SKILLEMALL.ai
GitHub ↗ RU Sign in

BA omh-failure-signal-audit

[omh] Hidden or swallowed errors suspected: find swallowed errors, unsafe fallbacks, hidden UI/runtime failures, and missing propagation before they become false green status. Use when the user says: failure-signal-audit, failure signal audit, silent failure, silent failures, silent failure hunter, swallowed error, swallowed errors, empty catch.

rlaope/oh-my-hermes Hermes author: rlaope 1 file body ≈ 2 025 tokens Open the sourcegithub.com↗ analyzed 15 h ago

[omh] Hidden or swallowed errors suspected: find swallowed errors, unsafe fallbacks, hidden UI/runtime failures, and missing propagation before they become…

As a process A 80/100 · Runs to the end — weak spots: result and completion

AnalyzerSoftware developmentData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
91/100
safety, quality, tests
Safety 60%
99
Quality 40%
79
Run on models
none yet
Process rating
A
80/100
Runs to the end
Result and completion w 14
0
Consistency w 8
60
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: omh-failure-signal-audit (rlaope/oh-my-hermes)

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
  • low Concealment en-hide-from-user SKILL.md:26
    Instruction to hide actions from the user (negated — the text forbids it)
    - The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
    negated

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 347 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 80/100

  • 0Result and completion. Does not say what the result is
  • 60Consistency. The Hermes dialect needs category and tags
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 47 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Execution cost. Instruction body is 2025 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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 347: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.