nano-pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI.

2.61x

Quality

52%

Does it follow best practices?

Impact

81%

2.61x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/nano-pdf/SKILL.md

Quality

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 concise and identifies the core domain (PDF editing) and tool (nano-pdf CLI), but it lacks specificity about what kinds of edits are supported and completely omits a 'Use when...' clause. Without explicit trigger guidance and more concrete action examples, Claude would struggle to reliably select this skill from a large pool.

Suggestions

Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user wants to edit, modify, annotate, or update PDF files using natural language commands.'

List specific concrete actions the skill supports, e.g., 'Add text, remove pages, reorder pages, annotate, merge, or split PDF documents.'

Include natural keyword variations users might say, such as '.pdf files', 'modify PDF', 'change PDF content', 'PDF manipulation'.

Dimension	Reasoning	Score
Specificity	Names the domain (PDFs) and a general action (edit), and mentions the specific tool (nano-pdf CLI), but does not list multiple concrete actions like extracting text, filling forms, merging, etc.	2 / 3
Completeness	Describes what it does (edit PDFs) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also quite thin, bringing this to a 1.	1 / 3
Trigger Term Quality	Includes 'PDFs' and 'edit' which are natural terms, but misses common variations like '.pdf files', 'modify PDF', 'update PDF', 'PDF editing', or specific operations users might request.	2 / 3
Distinctiveness Conflict Risk	The mention of 'nano-pdf CLI' adds some distinctiveness and the focus on editing PDFs is reasonably specific, but 'edit PDFs' could overlap with other PDF-related skills that also handle modifications.	2 / 3
	Total	7 / 12 Passed

Implementation

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a concise, well-structured skill for a simple CLI tool. Its main weakness is limited actionability—only one example command is shown, and the validation/verification guidance is vague ('sanity-check the output') rather than concrete. Adding a second example and an explicit verification step would meaningfully improve it.

Suggestions

Add 1-2 more example commands showing different edit types (e.g., adding text, removing elements, modifying images) to improve actionability.

Replace the vague 'sanity-check the output PDF' note with a concrete verification step, such as a command to view or inspect the output (e.g., `open output.pdf` or a diff tool).

Dimension	Reasoning	Score
Conciseness	Very lean and efficient. Every line serves a purpose—no explanation of what PDFs are or how CLI tools work. The notes are practical and non-obvious (0-based vs 1-based page numbering gotcha).	3 / 3
Actionability	The example command is concrete and copy-paste ready, but there's only one example covering a single use case. Missing details like installation, error handling, supported edit types, or what happens with multi-page edits reduce completeness.	2 / 3
Workflow Clarity	The skill mentions sanity-checking the output but doesn't provide an explicit validation step or command. For a tool that destructively modifies PDFs, a clearer workflow with verification (e.g., opening the output, diffing pages) would be expected. The page-numbering retry note is helpful but ad hoc.	2 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with a clear quick start section and practical notes. No bundle files are needed.	3 / 3
	Total	10 / 12 Passed

Validation

72%

Warnings & errors only

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

Repository: deepgram/dglabs-deepclaw
Commit: ec8d4f8

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.