BC stanley-druckenmiller-workflow
Thesis-driven macro-to-execution market workflow in natural Chinese or English. Generate A-share and U.S. equity Morning Briefs, Intraday Alerts, Close Reviews, Weekly Regime Resets, and pre-trade sanity checks. Use when the user asks for an A-share morning brief, a U.S. morning brief, a pre-market view, an intraday state update, an end-of-day review, a weekly regime reset, a market-location read, portfolio-bias guidance, falsification conditions, market priority, industry priority, or a translation from liquidity, rates, credit, real-economy demand, price, structure, sector expression, fundamentals, and reflexivity into Regime, Best Expression, Position Bias, Kill-switch, and Watchlist.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
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 · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9649 tokens (recommended < 5000); move details to references/
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
- 40Execution cost. Instruction body is 9649 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 605 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 18 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 696: enough signal without eating the budget
- +4Structure: 91 headings
- +3Step-by-step instructions: 605 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.