impact-framework-bridge

Estrellas4

Forks0

Actualizado18 de julio de 2026 a las 15:25

Export Lean Agentic AI Skills findings into Green Software Foundation Impact Framework (IF) manifests — turning directional findings into a measurement plan that IF can compute with real observations. Use this skill whenever the user wants actual measured numbers — "what is our real carbon figure", "leadership wants a number, not directional language", an emissions value for a system — or mentions the Impact Framework / IF / impact manifests, asks how to go from this module's findings to measured carbon, or wants a measurement plan for audited systems. This skill is the module's route from directional findings to computed figures; qualitative summaries belong to sci-receipt. Part of Lean Agentic AI Skills; a transformer from lean-findings.json to IF manifest scaffolds.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Fuente

navveenb

navveenb/lean-agentic-ai-skills

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

2 archivos

SKILL.md

readonly

name

impact-framework-bridge

description

Impact Framework Bridge

Transformer skill — the principled answer to "so what's the actual number?". Input: one or more findings files. Output: an Impact Framework manifest scaffold (manifest.yml) + a measurement plan naming exactly which observations the user must supply.

The module's contract forbids invented numbers; the GSF Impact Framework (https://if.greensoftware.foundation/) is the open standard for computing real ones from observed usage. This skill connects the two layers: findings say where the impact levers are; the manifest says how to measure them.

Procedure

Map subjects to IF tree nodes. Each audited subject (website, service, pipeline) becomes a component in the manifest tree; findings' location fields seed the child structure.
Choose plugins per component from the IF ecosystem, matched to subject type: cloud instance metadata + energy coefficients for compute subjects, network/transfer coefficients for web subjects, grid-intensity plugins (Electricity Maps / WattTime via their IF plugins) to convert energy to carbon with the region from the findings. Name each plugin and why.
Declare required observations — the honest core of the output: a checklist of inputs IF needs that only the user can supply (utilization time series, transfer bytes from a real network trace, instance types, region, duration). Each maps back to the findings file's out_of_scope entries — the bridge literally converts "couldn't assess" into "here's how to observe it".
Wire findings to hypotheses. For each high-severity finding, add a manifest variant (before/after) so IF can compute the delta once the "after" observations exist — turning directional impact language into a testable measurement.
Emit the manifest scaffold with placeholder observations clearly marked # REQUIRED: supply from <source> — the scaffold must not run as-is, by design; a manifest that computes numbers from defaults would be exactly the invented figure the module refuses.

Honesty rules

The manifest ships non-runnable until real observations are pasted in — placeholders never carry default values that produce output. Coefficient-based estimates (which IF supports) are labeled as estimates with their coefficient source when the user chooses them over direct measurement. This skill teaches the distinction rather than hiding it.

Not this skill's job

Producing findings (producers), running IF or hosting its results (user's environment), region/schedule advice (region-selector, carbon-aware-scheduler).

Más de este repositorio

mismo repositorio

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

impact-framework-bridge

description

Impact Framework Bridge

Procedure

Map subjects to IF tree nodes. Each audited subject (website, service, pipeline) becomes a component in the manifest tree; findings' location fields seed the child structure.
Choose plugins per component from the IF ecosystem, matched to subject type: cloud instance metadata + energy coefficients for compute subjects, network/transfer coefficients for web subjects, grid-intensity plugins (Electricity Maps / WattTime via their IF plugins) to convert energy to carbon with the region from the findings. Name each plugin and why.
Declare required observations — the honest core of the output: a checklist of inputs IF needs that only the user can supply (utilization time series, transfer bytes from a real network trace, instance types, region, duration). Each maps back to the findings file's out_of_scope entries — the bridge literally converts "couldn't assess" into "here's how to observe it".
Wire findings to hypotheses. For each high-severity finding, add a manifest variant (before/after) so IF can compute the delta once the "after" observations exist — turning directional impact language into a testable measurement.
Emit the manifest scaffold with placeholder observations clearly marked # REQUIRED: supply from <source> — the scaffold must not run as-is, by design; a manifest that computes numbers from defaults would be exactly the invented figure the module refuses.

Honesty rules

Not this skill's job

Producing findings (producers), running IF or hosting its results (user's environment), region/schedule advice (region-selector, carbon-aware-scheduler).