lean-education-builder

Stars4

Forks0

UpdatedJuly 18, 2026 at 15:25

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.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

navveenb

navveenb/lean-agentic-ai-skills

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Postsecondary Teachers, All OtherEducational Instruction and Library Occupations·SOC 25-1199

File Explorer

2 files

SKILL.md

readonly

name

lean-education-builder

description

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).

More from this repository

same repository

agentic-loop-auditor

navveenb/lean-agentic-ai-skills

Audit agent frameworks and agentic workflows for token-burning loop pathologies — unbounded retries, excessive planning depth, tool-call thrashing, context snowballing, missing loop budgets and kill switches. Use this skill whenever the user shares agent configs or traces (LangChain/LangGraph, CrewAI, AutoGen, custom loops), complains an agent is slow or expensive, or is designing any autonomous/multi-step agent. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

ai-eval-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit AI evaluation infrastructure for wasted compute — full benchmark suites re-run on unchanged cases, LLM-as-judge grading without caching, oversized judge models, redundant eval passes per commit, and missing result reuse. Use this skill whenever the user shares eval harness configs or CI eval steps, complains that evals are slow or expensive, mentions LLM-as-judge costs, or runs benchmark suites on every change. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

api-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit API design for chattiness and over-fetching — REST endpoints requiring N calls per screen, GraphQL resolvers with N+1 fan-out, default-everything payloads, missing pagination and field selection, provider-side polling where webhooks serve, and uncompressed responses. Use this skill whenever the user shares API schemas (OpenAPI, GraphQL SDL), resolver code, endpoint designs, or asks why clients make too many calls or payloads are heavy. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

caching-strategy-designer

navveenb/lean-agentic-ai-skills

Design caching layers so work is done once, not per request — HTTP/CDN caching, application-level caches (Redis/Memcached), computed-result caching, and cache-invalidation strategy. Use this skill whenever the user wants to add caching, asks why the same work is recomputed, designs a read-heavy system, or an audit skill (db-efficiency-audit, web-carbon-audit) flags uncached repeated work. Part of Lean Agentic AI Skills; emits a cache design plus lean-findings.json.

2026-07-184

carbon-aware-scheduler

navveenb/lean-agentic-ai-skills

Design time-shifting of flexible workloads (batch jobs, CI, training, backups, crons) to hours and regions when grid electricity is cleanest, using carbon-intensity signals like Electricity Maps, WattTime, or the Carbon Aware SDK. Use this skill whenever the user mentions carbon-aware computing, scheduling flexible/deferrable jobs, demand shifting, running workloads when energy is clean, or asks how to reduce the carbon intensity (not just amount) of their compute. Part of Lean Agentic AI Skills; emits schedule designs plus lean-findings.json.

2026-07-184

carbon-budget-designer

navveenb/lean-agentic-ai-skills

Design per-feature and per-service efficiency budgets — page-weight budgets, token budgets per AI feature, query budgets per endpoint, GPU-hour budgets per training project — with owners, review checkpoints, and enforcement hooks. Use this skill whenever the user wants sustainability targets for teams, asks how to keep efficiency from regressing organizationally, mentions performance-budget-style governance for carbon/energy, or is setting engineering standards. Part of Lean Agentic AI Skills; an advisor emitting budget definitions plus lean-findings.json.

2026-07-184

name

lean-education-builder

description

Green Education Builder

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

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).