projects-classic (or label-only automation on classic boards), point to GITHUB-AIDLC-PROJECT.md — copy workflow template, labels, project_card — and remind: no secrets in the repo, PAT in secrets.
For Linear, use work-tracking’s Linear table as a base; have them define: team, project or initiative, how phases map (workflow or labels), and where the feature/<slug>/ link lives (issue description, project doc field).
For Jira, do not invent workflows — there is no Jira template in this repo. Capture whatever they need as checklist items (project, issue types, status ↔ phase, automations) and fill the AGENTS.md table; optional extra doc in their docs/ only if the table is too small, linked from Notes in the table.
Output a ready-to-paste ## Issue tracker (AIDLC) section for the consumer AGENTS.md, using the basic or extended (dual-tracker) table from ISSUE-TRACKER-PORTABILITY.md. Fill the Value column from the conversation. Add ## UI validation environments from CONSUMER-SETUP.md when the repo has a UI.
If they use git, offer a branch name and git-workflow-style commit message for a PR that only adds/updates that AGENTS.md block (or say “paste this yourself” for non-Git flow).

Anti-patterns

Installing webhooks or tokens for the user without their explicit token handling rules.
Hard-coding “everyone uses GitHub Issues” in your narrative — their AGENTS.md is authoritative after setup.
Skipping the AGENTS.md block — phase orchestrators and other agents are supposed to read it.

Success

Consumer repo has a visible issue-tracker row in AGENTS.md, and the human has a numbered checklist for anything still manual (e.g. “Create Linear workflow state Plan”).