BD han-jr-system
小翰系统：1688平台自动化供应商联系系统。使用场景：用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。
小翰系统：1688平台自动化供应商联系系统。使用场景：用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Obfuscation
obf-hex-escape-chainscripts/inquiry_records.txt:52Escaped/char-code string obfuscationSupplier: cnalichn%E8%B4%9D%E5%8F%91%E9%9B%86%E5%9B%A2%E8%82%A1%E4%BB%BD%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8
-
medium Obfuscation
obf-hex-escape-chainscripts/inquiry_records.txt:64Escaped/char-code string obfuscationSupplier: cnalichn%E6%B8%A9%E5%B7%9E%E5%B8%82%E4%BD%90%E6%BE%9C%E5%93%B2%E6%96%87%E5%85%B7%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8
-
medium Obfuscation
obf-hex-escape-chainscripts/inquiry_records.txt:70Escaped/char-code string obfuscationSupplier: cnalichn%E5%B9%B3%E9%98%B3%E5%8E%BF%E4%BA%91%E7%A5%A5%E6%96%87%E5%85%B7%E5%8E%82
-
low Obfuscation
obf-hex-escape-chainscripts/results/鸭舌帽刺绣.json:36Escaped/char-code string obfuscation (quoted — discussed, not commanded)"link": "https://r.1688.com/auth/fcaReport.htm?_input_charset=utf8&loginId=…"
quoted
Files scanned: 80. 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 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 92 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2777 tokens
- 100Running it twice. No mutating operations
- low 13 top-level sections: this looks like several domains in one skill
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)
- +3Description length 110: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -342 of 51 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 47 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (23 code blocks)
- +4Reference files are cited in the instructions (4 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.