agentleFS
jordan-partstradejordan-partstrade/trade-agent-skills/skills/freight-estimator/SKILL.md

freight-estimator

Skill0 starsChanged 47 days agoMITView on GitHub

Estimate auto-parts freight from confirmed cartons or explicit packing references, using vehicle body type, size and part category to rank references. Calculate kg or CBM billing with supplied carrier terms. Use for freight arithmetic and packing-data preparation, not live rates or carrier booking.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the standard-library script scripts/estimate_freight.py for confirmed carton measurements.

    line 8
  2. Very specific:

    Run relative to this skill folder, or substitute the absolute script path.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Freight estimates

Use the standard-library script scripts/estimate_freight.py for confirmed carton measurements. Use scripts/prepare_shipment.py when you have vehicle/part context and explicit packing references; do not invent reference dimensions from a product name.

Before arithmetic: vehicle and packing evidence

Separate body_type (sedan, hatchback, suv, mpv, pickup, van, truck, bus, other, unknown) from size_class (compact, medium, large, oversize, unknown). Confirm exact model/year/variant and dimensional evidence when relevant; the script does not retrieve vehicle specifications or infer compatibility.

The preparation script can group supplied overall vehicle dimensions [length,width,height] in mm: compact up to 4500×1850, medium up to 4900×1950, large up to 5500×2100, otherwise oversize (length and width both must fit). Height remains context. These are explicit operational reference bins, not official market segments, legal limits or carton measurements. Without dimensions, a supplied size class is an assumption; do not present it as independently verified.

Evidence order: supplied packed cartons > unique exact-OE packing record > explicitly selected same-model/platform record > explicitly selected similar body/size record for size-sensitive parts. Similar body/size applies only to bumper covers/beams, hoods, doors, fenders, windshields and long trim. Small sensors and other small parts do not automatically become larger because the vehicle is an SUV.

Records must specify source, part type, units per carton, carton sides in cm and gross kg. A unique exact-OE reference can be selected automatically; model/platform/similarity matches and ambiguous records require reference_id. Every reused record remains an estimate for the new shipment. Partial cartons retain full reference dimensions/weight as a conservative assumption. Consolidation, folding, stacking and nesting are not inferred.

python scripts/prepare_shipment.py vehicle-input.json --output shipment.json
python scripts/estimate_freight.py shipment.json

See examples/vehicle-shipment.json in the repository; it is entirely fictional. Preparation reports candidates, selected sources and unresolved lines. If any line lacks packing evidence, it exits with code 2 and writes no shipment file. Do not silently omit unresolved goods or turn missing evidence into zero freight.

python scripts/estimate_freight.py shipment.json

Run relative to this skill folder, or substitute the absolute script path. See examples/freight.json and examples/freight-sea.json in the repository for fictional inputs.

Required inputs

  • rate_unit: kg or cbm; rate: a positive supplied rate; currency: uppercase three-letter code.
  • rate_source: identify the quote or reference used. This tool contains no live or historical rate table.
  • cartons: one object per carton group, with dimensions_cm: [L,W,H], gross_weight_kg, dimensions_source (measured, supplier, estimate) and optional integer count (identical cartons).
  • For kg billing, divisor_cm3_per_kg must be supplied from the carrier's terms. rounding_step_kg defaults to 1 and applies per carton; override when the carrier differs.

Optional carrier terms

minimum_billable_units is a shipment-level floor in kg or cbm. minimum_charge is a shipment-level monetary floor. surcharge_percent applies to the base after that monetary floor; flat_surcharge is added afterward, once per shipment. Supply a total flat surcharge yourself when fees are per carton; the script does not infer carrier rules.

max_length_cm and max_length_plus_girth_cm only flag size-limit breaches. They do not approve shipment or price oversize fees. Length plus girth is the longest side plus twice each other side.

Interpret correctly

Missing rates and invalid dimensions fail, rather than returning a zero quote. All results remain estimates; tax, clearance, delivery and unlisted fees are excluded. Verify carrier acceptance, current rates, minima and surcharges before treating the result as a quote. This tool does not guess carton arrangements, fitment, exchange rates or transit time.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.