DD pdf
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing. Routes automatically by document type and supports reports, posters, papers, resumes, extraction, merging, splitting, and form filling. Use this skill for any conversion whose output is a PDF: Office → PDF (.docx/.doc/.pptx/.ppt/.xlsx/.xls/.odt/.odp/.ods/.rtf/.csv/.txt → PDF), HTML → PDF, and LaTeX/.tex → PDF; also PDF → images, PDF → text, and PDF → tables when reading a PDF apart. Trigger when the user asks to convert, export, render, print, or turn a file into a PDF, or to merge/split/extract from one — including phrasings like 'Word转PDF', 'PPT转PDF', 'Excel转PDF', 'html转pdf', '导出为PDF', 'save/export as PDF', or 'PDF转图片/文字'.
Promises four workflows: PDF conversion from Office/HTML/LaTeX, text and table extraction, document splitting and merging with automatic routing. Two high-severity dangerous commands found in the codebase — execution can escape intended boundaries. Quality score 63, process score 44. Broken references in description. No sandbox run available.
Covers common tasks but security issues outweigh functionality. Don't install until the code is audited and tested in isolation.
The same skill from clawhub has been run on models: No improvement D see the result → This is a copy: its text may differ, so the grade is not carried over.
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
As a process D 44/100 · Unfinished process — References files that are not bundled: scripts/cover_render.py
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.
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.
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 5
-
high Dangerous commands
cmd-install-from-urlenv_setup/setup.md:210Installs a package from an untrusted URL / archivepython3 -m pip install -i https://pypi.tuna.tsinghua.edu.cn/simple \
-
high Dangerous commands
cmd-install-from-urlenv_setup/setup.md:231Installs a package from an untrusted URL / archivepython -m pip install -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn pikepdf pdfplumber pypdf reportlab PyMuPDF
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellbriefs/academic.md:999Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| macOS (binary) | `curl -sSL https://drop-sh.fullyjustified.net \| sh` |
table -
low Secrets in code
secret-high-entropy-tokenbriefs/poster.md:424High-entropy token-like string (may be an id, hash or a credential)| Handwritten | Zhan…n-2 | Via CDN | Casual, playful |
-
low Dangerous commands
cmd-execpolicy-bypassenv_setup/setup.md:40Runs PowerShell with execution policy bypassed (documentation table row)| Windows | `powershell -ExecutionPolicy Bypass -File "$env:PDF_SKILL_DIR\env_setup\setu…ps1"` |
table
Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 17851 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/cover_render.py - note
edit-residuethe text marks something as outdated (lines 749): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: scripts/cover_render.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 17851 tokens: crowds the task out of the window
- 60Steps. 49 steps, 6 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 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 The response is described with custom markup (17 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -215 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 765: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (21 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.