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, ExecutionPlan) → InformedExecution. Alias: Aitesis(αἴτησις).

Quality

17%

Does it follow best practices?

Impact

Pending

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 written in highly abstract, academic language that fails to communicate concrete actions or natural trigger terms. It reads more like a formal type theory specification than a practical skill description. A user needing Claude to ask clarifying questions before proceeding would never use any of the terms present in this description.

Suggestions

Rewrite using plain language describing concrete actions, e.g., 'Asks targeted clarifying questions before executing tasks when the user's request is ambiguous or missing key details.'

Add an explicit 'Use when...' clause with natural trigger scenarios, e.g., 'Use when a user request is vague, underspecified, or could be interpreted multiple ways.'

Include natural keywords users might associate with this behavior, such as 'clarifying questions', 'ambiguous request', 'missing information', 'confirm requirements', or 'gather details before proceeding'.

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 domains are mentioned.	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 for Claude to know when to select this skill.	1 / 3
Trigger Term Quality	The description contains no natural keywords a user would say. Terms like 'Aitesis(αἴτησις)', 'ContextInsufficient', and 'information-gain prioritized inquiry' are technical jargon that no user would naturally use in a request.	1 / 3
Distinctiveness Conflict Risk	The concept of asking clarifying questions before execution is somewhat distinct, but the description is so abstract that it could overlap with any skill that involves gathering requirements or asking questions. The type signature and alias add some uniqueness but not practical distinctiveness.	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 is an extremely dense formal specification that prioritizes mathematical rigor and completeness over practical usability. While the underlying protocol concept (inferring context insufficiency before execution) is valuable, the presentation buries actionable guidance under layers of type theory, formal notation, and exhaustive enumeration. The skill would benefit enormously from a concise overview with concrete examples, relegating formal specifications to referenced files.

Suggestions

Reduce the main file to a concise overview (~50-80 lines) covering the core concept, phase summaries, and one concrete example interaction, moving formal type definitions, detailed classification rules, and protocol distinctions to referenced files (e.g., TYPES.md, CLASSIFICATION.md, DISTINCTIONS.md)

Add a concrete, end-to-end example showing what an actual Aitesis interaction looks like — from Phase 0 scan through Phase 2 surfacing to Phase 3 resolution — with realistic task context and user responses

Remove or drastically compress the formal type notation (Grothendieck fibration, morphism definitions, convergence proofs) which does not translate to actionable behavioral guidance for Claude

Consolidate the 18 rules into a shorter set of essential behavioral constraints, as many are redundant with the phase descriptions or encode implementation details that don't need separate rule status

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines of dense formal notation, type theory, and abstract definitions. Much of this content (Grothendieck fibrations, morphism definitions, formal type signatures) is unnecessary for guiding Claude's behavior and explains concepts at a level of abstraction that doesn't translate to actionable steps. The protocol distinction table and advisory relationship details add significant bulk without proportional value.	1 / 3
Actionability	The protocol phases (0-3) provide a structured sequence of actions, and the surfacing format in Phase 2 gives a concrete template. However, the skill lacks executable code examples, concrete input/output demonstrations, and real-world scenarios showing what an actual Aitesis interaction looks like. The formal type notation is not directly executable guidance.	2 / 3
Workflow Clarity	The four-phase workflow (Phase 0-3) is clearly sequenced with explicit transitions and a loop mechanism. However, the workflow is buried within dense formal notation, making it hard to follow. Validation checkpoints exist (probe cleanup, convergence evidence) but the sheer complexity and multiple parallel classification paths make the actual execution sequence difficult to trace without significant effort.	2 / 3
Progressive Disclosure	The entire specification is presented as a monolithic wall of text with no references to external files for detailed content. The formal type system, UX safeguards table, 18 rules, phase details, and protocol distinctions are all inline. Content like the distinction table, formal types, and detailed probe constraints could be split into referenced files.	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: 9342160

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.