vector-text-fixer

Fix garbled text in PDF/SVG vector graphics caused by font encoding issues, making files editable in AI tools. Supports batch processing and JSON export for manual correction.

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 ./scientific-skills/Other/vector-text-fixer/SKILL.md

Quality

Content

61%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 a well-structured, command-driven reference with a real backing script and thorough parameter/error documentation. Its main weaknesses are duplicated sections inflating token cost, a documented parameter (--encoding) absent from the actual script, and no output-validation step in the workflow despite batch operation support.

Suggestions

Merge the redundant sections: fold Audit-Ready Commands into CLI Usage, consolidate the encrypted/scanned-PDF limitations into the single Limitations section, and combine Output Requirements with the Stress-Case checklist.

Remove the '--encoding' row from the Parameters table or add the flag to scripts/main.py so documented CLI surface matches the implementation.

Add an output-validation step to the workflow, e.g. re-open the output file after repair to confirm text blocks render correctly, and a retry path for low-confidence blocks in batch mode.

Dimension	Reasoning	Score
Conciseness	The content is operational rather than explanatory, but contains duplicated sections: 'python -m py_compile scripts/main.py' appears in both Quick Check and Audit-Ready Commands, Audit-Ready Commands repeats CLI Usage, and encrypted/scanned-PDF limitations appear in Stress-Case Output Checklist, Limitations, and Constraints. Merging these would tighten the document considerably.	3 / 5
Actionability	Commands are copy-paste ready and cover the common cases (single PDF/SVG, batch, interactive, JSON export, repair levels), and the parameter table is concrete. However, the documented '--encoding' parameter does not exist in scripts/main.py, a minor but real gap that would produce an error if used.	4 / 5
Workflow Clarity	The 5-step workflow is clearly sequenced with scope validation and a failure fallback, but this batch-capable skill has no output-verification or validate-fix-retry checkpoint — the batch-operation guideline caps workflow clarity at 3 without such validation.	3 / 5
Progressive Disclosure	Sections are well organized and the single bundle reference (scripts/main.py) is real, clearly signaled, and one level deep. Minor gaps come from duplicated sections that could be consolidated; at ~190 lines with everything inline it falls short of the top anchor.	4 / 5
	Total	14 / 20 Passed

Description

66%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 clearly communicates a specific niche capability with concrete actions and natural trigger keywords, but it lacks any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause with synonyms and file extensions would substantially improve it.

Suggestions

Append an explicit trigger clause, e.g. 'Use when PDF or SVG files show garbled, boxed, or unreadable characters (.pdf, .svg) caused by font or encoding issues.'

Add natural synonyms such as "broken text", "unreadable characters", and file extensions .pdf/.svg to broaden trigger coverage.

Mention the repair-level options (minimal/standard/aggressive) to round out the capability list toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("PDF/SVG vector graphics") and three concrete actions — "Fix garbled text", "batch processing", "JSON export" — but omits others like repair levels and interactive mode, so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance; "making files editable in AI tools" only weakly implies a use case, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural user phrases like "garbled text", "font encoding issues", "PDF", and "SVG", but misses common synonyms ("broken/unreadable text") and file extensions (.pdf, .svg) that the top anchor requires.	4 / 5
Distinctiveness Conflict Risk	The garbled-text/font-encoding repair niche is distinct from generic PDF manipulation skills, but "making files editable in AI tools" broadens it slightly toward general file-editing skills, leaving minor overlap risk.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/vector-text-fixer/SKILL.md
Commit: 686e09d

Reviewed: 12 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.