AC gate-info-defianalysis
DeFi ecosystem analysis via Gate-Info MCP. Use this skill whenever the user wants TVL rankings, protocol metrics, yield/APY, stablecoins, bridges, exchange reserves, or liquidation heatmaps. Trigger phrases include Uniswap TVL, DeFi ranking, USDC yield, bridge volume, exchange BTC reserves, liquidation density. Route coin-only fundamentals to gate-info-coinanalysis. Sub-scenario tools: info_platformmetrics_* family and info_coin_get_coin_info (exact tool names per scenario in SKILL.md).
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "updated" - note
frontmatter-keyunknown frontmatter key "required_credentials" - note
frontmatter-keyunknown frontmatter key "required_env_vars" - note
frontmatter-keyunknown frontmatter key "required_permissions"
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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (gate-info-defianalysis) differs from the folder (gate-info-defianalysis-staging)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 36 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 2788 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 491: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.