architect-analyze
Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or…
Use when the user asks for their active worklist — open PRs with next actionable move, merged work not yet closed, takable tickets, and blocked work, classified by next move.
$ npx -y skills add tikalk/adlc-team-skills --skill factory-tickets --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/factory-ticketsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks for their active worklist — open PRs with next actionable move, merged work not yet closed, takable tickets, and blocked work, classified by next move.
name: factory-tickets description: Use when the user asks for their active worklist — open PRs with next actionable move, merged work not yet closed, takable tickets, and blocked work, classified by next move.
`factory-tickets` is the read-only personal worklist engine of the software factory. It provides the user with an immediate, live, and actionable overview of their active queue, categorized by "next move" rather than abstract status.
It operates directly against the external issue tracker and PR host (GitHub, GitLab, Linear, Jira) using the tracker-agnostic integration layer (`factory-mission/references/tracker-integration.md`).
---
**When NOT to use**:
---
1. Discover the active tracker provider and credentials (`factory-mission/references/tracker-integration.md`). 2. Identify the authenticated user's login. Restrict the search to:
Never poll individual items. Run two paged searches (via MCP or CLI) to fetch the entire active set in one round-trip per source: 1. **Pull Request Search**: fetch the user's open PRs, including: draft status, review decision, unresolved threads, named check statuses, and mergeability. 2. **Issue Search**: fetch the user's assigned open issues, including: title, description, state, labels, milestones, and linked project metadata.
A PR routinely cross-references multiple tickets. Associate a pull request to a ticket **only** when there is explicit evidence:
If no explicit evidence exists, leave the association cell empty. Never guess based on mere textual mention.
Assign every retrieved item to exactly one of the following priority sections. **Render what was assigned — never reclassify during formatting**:
1. **Active Pull Requests (My Turn)**: Pull requests where the next action belongs to the user:
2. **Active Pull Requests (Their Turn)**: Pull requests waiting on external actions:
3. **Merged, Ticket Still Open**: The PR that closes this ticket has merged, but the ticket remains open on the board. Move is: verify, then close. 4. **Takable Now (Backlog)**: Open issues with lifecycle `spec-gated`, automation-gating `agent-can-execute`, and no pull request claiming them. (If empty, display an explicit "none"). 5. **Waiting on Someone Else**: Open issues with unresolved blocked-by dependencies, naming the blocking ticket.
*Note: Epics and parent issues go in an Appendix below a rule, showing child counts and progress. They are never mixed into the active task list.*
---
1. **Strictly Read-Only**: This skill physically cannot edit, comment, create, or modify any ticket, label, assignee, or board field. No `gh` or `glab` write commands are present. 2. **No Caching**: Every run performs a live fetch. A cached or stale queue is worse than none. 3. **No Rollup Guessing**: Never report check status from a rolled-up "failing" commit status if a job was merely cancelled or skipped. Read and name the exact failing context. 4. **Unparsed Word Reporting**: If the user's request contains words the query parser doesn't recognize, do not drop them. List them in an "Unparsed Terms" section below the table so the user knows what was ignored.
Agent skills that give coding agents your team's context at session start, so they stop working like strangers.
Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or…
Use when architecture work starts or a tech-stack or pattern decision emerges — injects the project ADR index…
Use when ADRs need review, gaps need filling, or ADR status must be approved as Accepted before architecture generation.
Use when accepted ADRs exist and AD.md must be produced or updated as unified architecture documentation.
Use when bootstrapping architecture documentation for a brownfield project by reverse-engineering ADRs from an existing codebase.
Use when you want guided trade-off analysis, multi-option comparison, or structured architectural decision facilitation before…