AF exa
Neural web search and content extraction via SkillBoss API Hub. Requires SKILLBOSS_API_KEY. Use for finding documentation, code examples, research papers, or company info.
As a process F 34/100 · Will not run — weak spots: result and completion, when it triggers, inputs and preconditions
IntegrationSoftware developmentInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
This is a copy of a skill from another catalog; the rating counts the canonical one: exa (ClawHub)
How to improve
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Map keys must be unique at line 3, column 1: name: exa name: exa ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 34/100
- 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
- 40Consistency. Frontmatter name (exa) differs from the folder (kirk-search)
- 50Steps. 2 steps
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Execution cost. Instruction body is 178 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 171: enough signal without eating the budget
- +4Structure: 6 headings
- +4Has examples (4 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.
External checks
ClawHub: clean
This skill is a straightforward hosted search and content-extraction helper, but users should treat searches and URLs as data sent to a third-party API.
LLM: benign (high) · VirusTotal: · 29 May 2026