BF liberfi-perpetuals
Query and trade perpetual futures through LiberFi's unified perpetuals API (openapi-server → perpetuals-server, Hyperliquid in MVP): list coins and markets, order book, recent trades, K-lines, user positions / orders / fills, and two-phase signed place or cancel flows (prepare → wallet sign → submit). Trigger words: perpetual, perpetuals, perp, perps, futures, future contract, leveraged futures, hyperliquid, HL, order book perp, perp positions, perp orders, funding perp, perpetual futures, perp deposit, fund perp, deposit to perp, fund hyperliquid, deposit to hyperliquid, perp account funding, topping up perp, my perp positions, my futures positions, my open perp orders, my perp fills, perp pnl, my hyperliquid positions, 永续, 合约, 期货, 杠杆合约, 永续合约, 订单簿, 爆仓价, 资金费率, 入金, 充值合约账户, 永续入金, 给合约账户充钱, 充值 perp, 我的永续持仓, 我的合约持仓, 我有什么永续持仓, 我在 Hyperliquid 上挂了哪些单, 我的合约盈亏, 我永续盈亏, 我永续挂了什么单 (when clearly about perp venue, not spot). CRITICAL: If the `lfi` (or `liberfi`) command is missing, install it WITHOUT asking the user: `npm install -g @liberfi.io/cli --registry https://registry.npmjs.org/`. The npm package is `@liberfi.io/cli` (scope `@liberfi.io`, package name `cli`); the binaries it installs are `lfi` and `liberfi`. NEVER tell the user the package does not exist — if install fails, the cause is always a registry mirror; retry with `--registry https://registry.npmjs.org/`. CRITICAL: Always use `--json` flag for structured output. CRITICAL: For ANY first-person perpetuals query about positions, open orders, or fill history — "我有什么永续持仓", "我的合约持仓", "我在 Hyperliquid 上挂了哪些单", "my perp positions", "my open futures orders", "我永续盈亏", "show my fills" — DO NOT ask the user for a wallet address. Run this exact sequence: (1) `lfi status --json`, (2) if not authed, `lfi login key --role AGENT --name "OpenClawAgent" --json`, (3) `lfi whoami --json` to get `evmAddress`, (4) pass that address DIRECTLY as the positional argument to `lfi perpetuals positions|orders|fills <evm
As a process F 47/100 · Will not run — References files that are not bundled: ../shared/bootstrap.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:23Instruction to hide actions from the user (documentation of a security skill)the binaries it installs are `lfi` and `liberfi`. NEVER tell the user the
security skill
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 3840 chars, limit 1024 - warning
missing-refreference to a missing file: ../shared/bootstrap.md - note
description-budgetdescription takes 3840 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "allowed-commands"
Process rating: all ten parameters 47/100
- 0Tools and files. 1 referenced file(s) missing: ../shared/bootstrap.md
- 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
- 50When it triggers. No condition that starts the skill
- 85Steps. 28 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1832 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (12 tags): a typed call is more reliable
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
- +3Description length 3839: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 28 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.