BF factor-prune
因子筛选（Factor Prune）技能 —— 在 stock-factor 技能产出初始因子清单（IC/IR 评估结果）后， 对有效因子做贪心前向选择 + 去相关筛选，精选出一组高有效性、低冗余的因子集合。 算法：汇总所有因子 → 按 |IR|/IC/time_potential 筛选有效 → 按有效性降序 → 贪心提取最优因子 → 与剩余因子做相关性评估 → 移除高相关冗余 → 提取下一个 → 如此反复直到收敛或达到上限。 技能提供两套主实现： (1) 文件驱动六步法 `prune_flow.py`（推荐）——脚本直连 QuantAll 自己跑完整个循环，临时文件统一在内存外的 state 目录； (2) 缓存矩阵法 `prune.py`——保留相关性矩阵缓存，适合换阈值重放（replay）。 另有「顶/底10% 分侧筛选」`window_opt.py` / `window_prune.py`：以因子分位窗口为优化对象、coverage 分侧门限 + 联合评分。 触发：用户提到"因子筛选""因子去冗余""因子精选""factor prune""选有效因子""去相关" "精选因子""因子压缩""分位筛选"等关键词时。 本技能依赖 QuantAll（全A解析）MCP 计算引擎和 stock-factor 技能的输出数据。 边界：本技能只产出「精选因子清单」（已去冗余），不含因子合成 / 策略回测 / 多因子组合——这些由下游另行处理。
因子筛选（Factor Prune）技能 —— 在 stock-factor 技能产出初始因子清单（IC/IR 评估结果）后， 对有效因子做贪心前向选择 + 去相关筛选，精选出一组高有效性、低冗余的因子集合。 算法：汇总所有因子 → 按 |IR|/IC/timepotential 筛选有效 → 按有效性降序 →…
As a process F 33/100 · Will not run — References files that are not bundled: scripts/output/, scripts/factor-pure.xlsx, scripts/output/pruned_factors.xlsx
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: 13. 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: scripts/output/ - warning
missing-refreference to a missing file: scripts/factor-pure.xlsx - warning
missing-refreference to a missing file: scripts/output/pruned_factors.xlsx - warning
missing-refreference to a missing file: scripts/output/pruned_removed.xlsx - warning
missing-refreference to a missing file: scripts/factor-window-opt.xlsx - warning
missing-refreference to a missing file: scripts/factor-pure-topbottom.xlsx - warning
missing-refreference to a missing file: scripts/output/*.xlsx - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 33/100
- 0Tools and files. 7 referenced file(s) missing: scripts/output/, scripts/factor-pure.xlsx, scripts/output/pruned_factors.xlsx
- 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
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1993 tokens
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
- +2Single-language instructions
- +3Description length 627: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (4 code blocks)
- +3All 9 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.