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

35%

Does it follow best practices?

Impact

Pending

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, but it relies heavily on abstract jargon and a formal type signature that would not help Claude match it to natural user requests. It lacks an explicit 'Use when...' clause and uses terminology (Syneidesis, AuditedDecision) that no user would naturally invoke, making it difficult for Claude to select this skill appropriately from a pool of available skills.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms like 'review my decision', 'what am I missing', 'check my assumptions', 'devil's advocate', or 'before I decide'.

Replace jargon like 'GapUnnoticed', 'AuditedDecision', and the Greek alias with plain language that describes the skill's purpose in terms users would recognize.

List concrete actions in plain terms, e.g., 'Identifies overlooked assumptions, missing alternatives, and procedural blind spots in a proposed decision, then presents them as questions for the user to address.'

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. The trigger condition ('when gaps go unnoticed') is embedded but not framed as explicit guidance for when Claude should select this skill.	2 / 3
Trigger Term Quality	The description uses highly specialized jargon ('GapUnnoticed', 'Syneidesis(συνείδησις)', 'AuditedDecision') that no user would naturally say. Terms like 'gap surfacing' and 'procedural gaps' are not natural trigger phrases users would use when seeking help with decisions.	1 / 3
Distinctiveness Conflict Risk	The concept of 'gap surfacing before decisions' is somewhat distinctive, but the abstract framing could overlap with any critical thinking, review, or decision-support skill. The type signature notation adds uniqueness but doesn't help Claude distinguish it from other analytical skills in practice.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

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 intellectually rigorous formal specification of a gap-surfacing protocol, but it prioritizes theoretical completeness over practical usability. The extensive formal notation, type theory, and comparison with 12 sibling protocols consume significant tokens without proportional actionability gains. The core workflow (detect gaps → surface as questions → collect judgment → adjust) is sound but buried under layers of abstraction that could be dramatically condensed.

Suggestions

Reduce the formal specification block to essential elements only — move the full type theory and morphism definitions to a separate REFERENCE.md file, keeping only the phase flow and key types in SKILL.md

Add a concrete worked example showing the full protocol applied to a real decision (e.g., a user saying 'deploy to production'), demonstrating detection, surfacing, and resolution in practice

Remove or drastically condense the 12-protocol comparison table — a 1-2 sentence distinction from the most commonly confused protocols (Aitesis, Epharmoge) is sufficient

Consolidate the scattered workflow descriptions (formal block phases, Protocol section, Interactive Surfacing) into a single clear sequential workflow with numbered steps

Dimension	Reasoning	Score
Conciseness	Extremely verbose and dense with formal notation, type theory, and extensive tables that Claude doesn't need explained at this level of detail. The formal morphism block, type definitions, and extensive comparison table with 12 other protocols consume enormous token budget. Much of this is definitional overhead rather than actionable instruction.	1 / 3
Actionability	The skill provides structured steps (Detection → Surfacing → Resolution) with concrete question forms and task format examples. However, much of the guidance is abstract formal notation rather than executable examples. The surfacing template and TaskCreate format are concrete, but the protocol lacks a clear worked example showing the full flow applied to a real decision.	2 / 3
Workflow Clarity	The phase transitions (Phase 0 → Phase 1 → Phase 2) and loop structure are defined, and there is a re-scan feedback loop. However, the workflow is buried in formal notation and scattered across multiple sections (formal block, Protocol section, Interactive Surfacing), making it hard to follow as a sequential process. Validation/convergence steps exist but are abstractly specified.	2 / 3
Progressive Disclosure	The content has clear section headers and some structural organization (Definition, Protocol, Rules, etc.), but the formal specification block is a monolithic wall of dense notation that should be separated or condensed. References to external files (graph.json) exist but the skill itself is a single massive document with no clear split between overview and detailed reference material.	2 / 3
	Total	7 / 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: a3403de

Reviewed: 2 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.