CtrlK
BlogDocsLog inGet started
Tessl Logo

format-specific-extraction

Format-specific document extraction workflows

51

Quality

56%

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 ./.ai-rulez/skills/format-specific-extraction/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a tight, actionable reference: each format lists a flow, concrete API calls, and source-file pointers, with security validation consistently ordered before extraction. It is well structured and concise, with only minor gaps in explicit error-recovery feedback and a few descriptive steps.

DimensionReasoningScore

Conciseness

The body is lean — flow diagrams plus terse numbered steps with real API calls and no padding or explanations of concepts Claude already knows — fitting the score-4 anchor 'Efficient; minor instances of over-explanation that could be trimmed'; the ASCII flow lines slightly duplicate the numbered steps, keeping it just below a 5.

4 / 5

Actionability

Concrete executable calls such as `ZipBombValidator::new(limits).validate(&mut archive)?`, `pdf_oxide::PdfDocument::from_bytes(content)?`, and exact file paths give mostly copy-paste-ready guidance, matching the score-4 anchor 'Mostly executable guidance; concrete code or commands with minor gaps' since a few steps remain descriptive (e.g. 'Extract XML files from archive').

4 / 5

Workflow Clarity

Each format has a clearly numbered sequence with an explicit security-validation checkpoint placed before extraction ("ZipBombValidator BEFORE any extraction"), matching the score-4 anchor 'Clear sequence with most checkpoints present; minor validation gaps'; extraction is non-destructive so the missing validate→fix→retry feedback loop does not cap it at 3.

4 / 5

Progressive Disclosure

The body is well organized into per-format sections plus a helpers table and an 'Adding a New Format' checklist, with 'See: extractors/...rs' pointers to implementation, matching the score-4 anchor 'Good structure; most content appropriately placed; minor organization gaps'; no bundle reference files exist to verify, and the file slightly exceeds the under-50-line simple-skill carve-out.

4 / 5

Total

16

/

20

Passed

Description

37%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 names the domain but is generic: it lacks concrete actions, natural trigger terms and file extensions, and any 'Use when' guidance. It is clear enough to avoid total ambiguity but would benefit from concrete verbs and explicit trigger phrases.

Suggestions

Add concrete actions, e.g. 'Extract text, tables, and metadata from PDF, DOCX, PPTX, EML and archive files.'

Append an explicit trigger clause, e.g. 'Use when extracting content from documents or when the user mentions PDF, DOCX, PPTX, EML, .eml, or archive files.'

Include natural synonyms and file extensions (PDF, PDFs, .pdf, DOCX, spreadsheets, emails) to improve trigger-term quality and distinctiveness.

DimensionReasoningScore

Specificity

Quotes "Format-specific document extraction workflows" — it names the domain (document extraction) but the only action, "extraction workflows", is generic and minimal, matching the score-2 anchor 'Names the domain but actions are minimal or generic' rather than the 1-2 concrete actions required for a 3.

2 / 5

Completeness

It states a clear 'what' ("document extraction workflows") but provides no 'when'/Use-when trigger guidance at all, which per the judging guidelines caps completeness at 3 — 'Has a clear what but when is missing'.

3 / 5

Trigger Term Quality

The phrase offers only the generic keywords "document" and "extraction" while omitting the natural terms users actually say (PDF, DOCX, Excel, .pdf), fitting the score-2 anchor 'One or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

"Format-specific document extraction workflows" is somewhat specific to extraction across formats yet still broad enough to overlap with general document-handling skills, matching the score-3 anchor 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

10

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
xberg-io/xberg
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.