nano-pdf

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

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/nano-pdf/SKILL.md

The canonical home for this skill is nano-pdf in Hung-Reo/hungreo-openclaw

Quality

Content

87%Weight 40%Scale 1-5

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

An exemplary lean single-command skill: fully executable example, no padding, and well-organized sections for a skill of this size. The only weakness is that the destructive edit operation's validation step is a vague 'sanity-check' note rather than a concrete checkpoint.

Suggestions

Make the verification concrete, e.g. 'Verify: nano-pdf render deck.pdf 1 to view the edited page before sending it out' or an equivalent check command.

Show how to detect the off-by-one case concretely (e.g. inspect the returned page image/text) so the retry loop is actionable rather than heuristic.

Dimension	Reasoning	Score
Conciseness	The body is six lines with zero padding: a one-line purpose statement ("Use `nano-pdf` to apply edits to a specific page in a PDF"), a single command, and two terse operational notes. No concepts Claude already knows are explained, matching 'Lean and efficient; every token earns its place'.	5 / 5
Actionability	The Quick start gives a fully executable, copy-paste-ready command with a realistic instruction ("Change the title to 'Q3 Results' and fix the typo in the subtitle") that covers the skill's single common case, matching the top anchor. It is not 4 because there is no gap — the exact CLI invocation is shown with arguments in order.	5 / 5
Workflow Clarity	Editing a PDF is a destructive/mutating operation, and the only validation is the vague "Always sanity-check the output PDF before sending it out" with no concrete checkpoint; the off-by-one retry note ("if the result looks off by one, retry with the other") is a partial feedback loop. This matches 'sequence present but checkpoints missing or implicit' and the destructive-operation cap of 3. Not 4 because no concrete verification method is given.	3 / 5
Progressive Disclosure	This is a simple, under-50-line, single-purpose skill with no need for external references; the body is well organized into a purpose line, a Quick start section, and a Notes list, which per the rubric's simple-skill guideline earns a 5. No bundle files exist to reference.	5 / 5
	Total	18 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 names a concrete, distinct capability, but it only covers a single action and provides no 'when to use' guidance or trigger synonyms. Adding a 'Use when...' clause and a few natural trigger terms would lift completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to change, fix, or update text in a PDF without editing it by hand.'

Broaden the action coverage slightly (e.g. 'edit text, fix typos, update titles and labels on specific pages') to raise specificity.

Include natural trigger variations such as 'PDF files', '.pdf', and 'make changes to a PDF' for better keyword coverage.

Dimension	Reasoning	Score
Specificity	"Edit PDFs with natural-language instructions using the nano-pdf CLI" names the PDF domain and one concrete action (edit) tied to a specific mechanism, but lists no other capabilities, matching 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not 4 because only a single action verb is given with no coverage of supported edit types.	3 / 5
Completeness	The 'what' is clear (edit PDFs via natural-language instructions with the nano-pdf CLI), but there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 4 because the 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	"PDFs" and "edit" are natural, relevant terms a user would say, but the description omits common variations and synonyms ("PDF files", ".pdf", "modify", "make changes"), matching 'Some relevant keywords but missing common variations or synonyms'. Not 2 because the keywords present are specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	PDF editing driven by natural-language instructions via a named CLI is a fairly distinct niche with only minor overlap risk against closely related PDF skills (extraction, form filling), matching 'Mostly distinct; minor overlap risk'. Not 5 because no explicit trigger phrasing separates it from those neighboring skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 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	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/nano-pdf/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 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.