CtrlK
BlogDocsLog inGet started
Tessl Logo

pdftotext-fallback

Recover PDF text extraction when read_file returns binary data by using pdftotext via shell

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdftotext-fallback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 body is well-structured and actionable with concrete pdftotext commands, but it carries some over-explanation Claude already knows and lacks an explicit validation feedback loop for confirming extraction succeeded.

Suggestions

Trim explanatory padding such as 'is a mature, command-line tool' and 'pre-installed on most Linux systems' that Claude already knows.

Add an explicit validation step, e.g. check the command exit code or non-empty output before proceeding, with a retry/OCR fallback loop.

Consolidate the duplicate pdftotext invocations between the Steps and Code Examples sections to reduce repetition.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but includes explanatory padding Claude already knows (e.g. 'is a mature, command-line tool', 'pre-installed on most Linux systems') and repeats the same pdftotext patterns across Steps and Code Examples.

3 / 5

Actionability

Provides concrete, executable pdftotext commands with flags for layout, encoding, and file output, though the Code Examples use `run_shell(...)` calls labeled as bash blocks, which is a minor inconsistency rather than pure copy-paste shell.

4 / 5

Workflow Clarity

Steps are sequenced (detect, extract, handle complex, verify) and Step 4 includes a verification check, but there is no explicit validation command or feedback loop for confirming extraction success before proceeding.

3 / 5

Progressive Disclosure

Well-organized sections (When to Use, Steps, Troubleshooting, Limitations) with a concise single-file structure appropriate for this simple skill; no external references are needed and content is properly placed.

4 / 5

Total

14

/

20

Passed

Description

78%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 concrete, third person, and carves out a distinct fallback niche, but it lacks an explicit 'Use when...' trigger clause and broader synonym/extension coverage that would push it to the top anchor.

Suggestions

Add an explicit 'Use when...' clause naming trigger scenarios, e.g. 'Use when read_file returns binary PDF data or Python PDF extraction fails.'

Include natural synonyms and the file extension, such as 'PDFs' and '.pdf', to broaden trigger-term coverage.

Mention additional concrete actions (e.g. preserve layout, handle encoding) to move specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the concrete recovery action (pdftotext via shell) and the failure conditions that trigger it, but lists only one core action rather than a comprehensive set.

4 / 5

Completeness

Clearly states what it does ('Recover PDF text extraction') and the when is implied by the failure-condition phrasing, but there is no explicit 'Use when...' clause, so the when is not as explicit as the 5-anchor.

4 / 5

Trigger Term Quality

Includes natural terms a user would say ('PDF text extraction', 'binary data', 'read_file returns binary') but lacks synonyms like 'PDFs' or the '.pdf' extension.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche as a fallback recovery strategy for binary PDF output, with distinct triggers unlikely to fire for unrelated skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
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.