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

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./syneidesis/skills/gap/SKILL.md

Quality

Content

67%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 content is a well-sequenced, actionable protocol with explicit phase checkpoints, feedback loops, concrete templates, and a clearly signaled single reference file. Its main weakness is conciseness: the pervasive formal-block notation and long rule paragraphs add token weight that competes with the operational guidance.

Suggestions

Move the bulk of the formal TYPES/PHASE TRANSITIONS type-theory notation into a separate reference file, keeping only the operationally essential symbols inline in SKILL.md.

Tighten the longest rules (e.g., Rule 5 and Rule 15) into terse imperative statements, deferring their rationale to the reference if needed.

Lead each phase with a one-line plain-language summary of the action before the formal block, so the executable intent is visible without parsing the notation.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but the extensive formal-block type theory (Σ, D, G, P morphism notation) and very long rule paragraphs (e.g., Rule 15) carry abstract machinery that could be tightened without losing the operational contract.	3 / 5
Actionability	As an instruction-only protocol it provides concrete, executable artifacts — named question forms ('Was [step] completed?'), a structured surfacing template, Address/Dismiss/Probe options, and a carrier record format — with only minor gaps where the formal notation obscures the immediate action.	4 / 5
Workflow Clarity	Phases 0–2 and the LOOP are explicitly sequenced with checkpoints (committed? gate, carrier recovery, convergence evidence) and feedback loops (re-scan after response, carrier_unreachable relay), satisfying the validation requirement for risky/decision operations with only minor implicit transitions.	4 / 5
Progressive Disclosure	Structure is well organized into sections with a single one-level-deep reference (references/round-composition.md) that is clearly signaled in Rule 5 and verified to exist; only minor organization gaps remain from the heavy inlined formal blocks.	4 / 5
	Total	15 / 20 Passed

Description

58%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 clearly conveys a distinctive capability (surfacing unnoticed gaps as questions before decisions) with concrete gap categories, but it relies on formal/technical vocabulary and lacks an explicit 'Use when...' trigger clause with natural user phrasings. It reads as a precise scholarly definition more than an auto-activation trigger.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasings (e.g., 'Use before committing to a decision, when weighing options, or when the user asks what they might be missing').

Replace or supplement the formal 'Type: (GapUnnoticed, AI, SURFACE, Decision) → AuditedDecision' notation with plain-language trigger terms users would actually say.

Include common synonyms/variations (e.g., 'blind spots', 'overlooked assumptions', 'what am I missing') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Raises procedural, consideration, assumption, and alternative gaps as questions' and 'producing an audited decision' — naming the domain and specific gap categories, with only minor abstraction in the formal 'Type:' notation keeping it below a 5.	4 / 5
Completeness	The 'what' is clear ('Gap surfacing before decisions ... producing an audited decision') but the 'when' is only weakly implied via 'before decisions' and 'when gaps go unnoticed', with no explicit 'Use when...' clause, capping completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	It contains relevant keywords ('decisions', 'gaps', 'assumption') but leans on technical taxonomy terms rather than natural user phrasings like 'what am I missing' or 'before I decide', and omits common synonyms or explicit trigger guidance.	3 / 5
Distinctiveness Conflict Risk	The niche is specific and distinctive — surfacing four named gap types as questions before decisions — with minimal overlap risk against other skills, though the absence of concrete trigger phrases leaves a small chance of ambiguity versus general decision-making skills.	4 / 5
	Total	14 / 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: syneidesis/skills/gap/SKILL.md
Commit: e56ccd7

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.