BC tavily-quota-router
Tavily quota-aware multi-key search router. Load BEFORE issuing any web_search call (Tavily is the default backend in this Hermes install, and burst searches burn rate limits within seconds). Use when you want reliable Tavily-backed web search across multiple API keys, automatic failover for invalid/rate-limited keys, official usage-based routing via Tavily's /usage endpoint, and status visibility for each key. Critical rules: max 1 web_search per assistant turn, stop on first 429, do not retry within cooldown.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-useSKILL.md:155Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)**Operational rule**: when user reports "I just need it to retry in 10-20s, not 10 minutes", first check if the actual recovery time is sub-minute by directly `curl https://api.tavily.com/search -H "A
vendor-hostquoted -
low Exfiltration
net-credential-useSKILL.md:234Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)4. 直接 `curl https://api.tavily.com/search -H "Authorization: Bearer $KEY" -d '{"query":"ping"}'` 实测 → 200 = quota 正常vendor-hostquoted
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5376 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5376 tokens
- 100Steps. 67 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 516: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.