BF tech-earnings-deepdive
科技股财报深度分析与多视角投资备忘录系统（v3.0）。覆盖A-P共16大分析模块、6大投资哲学视角、机构级证据标准、反偏见框架和可执行决策体系。当用户提到某科技公司财报分析、季报/年报解读、earnings call、收入增长分析、利润率变化、guidance指引、估值模型、DCF、反向DCF、EV/EBITDA、PEG、Rule of 40、管理层分析、竞争格局、持仓判断、是否买入/卖出/加仓某科技股、某公司最新财报怎么看、帮我做个deep dive、多角度估值、投资大师怎么看这家公司、variant view、key forces、kill conditions、筹码分布、高管团队、合作伙伴生态、宏观政策影响等话题时，务必使用此技能。即使用户只是笼统地问"帮我看看NVDA最新财报"或"META这季度表现如何"或"该不该继续持有MSFT"，也应触发此技能来提供全面的财报分析和多视角投资备忘录。此技能与us-value-investing技能互补——us-value-investing侧重长期价值四维评分，本技能侧重最新财报的深度拆解、多投资哲学的综合判断、以及可执行的持仓决策。
As a process F 35/100 · Will not run — References files that are not bundled: references/valuation-models.md, references/investing-philosophies.md, references/bias-checklist.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/valuation-models.md - warning
missing-refreference to a missing file: references/investing-philosophies.md - warning
missing-refreference to a missing file: references/bias-checklist.md
Process rating: all ten parameters 35/100
- 0Tools and files. 3 referenced file(s) missing: references/valuation-models.md, references/investing-philosophies.md, references/bias-checklist.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1557 tokens
- 100Running it twice. No mutating operations
- 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
- +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
- +5Description quotes 3 example trigger phrases
- +3Description length 497: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.