Edit PDFs with natural-language instructions using the nano-pdf CLI.
68
Quality
60%
Does it follow best practices?
Impact
81%
2.61xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/nano-pdf/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is too brief and lacks explicit trigger guidance. While it identifies the domain (PDFs) and tool (nano-pdf CLI), it fails to specify concrete editing capabilities and provides no 'Use when...' clause to help Claude distinguish when to select this skill over alternatives.
Suggestions
Add a 'Use when...' clause with trigger terms like 'edit PDF', 'modify PDF', 'change PDF content', 'update PDF'
List specific editing capabilities (e.g., 'add/remove pages, edit text, insert images, annotate') instead of generic 'edit'
Include natural keyword variations users might say: '.pdf files', 'PDF document', 'modify PDF'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PDFs) and mentions a tool (nano-pdf CLI), but 'edit' is a single vague action without listing specific capabilities like extracting text, merging, filling forms, etc. | 2 / 3 |
Completeness | Describes what (edit PDFs) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'PDFs' and 'edit' which are relevant, but misses common variations users might say like '.pdf files', 'modify PDF', 'change PDF', 'PDF editing', or specific operations. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'nano-pdf CLI' adds some distinctiveness, but 'edit PDFs' is generic enough to potentially conflict with other PDF-related skills without clear differentiation. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides immediately actionable guidance for using nano-pdf. Its main strength is token efficiency and clear executable example. The only weakness is the somewhat vague validation guidance ('sanity-check') which could be more specific about what to verify.
Suggestions
Make the validation step more concrete, e.g., 'Open the output PDF and verify the edit was applied to the correct page and the rest of the document is intact'
Consider adding a specific command or method for checking the output, such as viewing with a PDF reader or using a diff tool
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean - no unnecessary explanation of what PDFs are or how the tool works internally. Every line serves a purpose and assumes Claude's competence. | 3 / 3 |
Actionability | Provides a complete, copy-paste ready command with realistic example arguments. The command syntax is immediately executable. | 3 / 3 |
Workflow Clarity | For a simple single-command skill, the workflow is clear, but the validation step ('sanity-check the output') is vague rather than explicit. The page numbering ambiguity note is helpful but the retry guidance is informal. | 2 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with a single task, the content is appropriately structured with a quick start section and relevant notes. No external references needed for this scope. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
50ef2f3
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.