SKILLEMALL.ai
GitHub ↗ RU Sign in

CC docx-generation

Use when creating a Word DOCX report from Markdown, converting Markdown tables and lists to DOCX, or choosing a workflow for editing an existing DOCX while preserving its structure and styles. Use this workflow before running Markdown-to-DOCX shell commands. Includes report typography, table layout, a reusable reference document, and a Python converter.

The skillemall take

Promises to convert Markdown into DOCX while preserving tables, lists, and document styles. Seven files in the package: a Python converter, a template reference document, typography guidelines, and table layout instructions. Checks found ten medium and low severity issues—nothing critical, but minor problems exist. The skill wasn't tested on actual models. Code quality scores 82, process score 50. Runs on nine platforms including Claude and Cursor.

For routine report generation from Markdown, it works: the converter is there, structure is documented, typography is handled. Worth installing if you're willing to patch small bugs yourself—the skill hasn't been validated in real-world use.

aipoch/open-science Agent Skills author: aipoch 7 files · 4 scripts body ≈ 1 190 tokens Open the sourcegithub.com↗ analyzed 8 h ago

Use when creating a Word DOCX report from Markdown, converting Markdown tables and lists to DOCX, or choosing a workflow for editing an existing DOCX while…

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

GeneratorWordWriting and documentsData and analyticstype 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
C
87/100
safety, quality, tests
Safety 60%
90
Quality 40%
82
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • low Obfuscation obf-base64-blob kernel.py:4
      Long base64-looking blob (quoted — discussed, not commanded)
      'IyEv…GFy'
      quoted
    • low Obfuscation obf-base64-blob kernel.py:5
      Long base64-looking blob (quoted — discussed, not commanded)
      'ZCBs…3J0'
      quoted
    • low Obfuscation obf-base64-blob kernel.py:6
      Long base64-looking blob (quoted — discussed, not commanded)
      'IGpz…G9y'
      quoted
    • low Obfuscation obf-base64-blob kernel.py:7
      Long base64-looking blob (quoted — discussed, not commanded)
      'dCB0…Qpp'
      quoted
    • low Obfuscation obf-base64-blob kernel.py:8
      Long base64-looking blob (quoted — discussed, not commanded)
      'bXBv…XMu'
      quoted
    • low Secrets in code secret-high-entropy-token kernel.py:124
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      'YIhB…P2T+LxuI…l3w+rc3v…AAA'
      detector
    • low Secrets in code secret-high-entropy-token kernel.py:125
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'X3Jl…RpO+KCWe…F3m/VK+UyxKBhVtWg'
      quoted
    • low Secrets in code secret-high-entropy-token kernel.py:131
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'xUed…As6+AaLvUB2tca/pupOuBX0Y+03Q+L1xk…VtQ+1vZIbDhp/g'
      quoted
    • low Secrets in code secret-high-entropy-token kernel.py:132
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      '3ska…kmF/QuBTlXg/E4Qh…llY+UsS2…2lr'
      quoted
    • low Secrets in code secret-high-entropy-token kernel.py:137
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      'AdFK…fDq+7H7u…dPz/Ua0T…Mk8/+4+'
      quoted

    Files scanned: 7. 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 50/100

    • 0Result and completion. Does not say what the result is
    • 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 (bash, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 75Steps. 3 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1190 tokens
    • 100Running it twice. No mutating operations

    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)
    • +3Output format is not stated: the model decides each time
    • -32 of 3 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 355: enough signal without eating the budget
    • +4Structure: 4 headings
    • +3Step-by-step instructions: 3 items
    • +4Has examples (2 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.