BF effective-agent-skills
Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.
Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.
As a process F 42/100 · Will not run — References files that are not bundled: references/foo.md, scripts/validate.py
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The text references files that are not there: add them or drop the references.
- 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
-
medium Instruction override
en-ignore-previousSKILL.md:291Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)- Check references for prompt injection ("ignore previous instructions...")detector
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 100 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: references/foo.md - warning
missing-refreference to a missing file: scripts/validate.py - note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_repo" - 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 "license_source"
Process rating: all ten parameters 42/100
- 0Tools and files. 2 referenced file(s) missing: references/foo.md, scripts/validate.py
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 80 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3824 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Description length 100: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 43 headings
- +3Step-by-step instructions: 80 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.