SKILLEMALL.ai
GitHub ↗ RU Sign in

DF kingdoc

(no description)

ClawHub Agent Skills author: fyniujin v4.3.5 MIT-0 80 files · 63 scripts body ≈ 11 901 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

本版本针对第三方评测（综合 4.5/5「优秀」）的降分项做了逐项闭环： 本地生成文档、本地 OCR、硬件画像完全不需要 Key，开箱即用。

As a process F 29/100 · No process to follow — References files that are not bundled: references/user_blacklist.txt, references/user_whitelist.txt, references/sensitive_words.txt

IntegrationWordPowerPointData and analyticsAI and agentsCustomer supporttype 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
D
61/100
safety, quality, tests
Safety 60%
94
Quality 40%
11
Run on models
none yet
Process rating
F
29/100
No process to follow
References files that are not bundled: references/user_blacklist.txt, references/user_whitelist.txt, references/sensitive_words.txt
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Add a description to the frontmatter: without it the skill never triggers.
  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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-persistence engine/compliance_scheduler.py:113
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    sch = (f'schtasks /create /tn "{task_name}" '
    code literal
  • low Dangerous commands cmd-cron-mention engine/compliance_scheduler.py:127
    Mentions editing / listing crontab (string literal in code, not executed)
    "note": "非 Windows 系统：将上方 cron 行加入 crontab（crontab -e）即可周扫。"}
    code literal

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-missing SKILL.md: no `description` — the skill can never trigger
  • warning body-long SKILL.md body ≈ 11901 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/user_blacklist.txt
  • warning missing-ref reference to a missing file: references/user_whitelist.txt
  • warning missing-ref reference to a missing file: references/sensitive_words.txt
  • warning missing-ref reference to a missing file: assets/icon.png
  • warning missing-ref reference to a missing file: references/workflows.md

Process rating: all ten parameters 29/100

Will not run. References files that are not bundled: references/user_blacklist.txt, references/user_whitelist.txt, references/sensitive_words.txt
  • 0Tools and files. 5 referenced file(s) missing: references/user_blacklist.txt, references/user_whitelist.txt, references/sensitive_words.txt
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 23 mutating operations with no state check
  • 40Execution cost. Instruction body is 11901 tokens: crowds the task out of the window
  • 100Steps. 128 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 52 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 0: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -286 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 170 headings
  • +3Step-by-step instructions: 128 items
  • +4Has examples (42 code blocks)
  • +4Reference files are cited in the instructions (8 of 8)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 11.

External checks

ClawHub: suspicious
This skill is a coherent document automation tool, but it asks for secrets in chat and gives the agent powerful cloud document, webhook, and memory access without enough enforced safeguards.
LLM: suspicious (high) · 11 Oct 2026