BD us-stocks-analysis
US stocks analysis by an adversarial investment committee. Legendary-investor personas independently research a thesis, attack each other's cases against a shared evidence ledger (sentiment, smart money, SEC fundamentals), and reconcile into a verdict with recorded dissents. Structured rubrics keep every number sourced, on any model. Includes five quick data workflows. Use for stock research, investment thesis, bull case vs bear case, due diligence on a ticker, should I buy this stock, deep dive on a company. Read-only. No trading, no purchases, no write operations, no wallet access.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, 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:67Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -H "X-SentiSense-API-Key: $SENTISENSE_API_KEY" \
security skill -
low Secrets in code
secret-high-entropy-tokenSKILL.md:171High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)2. For sectors with `weeklyChange > +5` or `< -5`: `GET /api/v1/insights/market`. **There is no ticker field on these rows.** Each item carries exactly `insightId`, `insightType`, `insightText`, `cate
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 17635 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "primaryEnv"
Process rating: all ten parameters 48/100
- 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
- 10Execution cost. Instruction body is 17635 tokens: crowds the task out of the window
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 37 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 71 steps
- 100Failures and branches. 17 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 590: enough signal without eating the budget
- +4Structure: 46 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (25 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.