BB btcd-skill-beta
Run the BTCD collateralization flow on PGP chain. Use when the user asks to run a BTCD loan, collateralization flow, create/take orders, lock BTC, submit proofs, claim BTCD tokens, or repay loans on the PGP network.
Run the BTCD collateralization flow on PGP chain.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- 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 · 11
✓ No critical or high findings
Medium and low: 11
-
low Secrets in code
secret-high-entropy-tokenscripts/.env.template.txt:7High-entropy token-like string (may be an id, hash or a credential)BTC_PRIVATE_KEY=<AGEN…FIX>
-
low Secrets in code
secret-high-entropy-tokenscripts/abi/ArbitratorManager.json:962High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"name": "regi…C20",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/arbiter-client.js:105High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)config.contracts.arbitratorManager || '0xcB…5E2',
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/config.js:21High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)loanContract: process.env.LOAN_CONTRACT_ADDRESS || '0x5c…91e',
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/config.js:22High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)issuer: process.env.ISSUER_CONTRACT_ADDRESS || '0x91…Fa7',
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/config.js:23High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)btcdToken: process.env.BTCD_TOKEN_ADDRESS || '0xF9…c6B',
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/config.js:24High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)arbitratorManager: process.env.ARBITRATOR_MANAGER_ADDRESS || '0x1f…ae0',
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/utils/config.js:25High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)stakingFactory: process.env.STAKING_FACTORY_ADDRESS || '0xaB…A36',
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:173High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Loan Contract | `0x5c…91e` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:174High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Issuer | `0x91…Fa7` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:175High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| BTCD Token | `0xF9…c6B` |
table
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1810 tokens
- 100Running it twice. Mutating operations check current state
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 215: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (13 code blocks)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.