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

35%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./aitesis/skills/inquire/SKILL.md

Quality

Content

35%

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

The skill has a genuinely structured procedural core (phases, validation gates, feedback loops, a surfacing template) but it is buried under an enormous formal type-theory apparatus that dominates the file, destroying conciseness and obscuring actionability and workflow clarity. No progressive disclosure is used despite the length.

Suggestions

Move the formal TYPES/MORPHISM/FLOW/PHASE-TRANSITIONS block into a reference file (e.g. references/formal-model.md) and keep SKILL.md as a lean procedural overview, cutting the body to a fraction of its length.

Strip the philosophical and type-theory exposition (fibrations, Greek aliases, Pollock defeater framing) down to the operational rules Claude must follow, assuming Claude's intelligence.

Surface the executable workflow as a clean numbered checklist with validation checkpoints up front, and relegate the edge-case classification detail to a reference.

Dimension	Reasoning	Score
Conciseness	The body is roughly 500 lines of dense formal apparatus (Grothendieck fibrations, type theory, Greek-rooted terms, a large TYPES/MORPHISM/FLOW block) that heavily over-explains abstract epistemic theory rather than assuming Claude's competence, padding every token against the context budget.	1 / 3
Actionability	There is some concrete guidance — the numbered Phase 0-3 steps, tool grounding per phase, and a literal Phase 2 surfacing template with four options — but it is buried under abstract formal notation, leaving the executable core incomplete and hard to extract.	2 / 3
Workflow Clarity	A clear phase sequence with explicit checkpoints and feedback loops (backward arcs T2/T4, convergence trace, staleness guards) does exist, but the formal density interleaves type theory with the steps, obscuring the scannable step list a reader needs to execute it.	2 / 3
Progressive Disclosure	The body is section-organized, but it is a monolithic single-file wall of text with no bundle/reference files to offload the large formal type block, so content that should be split stays inline and navigation is flat.	2 / 3
	Total	7 / 12 Passed

Description

35%

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

The description states a clear niche but is dominated by formal jargon and a Greek alias, with no natural trigger terms and no explicit 'Use when' guidance. It reads as type-theory notation rather than a user-facing activation description.

Suggestions

Rewrite in plain third-person voice with natural trigger terms users would actually say (e.g., 'Ask clarifying questions before starting work. Use when requirements are ambiguous, a task depends on unstated assumptions, or context seems incomplete.').

Remove the formal type signature and 'Alias: Aitesis(αἴτησις)' from the description; keep that apparatus in the body if needed.

Add an explicit 'Use when...' clause naming concrete triggering situations to satisfy the completeness criterion.

Dimension	Reasoning	Score
Specificity	Names concrete actions like 'Infer context insufficiency' and 'Surfaces uncertainties through information-gain prioritized inquiry', but they are abstract and not comprehensive; the appended type signature '(ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution' is formal notation rather than a concrete capability.	2 / 3
Completeness	It states what the skill does (infer insufficiency, surface uncertainties, produce informed execution), but the 'when' is only implied via 'when AI infers areas of context insufficiency' and there is no explicit 'Use when...' trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	The description relies on technical jargon and a Greek term ('Aitesis(αἴτησις)', 'InformedExecution', type-theory notation) that no user would naturally say when they need this skill; there are no everyday keywords like 'ask clarifying questions' or 'check requirements'.	1 / 3
Distinctiveness Conflict Risk	The inquiry-before-execution niche is somewhat specific, but the jargon does not map cleanly to user intent and the body reveals a family of sibling epistemic protocols (Syneidesis, Anamnesis, etc.) with which it could overlap.	2 / 3
	Total	7 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (506 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: jongwony/epistemic-protocols
Path: aitesis/skills/inquire/SKILL.md
Commit: ab9aa56

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.