SKILLEMALL.ai

AC agent-native-speaker

Use when user asks about Agent architecture, design, or how an Agent works. Two-layer teaching: Layer 1 explains Agent concepts (agent loop, tool calling, memory, session, config), Layer 2 reads the Agent's own source code to explain specific architecture. Follows the Self-Explanation Protocol: always search code before answering architecture questions.

ClawHub Hermes author: joey xin v1.1.0 MIT-0 6 files body ≈ 3 874 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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 · 0

✓ No critical or high findings

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 355 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 60Tools and files. Uses tools (read) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 42 steps
  • 100Failures and branches. 7 branches, has a failure section
  • 100Execution cost. Instruction body is 3874 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +2Single-language instructions
  • +3Description length 355: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 42 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: clean
This is a documentation-only teaching skill that may read local source code for architecture explanations, and that behavior is disclosed and aligned with its purpose.
LLM: benign (high) · VirusTotal: · 28 May 2026