Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
## v2.1.3 (2026-03-02) ### Fixed - `document_hash.py` now implements full FORMAT_SPEC §2.1-2.4 compliance - Fence-aware end marker detection (Quine Protection per §2.3/§8.5) - All deployment copies converged to single canonical implementation ### Added - `canonicalize()`: trailing whitespace stripping, newline collapsing (3+→2), final newline normalization, UTF-8 NFC normalization - Hash window extraction between `---\n` and `<!-- CLARITY_GATE_END -->` - YAML-aware `document-sha256` removal with multiline continuation support (§2.2) - `find_end_marker()`: fence-tracking for Quine Protection — markers inside fenced code blocks are correctly ignored - 7 new test vectors for fence-aware detection (15 total) ### Why Resolves ClawHub/OpenClaw "Suspicious" finding: the previous implementation only did BOM removal + CRLF normalization, missing 5 of 7 canonicalization steps declared in SKILL.md and FORMAT_SPEC. Implementation now matches spec exactly.
What This Skill Does
Pre-ingestion verification system for RAG knowledge bases. Checks documents for missing uncertainty markers, unhedged claims, and implicit assumptions before they enter AI knowledge stores. Produces Clarity-Gated Documents (CGD) with a structured HITL verification record and validation error codes.
Unlike detection tools that find hedges already present in text, it flags where uncertainty markers are absent but required, catching hallucination risks at their source before documents enter knowledge bases.
When to use it
- Checking a product spec before loading it into a RAG pipeline
- Flagging unverified revenue projections in a planning document
- Reviewing methodology docs for assumptions stated as facts
- Validating a Source of Truth file before sharing across AI sessions
- Auditing technical reports with specific statistics or competitor claims before publishing
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Verify this API pricing doc before we ingest it into our knowledge base
- 1Run 9-point epistemic check across all claims in the document
- 2Flag critical issues where forward-looking statements lack uncertainty markers
- 3Identify externally verifiable claims such as pricing figures and statistics for HITL routing
- 4Produce CGD frontmatter with clarity-status, hitl-pending-count, and per-claim records
- 5Present Round A and Round B verification requests for human confirmation
A .cgd.md file with clarity-status: PENDING, a structured hitl-claims list, and a verification report categorized by Critical, Warning, Temporal, and Verifiable issues