SKILLEMALL.ai
GitHub ↗ RU Sign in

DD legal-translation

Translate legal documents from any language into English while preserving .docx formatting and translating track changes and headers/footers. Use this skill whenever the user asks to translate a legal document, contract, deed, agreement, or any formal legal text into English. Also trigger when the user mentions translating .docx files that contain legal content, or asks for a "format-preserving translation" of a legal document. This skill covers all legal domains: finance, M&A, corporate, IP, real estate, regulatory, consumer, taxes, litigation, SaaS and more. Even if the user just says "translate this contract" or "translate this into English", use this skill if the document is legal in nature.

Not recommendedcritical or high security findings · low grade D
lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 80 files · 20 scripts body ≈ 14 016 tokens Open the sourcegithub.com↗ analyzed 71 min ago

Translate legal documents from any language into English while preserving .docx formatting and translating track changes and headers/footers. Use this skill…

As a process D 43/100 · Unfinished process — References files that are not bundled: references/<domain>.md, references/*.md

ProcedureWordWriting and documentstype 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
75/100
safety, quality, tests
Safety 60%
81
Quality 40%
66
Run on models
none yet
Process rating
D
43/100
Unfinished process
References files that are not bundled: references/<domain>.md, references/*.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Obfuscation
If you install

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.

For the author

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

  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.
  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

  • high Obfuscation uni-zero-width skill-docs/04-translate.md:725
    Zero-width / invisible characters (possible hidden text) (12 occurrences)
    fix is the visible-space + ZWSP hybrid in Rule 1: `" ␀"` after a
Medium and low: 1
  • low Risky intent intent-offensive-security references/ip-it-technology.md:287
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | penetration test | Authorized security test attempting to find vulnerabilities | Pen test; Security penetration assessment |

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 14016 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/<domain>.md
  • warning missing-ref reference to a missing file: references/*.md

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: references/<domain>.md, references/*.md
  • 0Tools and files. 2 referenced file(s) missing: references/<domain>.md, references/*.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 12 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (legal-translation) differs from the folder (en-uk-legal-translation-wouter-van-den-berg)
  • 40Execution cost. Instruction body is 14016 tokens: crowds the task out of the window
  • 60Steps. 82 steps, 9 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 9 branches, has a failure section
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -31 of 20 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 704: enough signal without eating the budget
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 82 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (4 of 15)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.