BF alva
Use this skill when the user asks for financial data ("price of BTC", "P/E ratio of NVDA"), market analysis, stock or crypto research, quant strategies, backtesting ("backtest a momentum strategy"), tracking assets or portfolios, or help turning investing ideas into live playbooks, dashboards, and analytics on Alva. Powered by 250+ financial data sources across crypto, equities, macro, on-chain, and social data, along with cloud-side analytics and backtesting. Also use when the user asks about Alva platform capabilities.
As a process F 68/100 · Will not run — References files that are not bundled: user.md, market-views.md, references/api/*.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 45. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 16653 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: user.md - warning
missing-refreference to a missing file: market-views.md - warning
missing-refreference to a missing file: references/api/*.md
Process rating: all ten parameters 68/100
- 0Tools and files. 3 referenced file(s) missing: user.md, market-views.md, references/api/*.md
- 10Execution cost. Instruction body is 16653 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 158 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 33 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 24 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (28 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
- +4Description does not say when NOT to use the skill (false activations)
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 526: enough signal without eating the budget
- +4Structure: 75 headings
- +3Step-by-step instructions: 158 items
- +3Output format is stated explicitly
- +4Has examples (25 code blocks)
- +4Reference files are cited in the instructions (14 of 15)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.