SKILLEMALL.ai

BC halucatch

Evaluates the reliability of AI Skill execution. Assesses whether a Skill's output is trustworthy, reproducible, and withstands business scrutiny when executed by an AI agent. Covers four dimensions: data pipeline integrity, code risk, business logic ambiguity, and interpretation guardrails. Use when auditing an AI Skill, checking for hallucinations or unreliable outputs, verifying execution reproducibility, or reviewing a Skill's safety before deployment or sharing.

ClawHub Hermes author: Codery v1.8.8 MIT-0 22 files body ≈ 2 573 tokens Open the sourceclawhub.ai analyzed 30 h ago

Evaluates the reliability of AI Skill execution.

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerCustomer supportInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
C
50/100
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Bash

Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 472 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"

Process rating: all ten parameters 50/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 28 steps
  • 100Execution cost. Instruction body is 2573 tokens
  • 100Running it twice. No mutating operations
  • low 11 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -251 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 471: enough signal without eating the budget
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 28 items
  • +4Has examples (3 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
HaluCatch is a local skill-audit tool that reads a user-selected skill folder and writes Markdown reports, with no evidence of hidden network access, credential use, destructive behavior, or persistence beyond report files.
LLM: benign (high) · VirusTotal: · 12 Jul 2026