CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf-processor

Perform basic local PDF operations (merge, split, extract pages/text/tables, create) when users request offline PDF processing without external services.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/pdf-processor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

The content is highly actionable with complete executable CLI examples for every operation, but it is padded with several generic templated sections and lacks the validate->fix->retry feedback loops expected for batch/destructive PDF operations. Referenced bundle files (scripts/pdf_tool.py, scripts/requirements.txt, references/examples.md) are not actually present in the bundle.

Suggestions

Add an explicit validation feedback loop for batch/destructive operations (e.g., after split/merge, verify page count and ordering, and on mismatch re-run or report the error) to lift workflow_clarity above 3.

Ship the referenced bundle files (scripts/pdf_tool.py, scripts/requirements.txt) or remove the references if the tool is not bundled, so progressive disclosure reflects a real one-level-deep structure.

Trim the generic templated sections ('When Not to Use', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Input Validation') to reduce token overhead toward the lean score-5 anchor.

DimensionReasoningScore

Conciseness

Most of the body is tight, executable reference with no conceptual padding (PDF basics and library tutorials are absent), but several generic sections ('When Not to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Input Validation', 'Quick Validation') are templated boilerplate adding tokens beyond what Claude needs, keeping it just below the lean score-5 anchor.

4 / 5

Actionability

Every operation ships a complete, copy-paste-ready CLI invocation with real flags ('--operation merge', '--inputs', '--pages "1-3,5"', '--output'), plus implementation details and success criteria, fully matching the score-5 'copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

A 'Recommended Workflow' is sequenced and validation/quick-check steps appear, but the operations involve batch/destructive actions (split writes many files, merge overwrites) with no explicit validate->fix->retry feedback loop around execution; per the rubric, missing validation feedback loops for batch operations caps this at 3.

3 / 5

Progressive Disclosure

Structure is clear with section headers, but no bundle directories (references/, scripts/, assets/) exist — the body's only reference ('references/examples.md' is hedged as 'may be available') points to a file that is not present, so content stays inline and references are not actually realized at one level deep.

3 / 5

Total

15

/

20

Passed

Description

80%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 specific and action-rich, cleanly answering both what the skill does and when to use it with a distinctive offline/local framing. Trigger-term coverage is good but could add synonyms and the '.pdf' extension to reach the top anchor.

Suggestions

Add file-extension triggers like '.pdf' and common synonyms ('PDF files, PDFs') to broaden natural keyword coverage toward the score-5 anchor.

Expand the 'when' clause with concrete trigger phrases (e.g., 'when users ask to merge PDFs, extract text or tables, or split documents offline') to lift completeness to 5.

Consider listing a couple of explicit distinct triggers to further reduce overlap with general PDF skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'merge, split, extract pages/text/tables, create' — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor 'Extract text and tables from PDF files, fill forms, merge documents, convert pages to images'.

5 / 5

Completeness

Explicitly states both what ('Perform basic local PDF operations: merge, split, extract pages/text/tables, create') and when ('when users request offline PDF processing without external services'), but the 'when' clause is a single general trigger rather than the multiple concrete trigger phrases that mark a 5.

4 / 5

Trigger Term Quality

Includes natural terms 'PDF operations', 'merge', 'split', 'extract pages', 'offline PDF processing', but lacks synonyms and the explicit '.pdf' extension present in the score-5 anchor; coverage is good but a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'offline PDF processing without external services' framing carves a clear niche and distinct trigger, with only minor overlap risk against broader PDF skills; it does not reach the score-5 level of multiple distinct, low-conflict trigger phrasing.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

14

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.