BB template-library
Template register: name, type, owning module and department, owner, last updated and content link. Use for document template governance.
The skill offers a template registry with fields for name, type, owner, and update history. One instruction file at 3077 tokens, no critical errors or safety issues. Grade B reflects decent content quality (79) but weaker process implementation (66). No model testing data available for Claude or Hermes. Works as a boilerplate for document template governance in small setups. Install if you already have a use case in mind.
Template register: name, type, owning module and department, owner, last updated and content link.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 136 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_type" - note
frontmatter-keyunknown frontmatter key "date_added" - note
frontmatter-keyunknown frontmatter key "tools" - note
frontmatter-keyunknown frontmatter key "source_repo" - note
edit-residuethe text marks something as outdated (lines 210): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 66/100
- 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. 8 mutating operations with no state check
- 60Failures and branches. 2 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 37 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3077 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 136: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.