From devboy
Fetches and summarizes issues from GitHub, GitLab, Jira, or ClickUp trackers. Filters by state, labels, assignee, search; paginates; drills into single issues with comments and relations.
npx claudepluginhub meteora-pro/devboy-tools --plugin devboyThis skill uses the workspace's default tool permissions.
Enumerate issues from whichever tracker is active (GitLab, GitHub, ClickUp, or Jira) and hand back either a compact summary of the result set or the full body of a single ticket the user cares about. The skill is always a read-only operation — it never mutates state.
Reads and analyzes JIRA issues from Red Hat Issue Tracker: fetches details/comments/custom fields/Git links, searches via JQL, categorizes bugs/CVEs/features/stories, traverses ticket graphs (parents/children/links), generates summaries. Read-only Python tool.
Searches Jira Cloud issues by assignee, status, label, project, type, component, reporter, parent, or free text using structured flags that compose safe JQL. Renders paginated summary table.
Triages GitHub issues assigned to you: fetches via GH CLI with cc-triage-scope label, builds dependency graph, categorizes resolved issues, and applies labels (cc-create-issue, cc-exec-issue, cc-update-issue).
Share bugs, ideas, or general feedback.
Enumerate issues from whichever tracker is active (GitLab, GitHub, ClickUp, or Jira) and hand back either a compact summary of the result set or the full body of a single ticket the user cares about. The skill is always a read-only operation — it never mutates state.
solve-issue) needs to look up a specific ticket before acting on it.Most useful filters live directly on get_issues:
# Default: 20 most recently updated open issues
devboy tools call get_issues '{"state": "open", "limit": 20}'
# Narrow by label / assignee / free-text search
devboy tools call get_issues '{"state": "open", "labels": ["bug"], "assignee": "alice"}'
devboy tools call get_issues '{"search": "websocket reconnect", "limit": 10}'
Supported keys: state (open / closed / all), search, labels, assignee, limit (1–100), offset, sort_by (created_at / updated_at), sort_order (asc / desc), projectKey, nativeQuery. On Jira, nativeQuery accepts raw JQL and takes precedence over the other filters.
get_issues returns at most 100 items per call. Walk the pages with offset:
devboy tools call get_issues '{"state": "open", "limit": 50, "offset": 0}'
devboy tools call get_issues '{"state": "open", "limit": 50, "offset": 50}'
Stop once a page returns fewer items than limit.
Before dumping the raw list to the user, produce a compact roll-up:
open / closed).priority or status values that cluster (e.g. "4 urgent, 12 normal").If the user asked a qualitative question ("is anything blocking the release?"), prioritise issues with blocked, urgent, or in_progress status over a flat listing.
Once the user picks one, fetch the full record — including comments and relations in a single call:
devboy tools call get_issue '{"key": "DEV-123"}'
# or, to skip related chatter
devboy tools call get_issue '{"key": "DEV-123", "includeComments": false, "includeRelations": false}'
For heavier comment threads, page them separately:
devboy tools call get_issue_comments '{"key": "DEV-123"}'
devboy tools call get_issue_relations '{"key": "DEV-123"}'
If the user asks "what states can an issue be in?", surface the tracker's workflow:
devboy tools call get_available_statuses
This is handy before calling update-issue on a provider whose state vocabulary is not "open / closed".
ProviderUnsupported or an empty payload.create-issue / update-issue.solve-issue.