BC stock-realtime-brief
A股投研体系 v5.0 - 散户级 Bloomberg. 七大新工具：(1) DCF 内在价值 - 巴菲特/段永平/林奇思想 (2) 板块轮动识别 (3) 卖出信号体系 - 5维 (4) 北极星监控 - 公告自动 (5) 实时盘中警报 (6) 财报自动解析 (7) 历史回测引擎. 含 v2.1 选股模型(5维100分) + v5.0 蓝军对垒 + 7 铁律。触发: 盘前简报 / 智能选股 / 板块排名 / DCF估值 / 北极星 / 实时警报 / 财报解析 / 历史回测 / 纪律检查。仅适用 A股。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 64. 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")
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 136 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3101 tokens
- 100Progress reporting. Reports progress
- 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -264 emoji in the instructions: noise for the model
- -43 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 252: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 136 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.
External checks
ClawHub: suspicious
This is a coherent A-share analysis skill, but it includes under-scoped credential use, hard-coded portfolio paths, persistent monitoring, and QQ message sending to a fixed chat target.
LLM: suspicious (high) · 6 Jul 2026