// Use when the user wants to extract parameters, modelling values, or key variables from a PlanExe report (HTML or text) for napkin math, triage, or Monte Carlo simulation
| name | extract-parameters-from-full |
| description | Use when the user wants to extract parameters, modelling values, or key variables from a PlanExe report (HTML or text) for napkin math, triage, or Monte Carlo simulation |
Wraps the quantitative-triage system prompt at system-prompt.txt (next to this file) and applies it to a PlanExe report the user supplies. Output is strict JSON matching the schema in the system prompt — no markdown, no commentary.
Not for: full report summarisation, narrative analysis, code generation. The system prompt explicitly forbids those.
system-prompt.txt (sibling of this SKILL.md). Treat its contents as the authoritative extraction instructions — every rule, hard limit, and schema constraint applies.system-prompt.txt. Apply every "Important", "Additional modelling rules", and "Formula and dependency rules" section as you generate each field.<report-basename>.parameters.json next to the report.unit: "fraction". Never value: 60 for 60%.formula_hint — every variable must be declared in key_values, missing_values_to_estimate, or the object's own depends_on.formula_hint MUST also declare output_name (snake_case id of the computed value) and output_unit (e.g. "DKK", "people", "fraction"). Downstream consumers — generate-calculations, run-scenarios, monte-carlo — read these directly and do not parse formula_hint or pattern-match on tokens. The LLM is the single authority for both fields.source_text — strip citations, footnote markers, replacement chars, UI artifacts.| Mistake | Fix |
|---|---|
Wrapping JSON in ```json fences | Raw JSON only — the system prompt forbids markdown |
| Returning >8 key_values "because the report has many" | Hard cap. Triage. The point is to surface the few that matter |
Including suggested_low/base/high by default | Only include when essential to the value's meaning |
Using value: 60 for "60%" | Use value: 0.6 and unit: "fraction" |
Citing variable in formula_hint that isn't declared anywhere | Either add it to missing_values_to_estimate or rewrite the formula |
| Picking a descriptive timeline value over a funding gate | Prefer the gate — it determines pass/fail |
system-prompt.txt/Users/neoneye/git/PlanExe-web/20250720_faraday_enclosure_report.htmlUse when the user wants to extract parameters from a PlanExe extraction-input digest (the markdown produced by experiments/napkin_math/prepare_extract_input.py — the 137-recommended section bundle, with the four "Keep or compress" sections compressed) instead of the full PlanExe HTML report
Use when the user wants to generate low/base/high assumption ranges (bounds) for missing or uncertain variables in a validated extract-parameters-from-full JSON, in preparation for deterministic scenarios or Monte Carlo
Use when the user wants to run the napkin-math pipeline end-to-end on a PlanExe report, or resume a partially populated output directory by filling in only the missing stages. Orchestrates digest preparation, parameter extraction, validation, bounds, calculations, scenarios, Monte Carlo, and assessment rendering. Never copies artifacts forward from prior runs, and never re-runs a stage whose output is already on disk.
Use after the napkin_math pipeline has produced parameters/bounds/scenarios/montecarlo JSON to generate a plan assessment (assessment.md) — a thin interpretation layer over the intermediary artifacts. Emits a JSON manifest, a provenance map, gate verdicts (Critical / Fragile / Marginal / Robust), failure drivers, confidence and trust boundaries, scenario sanity check, and suggested next actions. The artifact is a navigation/judgment file, not a copy of the raw simulation data.
Use after the napkin_math pipeline has produced parameters.json (from extract-parameters-from-digest or extract-parameters-from-full) to validate it against the 16 structural checks the rest of the pipeline assumes. Writes validation.json next to parameters.json. Deterministic Python — no LLM call.
Use when the user wants to turn a validated extract-parameters-from-full JSON into a Python module of deterministic functions implementing the formula_hint expressions for downstream scenario runs and Monte Carlo