// Use with the root `twg` skill for on-call handoffs, HOT/reliability reviews, incident/PIR analysis, Assets and laptop refresh, capacity/staffing views, meeting summaries, and operational risk readouts.
Use with the root `twg` skill for topic deep dives, dependency maps, graph explanations, workitem/page/user context, project-to-repo discovery, experts, and "catch me up" prompts. Hydrate anchors and relationship evidence before synthesis.
Use with the root `twg` skill for pull-request queues, stale reviews, repo contributors, repo hot areas, PR-based status, issue-to-PR lookups, and engineering review bottleneck analysis.
Root operating skill for the TWG CLI. Use for Atlassian work-data tasks across Jira, Confluence, Bitbucket, goals/projects/focus areas, JSM, Assets, Admin, people, teams, org structure, docs, meetings, videos, search, graph context, and supported mutations. Exact command syntax must come from live `twg help`.
Use with the root `twg` skill for personal, team, org, project, goal, focus-area, executive, quarterly, appraisal, and leadership status rollups. Resolve scope first, collect bounded evidence, and synthesize a readout with confidence and gaps.
| name | twg-operational-health |
| description | Use with the root `twg` skill for on-call handoffs, HOT/reliability reviews, incident/PIR analysis, Assets and laptop refresh, capacity/staffing views, meeting summaries, and operational risk readouts. |
Use together with the root twg skill. Exact command grammar must come from
live twg help, twg help <terms>, or twg help describe <path>.
Resolve the operational scope and time window:
Do not start with a broad cross-product inventory. Find the operational anchor first, then join only surfaces that answer the question.
Calculated user before broad display
name filters.Resolve team/service/component. Pull incidents/HOTs/PIRs, recent Jira follow-up, runbooks/docs, linked projects, and owners. Cluster symptoms into patterns and produce a first-hour checklist plus escalation map.
Search/query HOTs, incidents, PIRs, linked follow-up work, service/component context, owners, comments, and status. Cluster by failure theme. Connect each theme to concrete follow-up and missing ownership.
Build the contributor list from project/goal/Jira/PR/doc/activity evidence. Query Assets schema/type metadata before AQL. Join people to laptops using discovered user-like attributes, then rank by contribution centrality plus asset risk.
Use Assets schema-first discovery. Confirm site, schema, object type, and owner or contact fields. Report confidence and gaps for each candidate.
Resolve project/topic/org. Identify people with related recent work, ownership, review influence, docs, and project/goal involvement. Check current load signals before recommending candidates.
Query meetings/videos for the requested time window and people scope. Fetch transcript preview first. Fetch full transcript only for central recordings and write it to a file when needed. Summarize decisions, action items, themes, and gaps.