inquire

Infer context insufficiency before execution. Surfaces uncertainties through information-gain prioritized inquiry when AI infers areas of context insufficiency, producing informed execution. Type: (ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution. Alias: Aitesis(αἴτησις).

Quality

17%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./aitesis/skills/inquire/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 heavily over-engineered with academic jargon, type signatures, and a Greek alias, making it nearly impenetrable for practical skill selection. It fails to communicate concrete actions in plain language and lacks any natural trigger terms a user would employ. The core concept—asking clarifying questions when information is missing—is simple but is obscured by unnecessary abstraction.

Suggestions

Rewrite in plain language describing concrete actions, e.g., 'Detects when a request lacks sufficient context and asks targeted clarifying questions before proceeding.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when a user request is ambiguous, underspecified, or missing key details needed for execution.'

Remove the type signature notation and Greek alias, which add no value for skill selection and obscure the description's purpose.

Dimension	Reasoning	Score
Specificity	The description uses highly abstract, academic language ('context insufficiency', 'information-gain prioritized inquiry', 'InformedExecution') without listing any concrete actions a user would recognize. No specific tasks or operations are described.	1 / 3
Completeness	The 'what' is buried in abstract language and the 'when' is only vaguely implied ('when AI infers areas of context insufficiency'). There is no explicit 'Use when...' clause or clear trigger guidance.	1 / 3
Trigger Term Quality	The description contains no natural keywords a user would say. Terms like 'ContextInsufficient', 'Aitesis(αἴτησις)', and 'Prospect' are technical jargon and type signatures that no user would naturally use in a request.	1 / 3
Distinctiveness Conflict Risk	The concept of asking clarifying questions when context is insufficient is somewhat distinct, but the description is so abstract that it could overlap with any skill that involves clarification or disambiguation. The type signature adds some uniqueness but doesn't help with practical disambiguation.	2 / 3
	Total	5 / 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 attempts to formalize the simple concept of 'ask clarifying questions before executing' into an elaborate formal system with type theory, fibration structures, and Greek terminology. While the underlying workflow logic is sound and the phase structure is well-conceived, the extreme verbosity and academic formalism make it nearly unusable as practical guidance for Claude. The content would benefit enormously from radical simplification — extracting the formal specification into a separate reference file and keeping the SKILL.md focused on clear, actionable instructions.

Suggestions

Reduce the SKILL.md to a concise overview (under 100 lines) covering the core workflow: scan for missing context → collect evidence → classify uncertainties → ask user about what remains unresolved → integrate answers → repeat until sufficient. Move all formal type definitions, mathematical notation, and detailed classification rules into separate reference files.

Replace formal notation (Σ, ℘, fibration, morphism, etc.) with plain English descriptions of the same concepts. Claude does not need category theory to understand 'classify each uncertainty by type and figure out the best way to resolve it.'

Add 1-2 concrete examples showing what a Phase 2 interaction actually looks like in practice — a real uncertainty identified from a real-ish task, with the classification summary and options presented to the user.

Split the monolithic content into bundle files: a TYPES.md for formal definitions, a CLASSIFICATION.md for the epistemic classification details, a RULES.md for the safeguards and rules, keeping SKILL.md as a navigable overview with clear pointers.

Dimension	Reasoning	Score
Conciseness	This skill is extremely verbose and over-engineered. It contains extensive formal type theory notation, Greek terminology, mathematical formalisms, and deeply nested classification hierarchies that far exceed what Claude needs to perform the core task of asking clarifying questions before execution. The content could be reduced by 80%+ while preserving all actionable guidance.	1 / 3
Actionability	The skill does contain concrete phase-by-phase instructions and specific tool groundings (Read, Grep, Bash, Write), and the Phase 2 surfacing format provides a usable template. However, the actionable content is buried under layers of formal notation and type theory that obscure rather than clarify what Claude should actually do. No executable code examples are provided despite referencing tool calls extensively.	2 / 3
Workflow Clarity	The multi-phase workflow (Phase 0→1→2→3) is clearly sequenced with explicit validation checkpoints, feedback loops (backward arcs), and escape conditions. However, the workflow is so complex and laden with formal notation that following it in practice would be extremely difficult. The numerous sub-steps, conditional branches, and cross-references between sections create cognitive overload that undermines the clarity the structure attempts to provide.	2 / 3
Progressive Disclosure	Despite being an extremely long document (500+ lines), there are no bundle files or external references to split content into. Everything is monolithically packed into a single SKILL.md. The formal type definitions, phase details, UX safeguards, and rules could easily be split into separate reference files, with the main SKILL.md serving as a concise overview with pointers.	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: a1acc87

Reviewed: 3 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.