| name | lean-education-builder |
| description | Turn audit findings into team learning material — workshop outlines, lunch-and-learn decks, onboarding modules, and quizzes built from your own codebase's real findings. Use this skill whenever the user wants to teach their team green/efficient practices, asks for training or workshop content from audit results, wants engineering onboarding to cover efficiency, or says "help the team learn from this". Consumes lean-findings.json from any Lean Agentic AI Skills audit; never audits anything itself. |
Green Education Builder
Pure consumer skill — the organizational-change layer. Input: one or more findings files (the more real, the better) plus audience (new joiners / whole team / leads) and format (workshop, deck, onboarding doc, quiz). Output: the learning artifact.
Audits change code; education changes the next thousand decisions. Generic sustainability training bounces off engineers — but a workshop built from your own repo's findings ("this N+1 storm is in our orders service, here's the actual query log") lands, because every example is one the team can go fix this sprint.
Prerequisites (platform-aware): for deck/doc output, use your environment's document skills where present (e.g. Claude's pptx/docx skills under /mnt/skills/public/); on other platforms use available document tooling. Deck styling follows lean-deck-builder's ink-light rules everywhere.
Formats
- Workshop outline (60–90 min) — arc: one warm-up concept (the three-symptoms framing: energy, cost, carbon), then 3–4 findings from the team's own audit as worked examples (issue → evidence → let the room propose the fix → reveal the finding's fix), then a hands-on block (attendees run one skill on a service they own), closing with the quick-wins list as the take-home sprint candidates.
- Lunch-and-learn deck (20 min) — one pattern deep-dive: the single most frequent finding family from the findings (or portfolio-aggregator output), taught through the local example, ending with the pattern's GSF source link.
- Onboarding module — the honesty rules and the team's budgets (from carbon-budget-designer if present) as "how we work here", with the current dashboard/findings as the living state new joiners inherit.
- Quiz — 6–10 questions generated from findings: show real evidence, ask which pattern it violates and which fix applies; distractors drawn from neighboring skills' patterns so wrong answers teach boundaries too.
Rules
- Real findings only. Examples come from the supplied findings files, verbatim evidence included. If no findings exist for a topic the user wants taught, say so and suggest running the audit first — invented "example findings" would violate the module's core rule inside its own classroom.
- Methodology gets taught, not skipped. Every format includes one honest segment: what audits can claim (counted, directional) and what needs measurement — the honesty rules are the curriculum's spine, not a disclaimer.
- Credit the
passed list. Teams learn better from "here's what we already do well" than pure deficit framing; every workshop opens with it.
- No shaming. Findings are anonymized to services, not authors; the audit is about the system.
- Effort-honest exercises. Hands-on blocks use low-effort quick wins so attendees experience a completed fix, not a stalled one.
Cost signal rendering
Where findings carry cost_signal, teach with it: "this finding's driver is prompt tokens per call — currently 370, counted" makes the business case part of the lesson. The three-axis split (energy and carbon directional, cost counted) is itself teaching material.
Not this skill's job
Producing the findings (any producer), stakeholder reporting (lean-deck-builder, lean-report-writer), setting the budgets it teaches (carbon-budget-designer), tracking remediation (lean-dashboard).
