twg-status-rollups

twg

twg help

twg help <terms>

twg help describe <path>

CLI launcher fallback

twg <command>

command not found

$HOME/.local/bin/twg

$env:LOCALAPPDATA\Programs\twg\bin\twg.exe

Use When

• "What did I/person/team/org work on?" or weekly personal update
• Short-window personal update, standup, handoff, or restart after time away
• "Status of project/goal/topic/focus area"
• "Is this project ready to launch?" or go/no-go decision brief
• Leadership, monthly, annual, cycle, appraisal, or goal-alignment readout
• Org bottlenecks, priorities, stale goals, or project risks

First Move

• Person/team/org: resolve identity, roster, or org-tree groups.
• Project, goal, focus area, or topic: resolve native key, ARI, URL, name, or central project/page/workitem anchors.

Tree Routing Matrix

• pr-tree

  : merged/open PRs, reviews, shipped work, or repo momentum by manager or team. Default for PR-constrained evidence.

• org-tree

  : manager chain, roster, and reporting structure; use for grouping, not delivery evidence.

• workitem-tree

  : Jira issue load and active/done movement by org tree.

• work-tree

  : multi-surface org counts across Jira, PRs, goals, projects, docs, or videos. Not for PR-only or Jira-only asks.

Fast Path: PR-Based Leadership Rollup

1. Preserve the requested scope and window; for "last 2 weeks," use

   --since 14d

   .
2. Use

   pr-tree

   first. It groups by reporting-tree

   directReports

   ; add

   org-tree

   only for hierarchy context.
3. If option shape is uncertain, inspect

   twg help describe "pr-tree"

   before the data call; do not probe incompatible flag combinations.
4. Start count-first, then make at most one supported sampling/full-fetch pass for repo or theme evidence. Synthesize at manager/team level from that tree. Do not issue per-person queries merely to populate every group; use one targeted PR follow-up only when a material theme lacks representative proof.
5. Add one secondary surface only for a named gap.

Evidence Policy

• Match evidence to prompt constraints; merged-PR-only conclusions require PR evidence.
• Start count-first on tree surfaces; hydrate examples only for themes, risks, or owner attribution.
• Rank broad lists before minimal hydration.
• Distinguish authored delivery from review, coordination, and influence.
• Stop when evidence is sufficient. After two identical backend failures, stop that path and report the gap.

Recipe Cards

Person Or Personal Update

references/personal-work-summary.md

Short-Window Personal Update / Standup

references/personal-work-summary.md

Team Or Org Leadership Readout

twg projects query --scope org --include-inferred

[Paid: Intelligence]

Project Or Goal Status

Decision Readiness / Go-No-Go

references/decision-readiness.md

Topic Status

References

• references/personal-work-summary.md

  - standups, catch-ups, and broader personal status evidence

• references/decision-readiness.md

  - cross-domain go/no-go and approval evidence

Appraisal / Performance Evidence

Output Shape

• Executive summary first, with 3-6 high-signal observations.
• Table with owner/team/workstream, positive signals, risk signals, current focus, confidence, and evidence.
• Risks and leadership attention ranked by impact and owner.
• Confidence and gaps, including stale updates, missing product coverage, ACL gaps, or sampled evidence boundaries.

Anti-Patterns

• Do not make a status report a list of every artifact.
• Do not infer goal/project health from issue counts alone.
• Do not fan out across every org member if manager/team-level grouping answers the prompt.
• Do not use search snippets as final evidence for status or risk.
• Start explicit merged/open PR rollups with

  pr-tree

  , not the other trees.