← ClaudeAtlas

issue-suggest-componentlisted

Suggest Jira components for one ticket or sweep all open tickets in a project. Gathers context from Jira, Confluence, and GitLab, proposes a conservative set of existing components (or recommends new ones), and confirms with the user before any modification. Bulk mode default project key is read from memory (`reference_jira_default_project.md`); max 250 tickets, highest key first. Use when user says "suggest components", "tag components", "fix components", "categorize tickets", or invokes /issue-suggest-component with or without a ticket key.
risadams/skills · ★ 2 · Web & Frontend · score 66
Install: claude install-skill risadams/skills
# Issue Suggest Component Suggest a focused set of Jira components for a ticket — adding only what's clearly supported by evidence in the ticket, linked Confluence pages, and related GitLab activity. Confirm every change with the user. ## Two modes | Trigger | Mode | Behavior | | --- | --- | --- | | `/issue-suggest-component PROJ-1234` | **Single** | Deep context gather + suggest + per-change confirm | | `/issue-suggest-component` (no key) | **Bulk** | Loop highest-key-first, max 250 open tickets in the default project (resolved from memory: `reference_jira_default_project.md`) | | `/issue-suggest-component ABC` (project key only) | **Bulk** | Same as bulk, override project | If the input is ambiguous, ask once. ## Suggestion bar (read this first) **Be conservative.** Suggesting nothing is acceptable and often correct. Only propose a component when there is **direct evidence** in the ticket text, comments, linked Confluence, or related MRs/commits. Do not infer from issue key alone, from the assignee, or from "tickets nearby usually have X." ## Constraints - **Confirm before every write.** Adding existing components, removing components, and creating new components each require explicit user approval. - **New components** require a second-level confirmation. The skill attempts creation via the Atlassian MCP; if no `create_component` tool is exposed (run `discover_tools` to check), surface the recommendation and instruct the user to create it manually in Jira. - **Neve