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 is highly abstract and uses philosophical jargon (Katalepsis/κατάληψις) and a pseudo-type-signature format that provides no practical information about what the skill actually does. It lacks concrete actions, natural trigger terms, and any explicit guidance on when to use it. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.

Suggestions

Replace abstract language with concrete actions: specify what the skill actually does (e.g., 'Explains AI-generated results in simpler terms, provides step-by-step breakdowns, and confirms user understanding through follow-up questions').

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user says they don't understand the output, asks for clarification, or requests an explanation of results.'

Remove the type signature notation and Greek alias, which add no value for skill selection, and instead describe the workflow in plain language that distinguishes this skill from general explanation or tutoring skills.

Dimension	Reasoning	Score
Specificity	The description uses extremely vague and abstract language like 'achieve certain comprehension,' 'results remain ungrasped,' and 'verified understanding.' No concrete actions are listed—there's no indication of what specific tasks this skill performs (e.g., summarize, explain, rephrase, quiz).	1 / 3
Completeness	The 'what' is extremely vague ('verifies understanding') and there is no explicit 'when' clause or trigger guidance. The type signature format does not serve as a usable 'Use when...' clause. Both dimensions are very weak.	1 / 3
Trigger Term Quality	The description contains no natural keywords a user would actually say. Terms like 'ResultUngrasped,' 'Katalepsis(κατάληψις),' and the type signature notation are technical jargon that no user would naturally use when seeking help understanding something.	1 / 3
Distinctiveness Conflict Risk	The description is so abstract and generic ('comprehension,' 'understanding,' 'verify') that it could overlap with virtually any explanatory or educational skill. There are no distinct triggers that would help Claude differentiate this from other skills.	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 is heavily over-engineered with formal mathematical notation and type theory that adds significant token cost without improving Claude's ability to execute the task. The core idea — Socratic verification of user comprehension after AI work — is sound but buried under layers of abstraction. The content would benefit enormously from being condensed to its essential workflow with concrete examples, moving formal specifications to reference files if needed at all.

Suggestions

Reduce the formal specification block (FLOW, MORPHISM, TYPES, PHASE TRANSITIONS, etc.) to a simple numbered workflow — Claude doesn't need type theory notation to understand 'ask verification questions about AI work results'.

Add 1-2 concrete end-to-end examples showing what a Katalepsis interaction actually looks like (e.g., after a code refactoring, show the actual questions Claude would ask and how responses are evaluated).

Split into a concise SKILL.md overview (under 100 lines) with references to separate files for the gap taxonomy, category taxonomy, and detailed phase specifications.

Remove the comparison table with 12 other protocols — this context is not needed for executing this specific skill and consumes significant tokens.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and over-engineered. The formal type theory notation, morphism definitions, phase transition algebra, and mode state specifications are unnecessary for Claude to execute a comprehension verification workflow. Much of this content explains abstract concepts rather than providing actionable guidance, and the mathematical formalism adds significant token cost without proportional value.	1 / 3
Actionability	The skill provides structured phases and some concrete examples (task creation templates, question formats), but the heavy abstraction layer makes it difficult to extract executable guidance. The pseudo-formal notation (morphisms, type signatures) is not directly executable, and many steps are described in abstract terms rather than concrete actions Claude can take.	2 / 3
Workflow Clarity	The multi-phase workflow (Phase 0-3) is clearly sequenced with sub-steps, and there are feedback loops (verify → fix → re-verify). However, the workflow is buried under layers of formal notation, making it hard to follow. The validation checkpoints exist (coverage checks, misconception handling) but the sheer complexity and redundant specification across the FLOW, PHASE TRANSITIONS, LOOP, and Protocol sections creates confusion rather than clarity.	2 / 3
Progressive Disclosure	The entire specification is a monolithic wall of text with no references to external files. The formal specification block alone is extremely long and could be split into separate reference documents. There's no separation between quick-start overview and detailed reference material — everything is inline in a single dense document.	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: a3403de

Reviewed: 2 days 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.