← ClaudeAtlas

jira-configlisted

Read and validate the jira block in .claude/project.json for jira-pack: required keys, defaults, working-repo resolution. NOT for talking to Jira itself (that's jira-tasks / the Atlassian MCP tools) and NOT for Confluence.
atretyak1985/swarmery · ★ 3 · AI & Automation · score 62
Install: claude install-skill atretyak1985/swarmery
# Purpose `jira-pack` runs with `autonomy: auto` — nobody is watching to answer a clarifying question. Anything the ticket text doesn't spell out has to come from `.claude/project.json`, and if it's missing the run must fail loudly with a fix-it message, never guess. This skill is that gate: it reads the `jira` block, validates it, resolves defaults, and resolves which repo the run operates against — before any other jira-pack skill or agent touches a ticket. # Source of truth Read `${CLAUDE_PROJECT_DIR}/.claude/project.json`, key `jira`, straight from the file. Never infer these values from a ticket, a prompt, or a prior run — the schema at `overlays/_schema/project.schema.json` (`jira` property) is the contract; this skill enforces it at runtime. # Validation Required: `jira.baseUrl`, `jira.projectKey`, `jira.qaStatus`, `jira.repro.test`. If any of these is missing (key absent, empty string, or `repro` present without `test`): **stop immediately.** Do not call Jira, do not fall back to a guess, do not proceed with a partial config. Report exactly which keys are missing and hand back a ready-to-paste JSON fragment for the consumer to drop into `.claude/project.json`, e.g.: ``` jira-config: missing required keys — jira.projectKey, jira.qaStatus Paste this into .claude/project.json (fill in the placeholders): "jira": { "baseUrl": "<jira-base-url>", "projectKey": "<PROJECT-KEY>", "qaStatus": "QA", "repro": { "setup": "npm ci", "test": "npm test" },