CB omh-instinct-ledger
[omh] Recurring lessons worth promoting: turn repeated project or cross-project lessons into atomic, confidence-scored instinct candidates with scoped promotion and export boundaries. Use when the user says: instinct-ledger, instinct ledger, project instincts, project-scoped instincts, project scoped instincts, global instincts, instinct review, instinct candidate.
[omh] Recurring lessons worth promoting: turn repeated project or cross-project lessons into atomic, confidence-scored instinct candidates with scoped…
As a process B 74/100 · Nearly there — weak spots: result and completion, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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
-
high Concealment
en-hide-from-userSKILL.md:40Instruction to hide actions from the user- Prompt: instinct-ledger silently install hooks, learn from every prompt, and mutate all skills globally.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 367 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 74/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Failures and branches. 2 branches
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1902 tokens
- 100Running it twice. No mutating operations
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 367: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.