BC compact-state
Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.
Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, 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.
For the model run — optional
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-wallet-secretsmolt-tools.js:319Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)storage: "Seed phrase stored locally by httpcat in ~/.httpcat/",
quoted -
low Risky intent
intent-wallet-secretsmolt-tools.js:321Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)backup: "The seed phrase is saved on your local filesystem. If your machine is wiped, the wallet is lost unless backed up.",
quoted -
low Risky intent
intent-wallet-secretsmolt-tools.js:323Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)recovery: "Run 'httpcat wallet show' to see your address. Run 'httpcat wallet export' to back up your seed phrase.",
quoted -
low Risky intent
intent-wallet-secretsmolt-tools.js:342Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)`Your private key and seed phrase are stored locally in ~/.httpcat/ on YOUR machine.\n` +
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 59/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 31 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1981 tokens
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 128: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.