grasp

Achieve certain comprehension after AI work. Verifies understanding when results remain ungrasped, producing verified understanding. Type: (ResultUngrasped, User, VERIFY, Result) → VerifiedUnderstanding. Alias: Katalepsis(κατάληψις).

Quality

13%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./katalepsis/skills/grasp/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description fails on all dimensions due to its use of abstract philosophical terminology, lack of concrete actions, absence of natural trigger terms, and missing explicit usage guidance. The cryptic type signature format and Greek term 'Katalepsis' make it nearly impossible for Claude to know when to select this skill or what it actually does.

Suggestions

Replace abstract language with concrete actions (e.g., 'Explains complex results step-by-step, provides analogies, and confirms user comprehension through follow-up questions').

Add a 'Use when...' clause with natural trigger terms like 'I don't understand', 'explain this', 'what does this mean', 'confused about', 'clarify'.

Remove the cryptic type signature and Greek terminology; describe the skill in plain language that matches how users naturally express confusion or need for clarification.

Dimension	Reasoning	Score
Specificity	The description uses abstract philosophical language ('Achieve certain comprehension', 'verified understanding', 'Katalepsis') without describing any concrete actions. There are no specific capabilities like 'explains concepts', 'breaks down complex topics', or 'provides examples'.	1 / 3
Completeness	The 'what' is extremely vague ('Verifies understanding') and there is no explicit 'when' clause or trigger guidance. The type signature format is cryptic and doesn't help Claude know when to select this skill.	1 / 3
Trigger Term Quality	No natural keywords users would say. Terms like 'ResultUngrasped', 'VerifiedUnderstanding', and 'Katalepsis(κατάληψις)' are technical jargon and Greek philosophical terms that users would never naturally use when asking for help understanding something.	1 / 3
Distinctiveness Conflict Risk	The description is so abstract and vague that it could theoretically apply to almost any explanatory or educational skill. 'Verifies understanding when results remain ungrasped' could conflict with any teaching, tutoring, or explanation skill.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill suffers from severe over-engineering with formal type theory notation, philosophical terminology, and excessive abstraction that obscures the core task: helping users understand AI work through Socratic questioning. The content contains useful concepts (gap taxonomy, verification phases, task tracking) but buries them under unnecessary formalism. The skill would benefit dramatically from a 90% reduction in length, removing the formal notation entirely, and splitting reference material into separate files.

Suggestions

Remove all formal notation (morphisms, type signatures, flow diagrams) and replace with plain English workflow steps - Claude doesn't need category theory to understand 'ask verification questions'

Split the Gap Taxonomy, Category Taxonomy, and Rules sections into separate reference files (e.g., GAPS.md, CATEGORIES.md) and link from a concise overview

Replace pseudo-YAML gate interaction examples with concrete, copy-paste ready question templates showing actual user-facing text

Add explicit validation checkpoints with 'if validation fails' recovery steps, especially for the misconception handling workflow

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive formal notation, type theory, and philosophical framing that Claude doesn't need. The 'morphism' and 'flow' notation adds complexity without actionable value, and concepts like 'phantasia' and Greek terminology are unnecessary overhead.	1 / 3
Actionability	Contains concrete steps and phase descriptions, but the formal notation obscures the actual actions. The protocol steps are buried under layers of abstraction. Gate interaction examples use pseudo-YAML but lack executable code or copy-paste ready commands.	2 / 3
Workflow Clarity	Multi-step process is defined with phases 0-3 and clear sequencing, but validation checkpoints are implicit rather than explicit. The loop termination conditions exist but are scattered across multiple sections. Missing explicit 'if X fails, do Y' recovery patterns.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline including detailed taxonomies, rules, and examples that could be split into separate reference documents. The 500+ line document has no clear navigation structure for quick reference.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jongwony/epistemic-protocols
Commit: 5f3bed3

Reviewed: about 14 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.