demand-shaping-designer

스타4

포크0

업데이트2026년 7월 18일 15:25

Design carbon-responsive experience tiers — gracefully reducing quality or deferring non-essential features when grid carbon intensity is high (eco modes, adaptive quality, deferred background work), the demand-shaping half of carbon-aware design. Use this skill whenever the user wants an eco mode, asks how the product itself can respond to dirty-grid hours, mentions demand shaping or carbon-aware UX, or wants the product experience itself to respond to grid conditions. Part of Lean Agentic AI Skills; emits a shaping design plus lean-findings.json.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

출처

navveenb

navveenb/lean-agentic-ai-skills

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Demand Shaping Designer

Advisor skill — the other half of carbon-awareness. carbon-aware-scheduler moves when work runs; this skill designs how the product does less when the grid is dirty, moving I and E together. The canonical mental model: video calls dropping resolution under low bandwidth — same idea, carbon signal instead of network signal.

Subject type: emit subject.type: "architecture" in findings.

Design procedure

Inventory shapeable experience dimensions. For each product surface: quality tiers (media resolution/bitrate, generation quality, sync frequency, prefetch depth, animation richness, model tier for AI features), and deferrable work (non-urgent notifications, feed pre-computation, speculative prefetch, background enrichment).
Classify by user impact: invisible (prefetch depth, background enrichment — shape freely), degraded-but-acceptable (media quality step-down, less frequent refresh — shape with disclosure), and core value (never shape; list explicitly so the design has a floor).
Pick the signal and thresholds — same sources as carbon-aware-scheduler (references/grid-data-sources.md there): regional intensity with two or three bands (normal / elevated / high), hysteresis so the experience doesn't flap at band edges, and a user's region resolved coarsely (privacy note: country/grid-zone granularity suffices; never precise location for this).
Design the transparency layer. Silent shaping of visible dimensions erodes trust; the design includes user-facing framing (an eco indicator, a setting to opt out or always-on) — eco mode as a feature users can be proud of, not a stealth downgrade. Default-on is defensible only for the invisible tier.
Emit the shaping matrix (dimension × band × behavior), the findings file (unshaped-but-shapeable dimensions as findings), and the measurement hook: shaped-vs-unshaped served ratios are countable and should be dashboarded.

Trade-offs to always name

User experience is the product — shaping visible dimensions trades satisfaction, and the classification step exists to protect that. Engineering complexity of tiered behavior is real (test matrix grows). Rebound honesty: shaping reduces intensity-weighted consumption; it is not license to grow baseline usage and call it green.

Not this skill's job

Time-shifting backend jobs (carbon-aware-scheduler), the media encoding ladder itself (video-streaming-optimizer), choosing regions (region-selector).

이 저장소의 다른 Skills

같은 저장소

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

demand-shaping-designer

description

Demand Shaping Designer

Subject type: emit subject.type: "architecture" in findings.

Design procedure

Inventory shapeable experience dimensions. For each product surface: quality tiers (media resolution/bitrate, generation quality, sync frequency, prefetch depth, animation richness, model tier for AI features), and deferrable work (non-urgent notifications, feed pre-computation, speculative prefetch, background enrichment).
Classify by user impact: invisible (prefetch depth, background enrichment — shape freely), degraded-but-acceptable (media quality step-down, less frequent refresh — shape with disclosure), and core value (never shape; list explicitly so the design has a floor).
Pick the signal and thresholds — same sources as carbon-aware-scheduler (references/grid-data-sources.md there): regional intensity with two or three bands (normal / elevated / high), hysteresis so the experience doesn't flap at band edges, and a user's region resolved coarsely (privacy note: country/grid-zone granularity suffices; never precise location for this).
Design the transparency layer. Silent shaping of visible dimensions erodes trust; the design includes user-facing framing (an eco indicator, a setting to opt out or always-on) — eco mode as a feature users can be proud of, not a stealth downgrade. Default-on is defensible only for the invisible tier.
Emit the shaping matrix (dimension × band × behavior), the findings file (unshaped-but-shapeable dimensions as findings), and the measurement hook: shaped-vs-unshaped served ratios are countable and should be dashboarded.

Trade-offs to always name

Not this skill's job

Time-shifting backend jobs (carbon-aware-scheduler), the media encoding ladder itself (video-streaming-optimizer), choosing regions (region-selector).