CtrlK
BlogDocsLog inGet started
Tessl Logo

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/extract/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Tight, executable, and well-organized, with copy-paste-ready code and output templates; the main gap is the absence of validation checkpoints between the back-to-back extraction stages of the pipeline.

Suggestions

Insert validation or sanity-check checkpoints between extraction stages (e.g., verify entities before relation/event extraction) so failures surface early rather than only at the final validator.

Add an explicit error-recovery loop around the validator step (detect issue → fix input/stage → re-run) for the batch pipeline.

Clarify the large-file chunking flow with a concrete chunk size and how partial results are merged, since the >50KB instruction is currently directional only.

DimensionReasoningScore

Conciseness

The body is lean with no concept-explanation padding: it jumps to executable imports and calls with only brief inline comments, so every token earns its place per the score-3 anchor.

3 / 3

Actionability

Provides fully executable Python imports and per-stage calls, concrete Markdown table templates, and a specific >50KB chunking threshold — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

The six-step sequence is clearly ordered, but a multi-stage pipeline runs extraction stages back-to-back with validation only at the end and no inter-step checkpoints, so per the guidelines workflow clarity is capped at 2.

2 / 3

Progressive Disclosure

This is a simple, single-purpose skill with no bundle files; its well-organized Steps/tables/summary sections are appropriately self-contained, qualifying for 3 under the simple-skills note.

3 / 3

Total

11

/

12

Passed

Description

67%

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 highly specific, third-person description of a concrete extraction pipeline, but it omits any 'Use when…' trigger guidance and leans on technical jargon over natural user phrasings.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to extract entities, relations, events, or triplets from a file or selected text.'

Include natural user-facing terms (e.g., 'extract named entities', 'find relationships', 'link pronouns') alongside the technical jargon to broaden trigger coverage.

Add common variations like 'semantic extraction', 'entity extraction', 'knowledge-graph triplets' so the description matches how users actually phrase the request.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'NER, relations, events, coreference resolution, triplets, and validation', 'Clears result cache before each run', 'Returns Markdown tables' — in third person, matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

It clearly answers 'what does this do' but provides no 'Use when…' or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2; it is not 1 because the 'what' is well covered.

2 / 3

Trigger Term Quality

Relevant technical terms appear ('semantic extraction', 'NER', 'relations', 'events', 'coreference', 'triplets') but common user-facing phrasings are absent, so coverage is partial rather than the natural-term spread expected at 3.

2 / 3

Distinctiveness Conflict Risk

The Semantica semantic-extraction niche with named sub-tasks (NER, coreference, triplets, validation) is distinct and unlikely to trigger the wrong skill, matching the clear-niche anchor.

3 / 3

Total

10

/

12

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
semantica-agi/semantica
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.