AB ask-graphql-mcp
Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially SubQuery/SubGraph). Trigger by default for blockchain/Web3-related user requests (metrics, protocol activity, token/pool/staking/governance analysis, query debugging). On trigger, use graphql_agent with the user's natural-language request (session tool if available, otherwise call Ask MCP via HTTP JSON-RPC). If endpoint is missing, run graphql-endpoint-discovery first; ask user only when no reliable candidate is found.
As a process B 69/100 · Nearly there — weak spots: consistency, running it twice, 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: 5. 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (ask-graphql-mcp) differs from the folder (web3-graphql)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 62 steps, 1 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 1480 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 518: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.