AB search
Content search and synthesis primitive using Kaito MCP tools. Use this skill to search for and synthesize content from Twitter (X) and News sources. Triggers on phrases like 'search for tweets about X', 'what's being said about Y', 'find content about Z', 'any news on X', 'what are people saying about Y on Twitter'. This is a primitive skill — it searches content via kaito_advanced_search and synthesizes results. It can be called standalone or composed into higher-level workflow skills. Do NOT use for mindshare tracking (mindshare skill), sentiment analysis (sentiment skill), or user profiling (user-profile skill).
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 2. 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 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (search) differs from the folder (crypto-search)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 70 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 3438 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 622: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 70 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.