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

65%

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

62%

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

The body is well-sequenced with explicit phases and validation checkpoints, but it is monolithic and padded with heavy formal notation that hurts conciseness and buries actionable templates. Splitting the formal type block into a referenced file and leading with the operational Protocol would materially improve it.

Suggestions

Move the formal Definition/type-theory block into a referenced file (e.g., references/formal-model.md) and keep SKILL.md as a lean overview pointing to it, improving both conciseness and progressive disclosure.

Lead with the operational Protocol (Detection → Pressure Assessment → Surfacing → Resolution → Gap Tracking) and the copy-paste templates so actionable guidance is not buried under formalism.

Trim Greek/notation prose in user-facing sections per Rule 10 (Plain emit discipline) — apply it to the SKILL.md body itself, not only to runtime emit.

Dimension	Reasoning	Score
Conciseness	The body contains genuine operational content, but a ~90-line formal block of type-theory notation, Greek terms (συνείδησις), morphisms, and coproduct definitions is heavy token overhead that could be tightened without losing the operational contract.	2 / 3
Actionability	Concrete templates exist (TaskCreate format, the surfacing prompt with three options, per-gap-type question forms, the intensity matrix), but they are interleaved with abstract formalism and some operations are left vague (e.g., "Internal analysis (no external tool)"), so guidance is incomplete rather than copy-paste ready throughout.	2 / 3
Workflow Clarity	Phases 0/1/2 are explicitly sequenced with transitions, a LOOP re-scan feedback loop is defined, and convergence-evidence validation is required before declaring AuditedDecision, matching the anchor for a clear sequence with explicit validation checkpoints.	3 / 3
Progressive Disclosure	The skill is a monolithic ~315-line file with no bundle files; sections are organized, but the large formal Definition block and reference-style material are inline rather than split into one-level-deep referenced files, so structure is present but not ideal.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 concrete capabilities and occupies a distinctive niche, but it omits an explicit "Use when…" trigger and dilutes natural keywords with formal type-theory notation and a Greek alias. Adding a plain-language trigger clause and trimming the formal tail would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when…' clause naming natural trigger situations (e.g., 'Use when about to commit to a decision and you want to audit for overlooked gaps').

Replace or move the 'Type: (GapUnnoticed, AI, SURFACE, Decision) → AuditedDecision' and 'Alias: Syneidesis' notation out of the description; keep user-facing natural terms like 'gap', 'decision', 'assumption', 'alternative'.

Add common keyword variations users might say ('second-guessing a decision', 'what am I missing', 'review assumptions') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Raises procedural, consideration, assumption, and alternative gaps as questions" and "producing an audited decision" — matching the anchor for listing several specific concrete actions rather than vague language.	3 / 3
Completeness	The "what" is clearly stated (gap surfacing, raising gaps as questions, audited decision), but there is no explicit "Use when…" trigger clause; "when gaps go unnoticed" only implies the when, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural terms ("gap", "decision", "questions", "assumption"), but the formal "Type: (GapUnnoticed, AI, SURFACE, Decision) → AuditedDecision" and "Alias: Syneidesis(συνείδησις)" are jargon a user would never say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The four-gap-type surfacing at decision points producing an audited decision defines a clear niche with distinct triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	10 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jongwony/epistemic-protocols
Path: syneidesis/skills/gap/SKILL.md
Commit: ab9aa56

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.