clarity-gate
Verifies documents for clarity and accuracy before they are added to RAG systems.
Install
mkdir -p .claude/skills/clarity-gate && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7250" && unzip -o skill.zip -d .claude/skills/clarity-gate && rm skill.zipInstalls to .claude/skills/clarity-gate
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflowKey capabilities
- →Perform 9-point epistemic verification
- →Generate Clarity-Gated Documents (CGD)
- →Validate Source of Truth (SOT) files
- →Execute HITL claim tracking
- →Compute deterministic document hashes
How it works
The tool enforces the presence of uncertainty markers in claims where epistemic quality is required. It uses structural validation rules and HITL verification records to ensure documents meet the Clarity Gate Format Specification.
Inputs & outputs
When to use clarity-gate
- →Pre-ingestion document review
- →Check for hallucination risks
- →Validate source of truth
About this skill
Clarity Gate v2.1
Purpose: Pre-ingestion verification system that enforces epistemic quality before documents enter RAG knowledge bases. Produces Clarity-Gated Documents (CGD) compliant with the Clarity Gate Format Specification v2.1.
Core Question: "If another LLM reads this document, will it mistake assumptions for facts?"
Core Principle: "Detection finds what is; enforcement ensures what should be. In practice: find the missing uncertainty markers before they become confident hallucinations."
Detailed Guide
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
Critical Limitation
Clarity Gate verifies FORM, not TRUTH.
This skill checks whether claims are properly marked as uncertain—it cannot verify if claims are actually true.
Risk: An LLM can hallucinate facts INTO a document, then "pass" Clarity Gate by adding source markers to false claims.
Solution: HITL (Human-In-The-Loop) verification is MANDATORY before declaring PASS.
When to Use
- Before ingesting documents into RAG systems
- Before sharing documents with other AI systems
- After writing specifications, state docs, or methodology descriptions
- When a document contains projections, estimates, or hypotheses
- Before publishing claims that haven't been validated
- When handing off documentation between LLM sessions
What This Skill Does NOT Do
- Does not classify document types (use Stream Coding for that)
- Does not restructure documents
- Does not add deep links or references
- Does not evaluate writing quality
- Does not check factual accuracy autonomously (requires HITL)
When not to use it
- →Classifying document types
- →Restructuring document content
- →Autonomous factual accuracy verification
Prerequisites
Limitations
- →Verifies form, not truth
- →Requires HITL for final validation
How it compares
Unlike tools that detect existing hedges, this skill enforces the inclusion of uncertainty markers for claims that require them.
Compared to similar skills
clarity-gate side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| clarity-gate (this skill) | 1 | 6mo | Review | Intermediate |
| firecrawl-scraper | 24 | 10mo | Caution | Beginner |
| embedding-strategies | 8 | 4mo | No flags | Intermediate |
| pinecone | 3 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by sickn33
View all by sickn33 →You might also like
firecrawl-scraper
jackspace
Scrape and extract web content, convert HTML to markdown, and bypass bot protection for dynamic sites using Firecrawl API.
embedding-strategies
wshobson
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
pinecone
davila7
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
embeddings
ruvnet
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
trulens-dataset-curation
truera
Create and curate evaluation datasets with ground truth for TruLens
ailey-tools-tag-n-rag
armoin2018
Process and index content from files, folders, Git repos, or URLs into tagged RAG (Retrieval Augmented Generation) sets with ChromaDB. Supports text, markdown, video/audio transcription, OCR, intelligent chunking, and metadata tagging. Use when preparing content for AI retrieval, building knowledge