inquire

Infer context insufficiency before execution. Surfaces uncertainties through information-gain prioritized inquiry. Type: (ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

41%Weight 40%Scale 1-5

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

The skill's workflow is rigorously sequenced with validation and feedback loops, but the body is massively over-formalized and abstract, offering almost no executable or example-level guidance and inlining what should be reference material. It reads as a research specification rather than an actionable skill.

Suggestions

Move the formal TYPES/MORPHISM/PHASE TRANSITIONS/MODE STATE block into a reference file and keep SKILL.md as a concise operational overview that points to it.

Add at least one concrete, rendered example of a Phase 2 inquiry round (sample uncertainty cluster, the options shown, and a user response) so the protocol is executable rather than only specified.

Trim the prose commentary inside the formal block and the Rules section to assume Claude's intelligence, retaining only the operational decisions an agent must make.

Dimension	Reasoning	Score
Conciseness	The body is a ~250-line, 31KB formal specification with Greek terminology, fibration math, and exhaustive edge-case commentary that does not respect the token budget and does not assume Claude's competence; it is noticeably verbose with many padded sections, though the content is novel rather than re-explaining known concepts, keeping it above a 1.	2 / 5
Actionability	Guidance is almost entirely abstract specification with no executable code or commands; the only concrete artifacts are the Light/Medium/Heavy Intensity table and high-level 'user-facing realization' directives, which are high-level hints missing the specific steps and rendered examples needed to execute.	2 / 5
Workflow Clarity	Phases 0–3 plus LOOP and CONVERGENCE are explicitly sequenced with validation checkpoints (Step₃ ReadOnlyVerify, admissibility predicate) and feedback loops (T2/T4 backward arcs, re-validation), matching 'clear sequence with most checkpoints present'; the abstraction density prevents a fully clear-executable 5.	4 / 5
Progressive Disclosure	There is one clearly signaled, one-level-deep reference ('Read references/round-composition.md before composing when...'), but the ~200-line formal block is inlined monolithically in SKILL.md as content that reads like reference detail, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 purpose and distinct niche but is written in heavy academic jargon with no explicit 'Use when...' trigger guidance, weakening trigger-term quality and capping completeness. A plainer, trigger-anchored rewrite would substantially raise the score.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when about to start a task with ambiguous requirements, when the user's intent or constraints are unclear, or before executing on an underspecified request').

Replace jargon ('context insufficiency', 'information-gain prioritized inquiry') with everyday verbs a user would actually say ('ask clarifying questions', 'check what's unknown before acting').

Drop the 'Type: (...)' signature from the description — it is notation, not a capability statement, and adds noise without aiding triggering.

Dimension	Reasoning	Score
Specificity	Names the domain ('context insufficiency') and a couple of actions ('Infer context insufficiency', 'Surfaces uncertainties through information-gain prioritized inquiry'), matching the 'names domain and 1-2 concrete actions' anchor; the 'Type:' suffix is a signature, not additional actions, so it does not reach 'several specific actions' (4).	3 / 5
Completeness	A clear 'what' is present (infer context insufficiency, surface uncertainties via inquiry) but there is no 'Use when...' or equivalent explicit 'when' clause — only a weak 'before execution' timing cue — so per the missing-trigger-guidance cap it cannot exceed 3.	3 / 5
Trigger Term Quality	Phrases like 'context insufficiency', 'information-gain prioritized inquiry', and the 'Type:' signature are technical jargon; only 'uncertainties'/'inquiry' are quasi-natural and the common phrasings a user would actually say ('ask clarifying questions', 'check what you need before starting') are absent, matching 'one or two generic keywords; missing the natural phrases'.	2 / 5
Distinctiveness Conflict Risk	The niche (AI-guided pre-execution context-inquiry with an epistemic-classification framing) is mostly distinct with only minor overlap risk against generic clarification skills; it is not as cleanly self-triggering as a 5 because its triggers are jargon rather than natural phrases.	4 / 5
	Total	12 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jongwony/epistemic-protocols
Path: aitesis/skills/inquire/SKILL.md
Commit: 3ffe94c

Reviewed: 1 day 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.