BB canopy
Canopy treasury wallet for AI agents — make policy-gated USD payments on-chain (Base), auto-pay paywalled APIs (x402 / MPP), and discover paid services. Every payment passes through the agent's policy: spend cap, recipient/service allowlist, and approval threshold. Payments above the threshold return pending_approval and wait for a human; payments outside the cap or allowlist return denied. Install only if your agent needs to spend org funds. Connect with the least-privileged agent + policy available, verify recipient and amount before each canopy_pay, and never auto-approve on the user's behalf. Requires a Canopy account at https://www.trycanopy.ai. After install, configure the canopy MCP server with your CANOPY_API_KEY and CANOPY_AGENT_ID from the dashboard.
As a process B 72/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:115High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**User:** "Pay 50 cents to 0x48…f97"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:116High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)→ `canopy_pay({ to: "0x48…f97", amountUsd: 0.50 })`. Surface `txHash` if `allowed`.quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1579 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 770: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.