SKILLEMALL.ai
GitHub ↗ RU Sign in

DB docx

Complete DOCX document creation, editing, and analysis capabilities with support for revisions, comments, formatting preservation, and text extraction. Also handles Word format conversion: legacy .doc → .docx, DOCX → PDF, DOCX → images (PNG/JPG) for visual review or previews, and DOCX → Markdown/plain text extraction. Use for creating new documents, modifying content, handling revisions, adding comments, other professional Word document tasks, or when the user asks to convert, export, or render a Word document to another format (e.g. 'Word转PDF', 'doc转docx', 'export this docx as PDF/images').

Not recommendedcritical or high security findings · low grade D
asgeirtj/system_prompts_leaks Agent Skills author: asgeirtj 24 files body ≈ 4 755 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Complete DOCX document creation, editing, and analysis capabilities with support for revisions, comments, formatting preservation, and text extraction.

As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, progress reporting

AnalyzerWordWriting and documentsData and analyticsResearchtype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
74/100
safety, quality, tests
Safety 60%
63
Quality 40%
90
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 3

  • high Dangerous commands cmd-install-from-url env_setup/setup.md:173
    Installs a package from an untrusted URL / archive
    python3 -m pip install -i https://pypi.tuna.tsinghua.edu.cn/simple \
  • high Dangerous commands cmd-install-from-url env_setup/setup.md:182
    Installs a package from an untrusted URL / archive
    python -m pip install -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn defusedxml
Medium and low: 1
  • low Dangerous commands cmd-execpolicy-bypass env_setup/setup.md:40
    Runs PowerShell with execution policy bypassed (documentation table row)
    | Windows | `powershell -ExecutionPolicy Bypass -File "$env:DOCX_SKILL_DIR\env_setup\setu…ps1"` |
    table

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 4755 tokens
  • 85Steps. 73 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 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 (3 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -213 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 598: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 73 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (7 of 10)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.