Running Shoe

The second non-software example — proof the tree is domain-agnostic.

18 capabilities 8 sections reference specification

Build against it

# give your agent the catalog — no account, no install
claude mcp add provespec -- npx -y provespec-mcp

# then, from any agent session
spec_get(slug: "running-shoe")                → the capability tree
spec_checklist(slug: "running-shoe")          → the questions to answer
spec_grade(slug: "running-shoe", grades: [...])  → parity % + the gap list

# or just fetch it
curl https://provespec.com/catalog/running-shoe/spec.json

Grade every capability below as yes · partial · no · na, with a file reference as evidence. Whatever you leave ungraded counts as missing — the gap list is the work queue.

Or just paste this to your agent

Use the ProveSpec MCP server. Fetch the "running-shoe" spec with
spec_get, then walk spec_checklist and grade this repository against it —
one verdict per capability, each with a file reference as the note.
Call spec_grade with the results and give me the gap list as the plan.

If the server is not registered, add it first:
  claude mcp add provespec -- npx -y provespec-mcp

The specification

Fit 4

✓ Size range and width options
✓ Toe box volume
✓ Heel hold and collar padding
✓ Upper material and breathability

Cushioning 4

✓ Stack height, heel and forefoot mm
✓ Drop mm heel minus forefoot
✓ Midsole foam and energy return
✓ Plate carbon, nylon, none

Ride 3

✓ Intended use daily, tempo, race, trail
✓ Stability features neutral versus supportive
✓ Ground feel versus isolation

Traction 2

✓ Outsole rubber coverage and lug depth
✓ Wet-surface grip

Durability 2

✓ Expected outsole life km
✓ Midsole compression over time

Weight 1

✓ Weight at a stated size g at US M9 always state the size

Care 1

✓ Washability and drying

Value 1

✓ Price and price per 100 km

Download spec.json All 53 specs