team-health-report
Skill1 starsChanged 6 months agoMITView on GitHub
Orchestration skill that runs all metrics analyses and produces a unified team health dashboard. Combines review network, review cycles, project-people map, contribution velocity, review cards, and 9-box into a single comprehensive report with period-over-period comparison. Use when asked to 'run team health', 'full metrics report', 'quarterly team assessment', or 'team dashboard'.
In this repository30 other files it gives its agents.
- setupSkill
- enrich-prsSkill
- epic-cleanupSkill
- epic-overviewSkill
- oncall-reviewSkill
- sprint-managementSkill
- sprint-statusSkill
- team-activitySkill
- team-data-syncSkill
- direct-report-prepSkill
- interview-analysisSkill
- interview-prepSkill
- peer-prepSkill
- project-statusSkill
- team-analysisSkill
- today-prioritiesSkill
- weekly-snippetSkill
- bus-factorSkill
- contribution-velocitySkill
- nine-boxSkill
- project-people-mapSkill
- review-cardsSkill
- review-cyclesSkill
- review-networkSkill
- task-rolloverSkill
- context-checkSkill
- prep-my-daySkill
- initiative-breakdownSkill
- product-briefSkill
- technical-deep-diveSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run all metrics skills and produce a unified team health dashboard with period-over-period comparisons.
- Distinctive: line 24
All data sources from constituent skills:
- Distinctive: line 35
Ask the user or infer:
- Distinctive: line 42
Verify data exists for the requested period:
- Very specific: line 43
Check data/YYYY-MM/ directories cover the full range
- Distinctive: line 44
Check enrichment data availability (what % of PRs are enriched?)
- Very specific: line 45
If data is missing, offer to fetch it first via team-activity skill
- Distinctive: line 161
Write the report to:
- Distinctive: line 172
If enrichment data is sparse (< 50% of PRs enriched), flag it and note which metrics are affected.
- Distinctive: line 174
Keep the executive summary short enough to scan in 30 seconds.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Team Health Report (Orchestration)
Run all metrics skills and produce a unified team health dashboard with period-over-period comparisons.
When to Trigger
- "team health report", "run team health", "full metrics"
- "quarterly assessment", "team dashboard", "metrics report"
- "how's the team doing?" (when comprehensive answer desired)
Data Sources
All data sources from constituent skills:
data/YYYY-MM/{login}-prs.jsondata/YYYY-MM/{login}-reviews.jsondata/YYYY-MM/{login}-issues.jsondata/enrichment/{pr_number}.jsonteam.json
Process
Phase 1: Determine scope
Ask the user or infer:
- Period: Quarter (default), month, or custom date range
- Comparison: Auto-select previous same-length period
- Depth: Full (all sections) or summary (dashboard + flags only)
Phase 2: Data check
Verify data exists for the requested period:
- Check
data/YYYY-MM/directories cover the full range - Check enrichment data availability (what % of PRs are enriched?)
- If data is missing, offer to fetch it first via
team-activityskill
Report data coverage:
Data coverage: 2026-01 through 2026-03
Enrichment: 142/184 PRs enriched (77%)
All 7 team members have activity data.Phase 3: Run analyses (in order)
Execute each metrics skill's logic:
- Review Network → network density, Gini, bottleneck ratio, matrix
- Review Cycles → avg rounds per person, trends, outlier PRs
- Project-People Map → bus factor, silo detection, breadth scores
- Contribution Velocity → TTM, throughput, responsiveness
- Review Cards → per-person quarterly grades
- 9-Box → talent grid placement
Phase 4: Synthesize dashboard
Combine all outputs into a unified report with:
Executive summary (3-5 bullet points):
- Headline team health signal (improving/stable/declining)
- Biggest win this period
- Biggest risk or concern
- Notable individual movements
Key metrics table (the "vital signs"):
| Metric | Current | Previous | Trend | Target |
| Network density | 0.86 | 0.71 | 🟢 +21% | >0.7 |
| Gini coefficient | 0.32 | 0.49 | 🟢 -35% | <0.4 |
| Team TTM p50 | 18h | 24h | 🟢 -25% | <24h |
| PRs/FTE/month | 14.2 | 12.8 | 🟢 +11% | >10 |
| Avg review rounds | 1.3 | 1.6 | 🟢 -19% | <2.0 |
| Bus factor 1 repos | 3 | 5 | 🟢 -40% | 0 |
| First review p50 | 4h | 6h | 🟢 -33% | <8h |
Individual highlight cards (per person, 2-3 lines):
- Current grade, trajectory, standout metric, concern if any
Phase 5: Generate insights
Go beyond the numbers. Identify:
Patterns:
- Is the team trending healthier or declining?
- Are specific pairs over-indexing on each other?
- Is scope expanding or contracting?
Coaching signals:
- Who needs attention? (declining metrics, high review cycles)
- Who deserves recognition? (growth trajectory, network contributions)
- Who is ready for more scope? (exceeding consistently, narrow breadth)
Structural observations:
- Any single points of failure that need addressing?
- Is review load balanced or bottlenecked?
- Are new team members ramping appropriately?
Phase 6: Recommendations
Actionable next steps (3-5 max):
- Specific, addressed to the manager
- Tied to data (not generic advice)
- Prioritized by impact
Example:
1. Pair dave with carol on data-pipeline reviews (bus factor 1 → 2, carol has capacity)
2. Recognize alice in team standup (A+ velocity for 3 consecutive months)
3. Check in with bob about TTM regression (45h → 72h this month, was 22h prior)Output Format
The full report follows this structure:
# Team Health Report: {period}
> Compared against: {previous_period}
## Executive Summary
- [3-5 bullet synthesis]
## Vital Signs
[key metrics table]
## Review Network
[condensed network output — matrix, density, key flags]
## Contribution Velocity
[per-person velocity table, team trends]
## Review Quality
[review cycles summary, outliers]
## Project Coverage
[heatmap, bus factor flags, silo alerts]
## Individual Cards
[grade table for all members]
## 9-Box Grid
[current placement, movement from prior]
## Insights & Recommendations
[synthesized coaching signals and action items]Output Location
Write the report to:
reports/metrics/team-health-{YYYY-MM-DD}.md(in the data workspace)- Optionally: the user's vault at a location they specify
Cadence
Recommended: run quarterly (aligned to fiscal year quarters). Can run monthly for tighter feedback loops. Monthly reports can be lighter (skip 9-box and review cards, focus on velocity and network).
Notes
- This is a READ-ONLY analysis skill. It produces reports but never modifies source data.
- If enrichment data is sparse (< 50% of PRs enriched), flag it and note which metrics are affected.
- The report should be useful standalone; a reader shouldn't need to open constituent reports.
- Keep the executive summary short enough to scan in 30 seconds.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

