gap

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 dense but well-structured protocol specification with a concrete user-facing gate template, explicit phase checkpoints, an error-recovery relay, and a verified one-level-deep reference. Its main weakness is the heavy formal notation, which hurts token efficiency and readability without adding proportional actionability.

Suggestions

Trim or move the elaborate formal type/locator notation into a reference file, keeping the SKILL.md body focused on the executable phases and the gate template.

Add a short plain-language step list (scan → select → surface gate → record → converge) alongside the formal block so the workflow reads as a checklist.

Move the formal 'Definition' block's morphism/type detail behind a clearly signaled reference so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the large formal block (morphisms, type signatures, locator/carrier notation) is elaborate specification that could be tightened for token efficiency; mostly efficient but noticeably heavier than needed.	3 / 5
Actionability	The user-facing realization provides a copy-paste-ready gate template (Address/Dismiss/Probe options) and the Rules give concrete, specific guidance; minor gaps remain because the formal block itself is abstract rather than directly executable.	4 / 5
Workflow Clarity	Phases 0–2 plus the re-scan loop are clearly sequenced with explicit checkpoints (committed? gate, carrier recovery, convergence evidence) and an error-recovery relay (carrier_unreachable); not a 5 because the dense notation makes the sequence harder to follow than a plain checklist.	4 / 5
Progressive Disclosure	Structure is clear (Definition, Mode Activation, Protocol, Rules) with one well-signaled, one-level-deep reference to references/round-composition.md that exists as a real file; minor gap because the core formal spec is a large inline monolithic block rather than split out.	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 states a clear, specific purpose with four concrete gap categories, but lacks an explicit 'Use when' trigger clause and leans on abstract type-signature jargon that users would never say. Trigger-term naturalness and explicit usage guidance are the main weaknesses.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases users would say (e.g. 'Use when about to commit to a decision and wondering what was overlooked').

Drop or relocate the 'Type: (GapUnnoticed, AI, SURFACE, Decision) → AuditedDecision' signature; it is jargon that adds no user-facing capability and hurts trigger-term quality.

Include common-sense synonyms for 'gap' (e.g. 'oversight', 'missing consideration', 'unchecked assumption') so the description matches how users phrase the need.

Dimension	Reasoning	Score
Specificity	Names the domain (gap surfacing before decisions) and four concrete gap categories raised as questions, giving several specific actions rather than generic language; falls short of 5 because the trailing 'Type:' signature is abstract jargon adding no concrete capability.	4 / 5
Completeness	The 'what' is clear (raises four gap types as questions before decisions), but there is no explicit 'Use when...' trigger clause and 'when' is only weakly implied by 'before decisions', which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords ('gap', 'decisions', 'questions', 'assumptions') appear, but the natural phrases a user would actually say ('what am I overlooking', 'did I miss anything') are absent and the 'Type:' clause is pure technical jargon, so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	'Gap surfacing before decisions' with four named gap types is a clear, mostly distinct niche with minor overlap risk against related decision/audit skills; not a 5 because the abstract type signature blurs the trigger.	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: ed3cc09

Reviewed: 13 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.