impact-framework-bridge

name

impact-framework-bridge

description

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.

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

1. 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.
2. 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.
3. 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".
4. 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.
5. 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).