AF agent-config-lint
Check agent config for things that break silently on someone else's machine. Use before publishing or committing a SKILL.md, AGENTS.md, CLAUDE.md or llms.txt, before publishing a skill to ClawHub, when a skill "works on my machine" but not for a teammate, when a skill fails to trigger, or when asked to review agent config. Catches references to files that do not exist, absolute paths under the author's home directory, undeclared CLI dependencies, a frontmatter name that does not match the skill's directory, and two skills whose descriptions are so similar the agent fires the wrong one.
Check agent config for things that break silently on someone else's machine.
As a process F 39/100 · Will not run — References files that are not bundled: scripts/build-report.py
How to improve
- 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 · 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
missing-refreference to a missing file: scripts/build-report.py
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: scripts/build-report.py
- 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
- 50When it triggers. No condition that starts the skill
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 814 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 592: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.