AF write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Create new agent skills with proper structure, progressive disclosure, and bundled resources.
As a process F 28/100 · Will not run — References files that are not bundled: REFERENCE.md
This is a copy of a skill from another catalog; the rating counts the canonical one: write-a-skill (ClawHub)
How to improve
- The text references files that are not there: add them or drop the references.
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 · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: REFERENCE.md
Process rating: all ten parameters 28/100
Will not run. References files that are not bundled: REFERENCE.md
- 0Tools and files. 1 referenced file(s) missing: REFERENCE.md
- 0Result and completion. Does not say what the result is
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (write-a-skill) differs from the folder (write-a-skill-v3)
- 100Steps. 31 steps
- 100Execution cost. Instruction body is 708 tokens
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
- +1No license
- +2Single-language instructions
- +3Description length 153: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.
External checks
ClawHub: clean
The available evidence does not show hidden, destructive, or unrelated behavior, and the supplied security scanners are clean.
LLM: benign (medium) · VirusTotal: · 17 Jun 2026