Tessl • The management layer for AI agent skills

SkillPublic

extracting-tables

Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.

Quality

86%

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

Quality

Content

92%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.

Excellent action-oriented content: lean, executable, and with strong troubleshooting feedback loops. The one real weakness is navigation — two of its four file references point to paths absent from this skill's bundle, and the other two defer to an external sibling skill.

Suggestions

Ship references/cli-reference.md and references/advanced-features.md inside this skill's bundle, or inline the key layout flags so the body is self-sufficient.

Qualify the cli-reference/advanced-features pointers the same way the python-api/nodejs-api ones are qualified (e.g., "in the sibling xberg skill") if that is where they actually live, so readers know where to resolve them.

Add a one-line Node.js snippet (mirroring the Python example) since the section currently names the API surface without showing it.

Dimension	Reasoning	Score
Conciseness	The body is lean: every section is tool-specific commands, a model-selection table, or failure-mode fixes, with no explanation of concepts Claude already knows; even asides like "Good for LLM ingestion" serve format-selection decisions.	5 / 5
Actionability	Fully executable throughout: copy-paste CLI commands for both output shapes, a jq inspection pipeline, a model-selection table with concrete flags, and a complete runnable Python example with imports covering the common cases.	5 / 5
Workflow Clarity	This is a single-action skill with unambiguous commands, satisfying the simple-skill carve-out; the jq example shows how to inspect results and "Common failure modes" provides explicit detect-then-fix feedback loops (empty tables → drop --layout-confidence; ragged output → switch table model).	5 / 5
Progressive Disclosure	Section structure and reference signaling are good, but the referenced files do not exist in this skill's bundle — there is no references/ directory, so "references/cli-reference.md" and "references/advanced-features.md" are dangling, and the Python/Node API references point to a "sibling xberg skill" whose presence cannot be assumed.	3 / 5
	Total	18 / 20 Passed

Description

75%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.

A solid description with an explicit trigger clause, concrete capability list, and natural keywords. It sits just below top marks because it lacks synonyms/file extensions in its triggers and pads the capability list with the vague "known limits".

Suggestions

Add file extensions and synonyms to the trigger clause, e.g., "Use when extracting tables from PDFs, spreadsheets (.xlsx, .csv), or images."

Replace the vague "and known limits" with a concrete capability (e.g., "and troubleshooting failed table detection") or drop it.

Dimension	Reasoning	Score
Specificity	"layout-aware table detection, table model selection, output formats (markdown / JSON cells)" lists several concrete capabilities, but the trailing "and known limits" is generic and the phrasing is feature enumeration rather than the crisp action verbs of the anchor-5 example.	4 / 5
Completeness	"Use when extracting tabular data from PDFs, spreadsheets, or images" is an explicit when-clause with concrete triggers, and the what is stated clearly; however "known limits" leaves the what slightly vague compared to the fully concrete anchor-5 example.	4 / 5
Trigger Term Quality	"extracting tabular data", "PDFs", "spreadsheets", "images" are natural user phrases with good coverage, but common synonyms (e.g., "table extraction", "invoice") and file extensions (.xlsx, .csv, .pdf) are missing, short of the anchor-5 bar.	4 / 5
Distinctiveness Conflict Risk	The table-extraction niche with PDF/spreadsheet/image triggers is mostly distinct; minor overlap risk remains with generic PDF- or document-extraction skills.	4 / 5
	Total	16 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: xberg-io/xberg
Path: plugin/.cursor-plugin/skills/extracting-tables/SKILL.md
Revision: df72569

Reviewed: 15 days ago

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.

extracting-tables

Table of Contents

Is this your skill?