Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert agile coaching: framework selection, maturity assessment, retrospective facilitation, transformation roadmaps. Use when selecting an agile framework, coaching teams, facilitating retrospectives, or designing a transformation.
.claude/skills/borghei-agile-coach/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -23% | 0% |
The agent acts as an expert agile coach guiding teams and organizations through framework selection, transformation planning, maturity assessment, and continuous improvement. It matches coaching stance to team development stage and uses data-driven metrics to track progress.
| Tool | Purpose | Command | |------|---------|---------| | maturity_scorer.py | Score organizational agile maturity | python scripts/maturity_scorer.py --assessment assessment.yaml | | metrics_dashboard.py | Generate team metrics dashboard | python scripts/metrics_dashboard.py --team "Team Alpha" | | retro_format.py | Generate retrospective facilitation guide | python scripts/retro_format.py --format sailboat | | transformation_tracker.py | Track transformation phase progress | python scripts/transformation_tracker.py --phase pilot |
In Scope: Framework selection and recommendation, team-level coaching and facilitation, maturity assessment and scoring, retrospective design, transformation roadmap creation, conflict resolution within agile teams, stakeholder alignment for agile adoption.
Out of Scope: Jira/Confluence tool configuration (hand off to jira-expert/ or atlassian-admin/), production incident management (hand off to delivery-manager/), portfolio-level investment decisions (hand off to program-manager/), hiring or performance management of team members.
Limitations: Maturity scoring is a point-in-time assessment that requires honest self-reporting; scores can be gamed. Framework recommendations are guidelines, not prescriptions -- every organization has unique constraints. Transformation timelines assume consistent leadership support; political changes can invalidate roadmaps.
| Integration | Direction | What Flows | |-------------|-----------|------------| | scrum-master/ | Bidirectional | Agile coach sets framework; Scrum Master executes sprint-level practices | | delivery-manager/ | Coach -> DM | Transformation roadmap milestones feed into delivery planning | | program-manager/ | Coach -> PgM | Scaling framework selection informs program governance structure | | jira-expert/ | Coach -> Jira | Board and workflow requirements derived from framework selection | | senior-pm/ | PM -> Coach | Portfolio priorities shape which teams get coaching focus first | | confluence-expert/ | Coach -> Confluence | Coaching artifacts (maturity reports, retro outcomes) documented in Confluence |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,020 | 23,199 | +10% | 1 | 1 | 0% | 3,217 | 4,514 | +40% | 0 | 0 | — |
case-02 | fail→fail | 22,149 | 23,560 | +6% | 1 | 1 | 0% | 3,281 | 4,079 | +24% | 0 | 0 | — |
case-03 | fail→pass | 21,861 | 20,870 | -5% | 1 | 1 | 0% | 3,565 | 4,213 | +18% | 0 | 0 | — |
case-04 | fail→pass | 16,017 | 7,602 | -53% | 1 | 1 | 0% | 2,616 | 2,049 | -22% | 0 | 0 | — |
case-05 | fail→pass | 14,957 | 5,099 | -66% | 1 | 1 | 0% | 2,194 | 1,623 | -26% | 0 | 0 | — |
case-06 | fail→pass | 20,649 | 10,908 | -47% | 1 | 1 | 0% | 3,268 | 2,508 | -23% | 0 | 0 | — |
case-07 | fail→pass | 18,368 | 10,400 | -43% | 1 | 1 | 0% | 2,902 | 2,486 | -14% | 0 | 0 | — |
case-08 | fail→pass | 7,747 | 2,494 | -68% | 1 | 1 | 0% | 1,166 | 1,241 | +6% | 0 | 0 | — |
case-09 | fail→pass | 10,187 | 2,082 | -80% | 1 | 1 | 0% | 1,573 | 1,246 | -21% | 0 | 0 | — |
case-10 | fail→pass | 10,286 | 1,756 | -83% | 1 | 1 | 0% | 1,567 | 1,170 | -25% | 0 | 0 | — |
case-11 | fail→pass | 8,417 | 2,269 | -73% | 1 | 1 | 0% | 1,301 | 1,263 | -3% | 0 | 0 | — |
case-12 | pass→pass | 12,819 | 8,308 | -35% | 1 | 1 | 0% | 1,991 | 2,179 | +9% | 0 | 0 | — |
case-13 | pass→pass | 14,581 | 12,197 | -16% | 1 | 1 | 0% | 2,117 | 2,766 | +31% | 0 | 0 | — |
case-14 | pass→pass | 12,547 | 13,332 | +6% | 1 | 1 | 0% | 1,873 | 2,879 | +54% | 0 | 0 | — |
case-15 | fail→fail | 11,374 | 3,416 | -70% | 1 | 1 | 0% | 1,764 | 1,478 | -16% | 0 | 0 | — |
case-16 | fail→pass | 10,520 | 2,898 | -72% | 1 | 1 | 0% | 1,730 | 1,296 | -25% | 0 | 0 | — |
case-17 | fail→pass | 15,839 | 3,083 | -81% | 1 | 1 | 0% | 2,474 | 1,408 | -43% | 0 | 0 | — |
case-18 | fail→pass | 11,276 | 2,952 | -74% | 1 | 1 | 0% | 1,546 | 1,375 | -11% | 0 | 0 | — |
case-19 | fail→pass | 7,434 | 1,723 | -77% | 1 | 1 | 0% | 1,069 | 1,216 | +14% | 0 | 0 | — |
case-20 | pass→pass | 13,719 | 14,523 | +6% | 1 | 1 | 0% | 2,231 | 3,119 | +40% | 0 | 0 | — |
case-21 | fail→pass | 13,002 | 7,407 | -43% | 1 | 1 | 0% | 1,906 | 1,990 | +4% | 0 | 0 | — |
case-22 | fail→fail | 9,847 | 9,730 | -1% | 1 | 1 | 0% | 1,590 | 2,438 | +53% | 0 | 0 | — |
case-23 | pass→pass | 24,547 | 16,983 | -31% | 1 | 1 | 0% | 2,182 | 3,559 | +63% | 0 | 0 | — |
case-24 | pass→pass | 15,079 | 13,021 | -14% | 1 | 1 | 0% | 2,187 | 2,808 | +28% | 0 | 0 | — |
case-25 | pass→pass | 13,648 | 8,602 | -37% | 1 | 1 | 0% | 2,127 | 2,262 | +6% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +60 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.