SKILLEMALL.ai
RU Sign in

BF 1688-alibaba-data-fetcher

1688卖家工作台数据抓取：原生聊天用MEDIA、飞书必须用message；登录必须同回合内持续poll。

ClawHub Agent Skills author: howerlin0329 v1.0.2 MIT-0 26 files · 7 scripts body ≈ 5 162 tokens Open the sourceclawhub.ai↗ analyzed 26 h ago

1688卖家工作台数据抓取：原生聊天用MEDIA、飞书必须用message；登录必须同回合内持续poll。

As a process F 31/100 · Will not run — References files that are not bundled: scripts/.feishu_token.json

ProcedureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
96
Quality 40%
48
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: scripts/.feishu_token.json
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: 1688-alibaba-data-fetcher (ClawHub)

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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 Exfiltration exfil-secret-in-url plugin/content.js:130
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    const apiUrl = `https://h5ap…com/h5/mtop.alibaba.cbu.workdiordatareaderservice.getvaluesfromgateway/1.0/?jsv=2.7.2&appKey=…&t=…&sign=…&api=…
    placeholder
  • low Exfiltration exfil-secret-in-url plugin/content.js:167
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    const apiUrl = `https://h5ap…com/h5/mtop.alibaba.cbu.workdiordatareaderservice.getvaluesfromgateway/1.0/?jsv=2.7.2&appKey=…&t=…&sign=…&api=…
    placeholder
  • low Obfuscation obf-base64-blob plugin/manifest.json:6
    Long base64-looking blob (quoted — discussed, not commanded)
    "key": "MIIB…6CE+BGEB…WEF+rhbE…CLF+/b9nE…JLf/3B4c…gOD
    quoted
  • low Dangerous commands cmd-execpolicy-bypass scripts/login.py:56
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    cmd = f'powershell -ExecutionPolicy Bypass -File "{script}"'
    quoted

Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5162 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/.feishu_token.json

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: scripts/.feishu_token.json
  • 0Tools and files. 1 referenced file(s) missing: scripts/.feishu_token.json
  • 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
  • 30Running it twice. 14 mutating operations with no state check
  • 70Execution cost. Instruction body is 5162 tokens
  • 100Steps. 59 steps
  • 100Consistency. Name and required fields are in place
  • low 10 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 53: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -242 emoji in the instructions: noise for the model
  • -31 of 14 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 59 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.

External checks

ClawHub: suspicious
The skill is broadly purpose-aligned, but it handles sensitive seller analytics through overbroad extension access and recurring outbound reporting that should be reviewed carefully.
LLM: suspicious (high) · 14 Jul 2026