gap

Gap surfacing before decisions. Raises procedural, consideration, assumption, and alternative gaps as questions when gaps go unnoticed, producing an audited decision. Type: (GapUnnoticed, AI, SURFACE, Decision) → AuditedDecision. Alias: Syneidesis(συνείδησις).

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./syneidesis/skills/gap/SKILL.md

Quality

Discovery

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 attempts to define a niche around surfacing overlooked gaps in decision-making, which is a potentially distinctive concept. However, it relies heavily on abstract jargon, type-signature notation, and a Greek alias that provide no practical value for skill selection. It lacks an explicit 'Use when...' clause and natural trigger terms that users would actually say.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user is making a decision and may be overlooking risks, assumptions, or alternatives.'

Replace jargon and type signatures ('GapUnnoticed, AI, SURFACE, Decision → AuditedDecision', 'Syneidesis') with plain language that describes concrete actions, e.g., 'Identifies overlooked assumptions, missing alternatives, and procedural blind spots in decision-making.'

Include natural keywords users would say, such as 'decision review', 'blind spots', 'what am I missing', 'risk assessment', 'assumption check'.

Dimension	Reasoning	Score
Specificity	It names a domain (decision-making) and describes some actions (raises procedural, consideration, assumption, and alternative gaps as questions), but the language is abstract and the concrete actions are not clearly enumerable tasks a user would recognize.	2 / 3
Completeness	The 'what' is partially addressed (raises gaps as questions to produce an audited decision), but there is no explicit 'Use when...' clause or clear trigger guidance for when Claude should select this skill. The type signature hints at conditions but is not user-facing guidance.	2 / 3
Trigger Term Quality	The description uses highly specialized jargon ('GapUnnoticed', 'Syneidesis(συνείδησις)', 'AuditedDecision') and type signatures that no user would naturally say. Terms like 'gap surfacing' and 'procedural gaps' are not natural user language for requesting decision support.	1 / 3
Distinctiveness Conflict Risk	The concept of 'gap surfacing before decisions' is somewhat distinctive, but the abstract framing could overlap with general reasoning, critical thinking, or decision-analysis skills. The jargon-heavy type notation adds uniqueness but doesn't help Claude disambiguate in practical terms.	2 / 3
	Total	7 / 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 a heavily over-engineered formal specification for what amounts to 'surface unnoticed gaps as questions before committed decisions.' The formal type theory, morphism definitions, and extensive rule sets consume enormous token budget while adding little actionable value beyond what Claude could derive from a concise description. The core idea is sound but buried under layers of academic formalism that work against practical usability.

Suggestions

Reduce the formal block to a brief summary (5-10 lines max) of the phase flow and key types; move detailed formal specification to a separate reference file if needed.

Lead with a concise quick-start section showing the actual user-facing interaction pattern: detect gap → present question → collect judgment → track resolution, with a concrete example.

Extract the Gap Taxonomy, Rules, and Intensity tables into a separate reference file, keeping only the essential activation conditions and surfacing template in the main SKILL.md.

Remove explanations of concepts Claude already understands (e.g., what 'committed actions' are, extensive definitions of judgment types) and replace with terse operational instructions.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and over-engineered for what is essentially 'ask clarifying questions before irreversible decisions.' The formal type theory notation, Greek terminology, morphism definitions, and extensive rule sets massively exceed what Claude needs. Most of the formal block is unnecessary overhead that Claude already understands conceptually.	1 / 3
Actionability	The skill does provide concrete output formats (the surfacing template with Gap/Pressure/Options), task tracking format, and specific question forms in the Gap Taxonomy. However, much of the guidance is abstract formal specification rather than executable instruction, and the relationship between the formal definitions and actual behavior is left for Claude to interpret.	2 / 3
Workflow Clarity	The phase transitions (0→1→2) and loop structure are defined, and there are validation/convergence steps. However, the workflow is buried in dense formal notation and scattered across multiple sections (formal block, Protocol section, Rules), making it hard to follow the actual sequence of actions. The re-scan loop and convergence criteria are specified but operationally unclear.	2 / 3
Progressive Disclosure	Everything is in a single monolithic file with no bundle files or external references. The content is a wall of dense formal specification, tables, and rules without clear separation of quick-reference material from detailed specification. The formal block alone is enormous and could be extracted, but isn't.	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.