Name: clarity-gate
Rating: 49.6 (1 reviews)
Author: administrakt0r

clarity-gate

Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/clarity-gate/SKILL.md

The canonical home for this skill is clarity-gate in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

52%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 largely actionable with concrete scripts, templates, and a clear verification hierarchy, but it is verbose and structurally weak: referenced bundle files and the format spec do not exist, and reference-grade material is inlined rather than progressively disclosed. Tightening and actually shipping the referenced files would lift the two lowest dimensions.

Suggestions

Deduplicate the E-TB01-07 table (present in both 'Validation Codes' and 'SOT Validation') and move the full validation-code reference and changelog into the referenced docs/CLARITY_GATE_FORMAT_SPEC.md so SKILL.md stays a lean overview.

Provide the missing bundle files referenced by the body (scripts/claim_id.py, scripts/document_hash.py, docs/CLARITY_GATE_FORMAT_SPEC.md, RFC-001) or remove/soften the references so navigation is not broken.

Reframe the 9 Verification Points as an ordered, checkpointed workflow (extract claims -> run epistemic checks 1-4 -> data checks 5-7 -> routing 8-9 -> validate CGD structure -> HITL) with explicit validation gates between stages.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is noticeably verbose: the E-TB01-07 validation table is duplicated across 'Validation Codes' and 'SOT Validation', and a full multi-version changelog plus spec-versioning detail that belongs in the spec file are inlined; matches 'several unnecessary explanations or padded sections'.	2 / 5
Actionability	Provides concrete, mostly-executable guidance: real script invocations ('python scripts/claim_id.py "..." "..."'), algorithm steps, test vectors, and a full CGD YAML template; minor gaps because the 9-point review is described via fails/passes tables rather than an executable procedure.	4 / 5
Workflow Clarity	Sequences the process clearly (verification hierarchy -> Tier 1 automated / Tier 2 HITL -> Round A/B -> APPROVE/REJECT) with validation gates (validation codes, mandatory HITL before PASS); minor gaps because the 9 points are presented as a checklist rather than an ordered, checkpointed workflow.	4 / 5
Progressive Disclosure	Scored against the actual bundle: the body references scripts/claim_id.py, scripts/document_hash.py, docs/CLARITY_GATE_FORMAT_SPEC.md, and RFC-001, but none of these files exist in the workspace, so references are broken; bulk reference material (validation tables, spec semantics, changelog) is inlined in SKILL.md rather than split out.	2 / 5
	Total	12 / 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 states what the skill does and targets a distinct niche, but it lacks an explicit 'Use when...' trigger clause and leans on domain jargon rather than natural user phrases. This caps completeness and trigger-term quality at mid-range.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use before ingesting documents into a RAG knowledge base, or when checking a document for hallucination/equivocation risks').

Replace or supplement jargon ('CGD', 'SOT', 'epistemic quality') with plain-language terms a user would actually say ('check document clarity', 'pre-ingestion check', 'hallucination risk review').

Move the natural trigger phrases currently only in the frontmatter `triggers:` list into the description so the when-to-use guidance is self-contained.

Dimension	Reasoning	Score
Specificity	Names the domain ('epistemic quality in RAG systems', 'knowledge bases') and lists several concrete actions ('Ensures documents are properly qualified', 'Produces CGD', 'validates SOT files'), matching the 'several specific actions; minor gaps' anchor; not a 5 because coverage is not comprehensive.	4 / 5
Completeness	Has a clear 'what' (verification + CGD/SOT production) but no 'Use when...' or explicit 'when' guidance inside the description; per the rubric guideline, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant phrases like 'pre-ingestion verification', 'RAG systems', and 'knowledge bases', but natural user-said terms and synonyms are limited and mostly niche; matches 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (CGD/SOT, epistemic quality) with low overlap risk, but the niche-jargon phrasing keeps it just below the 'clear niche with minimal conflict risk' anchor of 5.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (714 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/clarity-gate/SKILL.md
Commit: 57c135b

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.