Name: clarity-gate
Rating: 53.6 (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

61%

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-claude/skills/clarity-gate/SKILL.md

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

Quality

Content

63%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 body is well-structured with concrete, executable guidance and a clearly sequenced verification workflow, but it is longer than necessary due to redundancy and ships references to bundled files that are not actually present, weakening progressive disclosure.

Suggestions

Either include the referenced scripts/claim_id.py, scripts/document_hash.py and docs/CLARITY_GATE_FORMAT_SPEC.md in the bundle, or drop the inline algorithm/test-vector detail and keep only usage examples.

Deduplicate the validation-code tables (they appear in both 'Validation Codes' and 'SOT Validation') and move the full changelog to a separate CHANGELOG.md, keeping SKILL.md focused on the current workflow.

Tighten the 9-point section by presenting each point once with its fails/passes table rather than restating them in the SOT application table.

Dimension	Reasoning	Score
Conciseness	At ~680 lines the body is mostly task-relevant and avoids explaining basic concepts, but it repeats content (validation codes listed in both 'Validation Codes' and 'SOT Validation', the 9-point tables recur) and carries a full changelog that competes for context budget.	3 / 5
Actionability	Provides concrete, copy-paste-ready guidance (exact CLI invocations with test vectors, a full CGD YAML template, specific marker fixes), though the referenced scripts/claim_id.py, scripts/document_hash.py and docs/CLARITY_GATE_FORMAT_SPEC.md are not actually present in the bundle.	4 / 5
Workflow Clarity	The multi-step process is clearly sequenced with a tier-1/tier-2 hierarchy diagram, an explicit Round A then Round B HITL loop with a 'Reply confirmed or flag any I misread' checkpoint, and validation codes that gate PASS — a clear sequence with most checkpoints present.	4 / 5
Progressive Disclosure	Has section headers and references out to a format spec and scripts, but those referenced files (docs/CLARITY_GATE_FORMAT_SPEC.md, scripts/*.py) are not in the bundle, and substantial spec-grade content (validation-code tables, format excerpts, changelog) is inlined in SKILL.md rather than split out.	3 / 5
	Total	14 / 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 the skill's domain and several concrete actions with low conflict risk, but it omits an explicit 'when to use' clause and relies on jargon/acronyms rather than natural user trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming concrete user moments (e.g., 'Use before ingesting documents into a RAG knowledge base, or when a document mixes assumptions with facts').

Replace or supplement the CGD/SOT acronyms in the description with natural phrasing like 'check documents for unmarked assumptions' or 'verify epistemic quality'.

Add common synonyms users might say ('hallucination risk', 'document clarity check') to mirror the trigger terms already in the triggers array.

Dimension	Reasoning	Score
Specificity	Names the domain ('pre-ingestion verification for epistemic quality in RAG systems') and several concrete actions ('Ensures documents are properly qualified', 'Produces CGD', 'validates SOT files'), though the verbs are slightly more abstract than the granular PDF example.	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' clause or equivalent trigger guidance in the description itself, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains relevant keywords ('pre-ingestion', 'RAG systems', 'knowledge bases') but leans on jargon and acronyms (CGD, SOT) that users would not naturally say, missing common synonyms; the more natural phrases live in the triggers array rather than the description.	3 / 5
Distinctiveness Conflict Risk	Occupies a fairly distinct niche (epistemic-quality pre-ingestion checks for RAG) with only minor overlap risk against generic document-review skills.	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-claude/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.