CF liberfi-predict
Browse and trade prediction markets: list events with filtering and search, view event details and embedded markets, check USDC balances on Kalshi and Polymarket, view portfolio positions and trade history, list and inspect orders, request Kalshi quotes, submit signed Kalshi transactions, and create Polymarket orders. Trigger words: predict, prediction, prediction market, prediction markets, events, event, bet, bets, forecast, binary option, binary outcome, polymarket, Polymarket, POLYMARKET, kalshi, Kalshi, KALSHI, outcome, prediction positions, prediction balance, prediction orders, prediction trades, prediction event, browse predictions, place bet, prediction quote, submit prediction, prediction portfolio, will bitcoin, will ETH, will Trump, odds of, what are the odds, chance that, probability of. Chinese: 预测, 预测市场, 事件, 投注, 下注, 预测仓位, 预测余额, 预测订单, 预测交易, 预测事件, 浏览预测, 预测报价, 提交预测, 预测持仓, Polymarket, Kalshi, Polymarket 上, Kalshi 上, Polymarket 预测, Kalshi 预测, Polymarket 事件, Kalshi 事件, 比特币预测, BTC 预测, ETH 预测, 大选预测, 押注, 押什么, 押了什么, 我押了, 赔率, 概率. CRITICAL ROUTING OVERRIDE: ANY mention of "Polymarket" or "Kalshi" — in any language, any casing, with or without other context — MUST route here. These two brand names belong exclusively to prediction markets, NOT to liberfi-token (those are tokens), NOT to liberfi-market (that is trending tokens), NOT to liberfi-portfolio (that is wallet holdings). Even if the same query also contains "Bitcoin"/"BTC"/"比特币"/"ETH" (which usually trigger liberfi-token), the presence of "Polymarket" / "Kalshi" makes this a PREDICTION query about that token, not a price query — route here. 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 i
As a process F 55/100 · Will not run — References files that are not bundled: ../shared/bootstrap.md, ../shared/security-policy.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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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:36Instruction 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 5213 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5893 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../shared/bootstrap.md - warning
missing-refreference to a missing file: ../shared/security-policy.md - note
description-budgetdescription takes 5213 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "allowed-commands"
Process rating: all ten parameters 55/100
- 0Tools and files. 2 referenced file(s) missing: ../shared/bootstrap.md, ../shared/security-policy.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70Execution cost. Instruction body is 5893 tokens
- 100Steps. 154 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 15 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (54 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 5212: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 28 headings
- +3Step-by-step instructions: 154 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 42.