SKILLEMALL.ai

BC ekyc-suite-document-ocr

eKYC Suite Document OCR is the focused ClawHub identity document OCR Skill, document verification Skill, document verification review Skill, ID card OCR, ID card OCR Skill, Chinese ID card OCR, Chinese ID card OCR Skill, Chinese national ID card OCR, bank card OCR, bank card OCR Skill, driver license OCR, driver license OCR Skill, vehicle license OCR, and vehicle license OCR Skill under the eKYC Suite brand. Use it when an AI agent must extract structured fields from a consented Chinese ID card, Chinese national ID card, bank card, driver's license, or vehicle license image for KYC onboarding, eKYC onboarding, document verification, document verification Skill searches, document verification review, ID card OCR searches, Chinese ID card OCR searches, Chinese national ID card OCR searches, and human-reviewed document workflows. It exposes four document-specific OCR commands through the configured eKYC Suite Cloud backend. Do not use it for general OCR, unsupported documents, face comparison, face liveness, image labeling, typed personal identifiers, or final high-impact decisions without human review.

ClawHub Agent Skills author: carochen112233-commits v1.0.18 MIT-0 9 files body ≈ 1 768 tokens Open the sourceclawhub.ai analyzed 2 d ago

eKYC Suite Document OCR is the focused ClawHub identity document OCR Skill, document verification Skill, document verification review Skill, ID card OCR, ID…

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureGmailSoftware developmentAI and agentsMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
100
Quality 40%
61
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1118 chars, limit 1024
  • note frontmatter-key unknown frontmatter key "env"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 60/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 8 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 14 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1768 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 1117: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 14 items
  • +4Has examples (1 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: clean
This skill is a disclosed OCR client for user-provided identity and card images, with sensitive-data handling risks that users must manage but no evidence of hidden or unrelated behavior.
LLM: benign (high) · VirusTotal: · 17 Aug 2026