BC typed-decisions-around-llms
Decide WHERE a typed judgment model (TypeSafe's Jev or any System One model) belongs relative to a generative LLM, and who is allowed to authorize what. Use when adding a guardrail, router, verifier, or approval gate around an LLM; when converting a free-text 'LLM-as-judge' step into a typed decision; when a model's own confidence score is being used to authorize its own output; when choosing thresholds, confidence bands, or fallback behavior; or when reviewing an agent/tool-calling pipeline for who holds authority. This is the architecture question — placement, ordering, and authority. For API mechanics, primitive selection, and question wording use the typesafe-ai skill and the live docs instead.
Decide WHERE a typed judgment model (TypeSafe's Jev or any System One model) belongs relative to a generative LLM, and who is allowed to authorize what.
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 707 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70Execution cost. Instruction body is 4092 tokens
- 100Steps. 63 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +2Single-language instructions
- +3Description length 707: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 63 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.