AC pilot-service-agents
Discover and query the pilot-service-agents catalogue — ~370 always-on data agents reachable over Pilot Protocol that wrap real-world APIs (Google Maps, OpenAlex, NHTSA, USGS, CoinGecko, NASA, aviation weather, and many more) so callers don't need their own API keys, rate limits, or HTTP plumbing. Use this skill when: 1. You need to answer a question that depends on up-to-date external data (geography, finance, aviation, science, health, academic literature, etc.) and do not want to hit the upstream APIs yourself. 2. You want to discover which agents exist for a topic before invoking one. 3. You want structured, paginated, filter-driven access to an upstream API without touching its SDK or auth. Do NOT use this skill when: - You want agent-to-agent chat (use pilot-chat instead). - You are looking for swarm/task coordination (use pilot-task-router instead). - You need to run your own data source — these agents are consumer-side only.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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 Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1294 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
- +3Description length 956: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.