SKILLEMALL.ai
GitHub ↗ RU Sign in

BF stock-factor

股票因子（Stock Factor）技能 —— 当前已收录 **1101 个因子（18 个因子族）**，为 AI 提供一套已收集、已转写、可由 QuantAll（全A解析）直接运行的 A 股因子清单（含 IC / IR / time_potential 等评估指标）。既可直接读取因子清单（scripts/output/*.xlsx）， 也可通过 run_task_file 执行 scripts/task/*.json 用 QuantAll 实时重算/更新因子参数。 已汇总 Qlib Alpha158、Qlib Alpha360、国泰君安 GTJA Alpha191、WorldQuant Alpha101（已全量转写）， 并补充 stock_daily（量价/估值/市值/换手等）、stock_report（财务质量/成长/偿债）两类基础因子， 以及 TA-Lib 技术指标 + 常用指标（KDJ/BIAS）共 84 个。 内置 gen_report.py 报告生成器：一键汇总全部因子族的 IC/IR 统计并生成可视化 HTML 报告。 触发：用户提到"股票因子""因子清单""因子库""因子分析""IC分析""Alpha158/360/191/101""选股因子" "更新因子""跑因子""因子报告"等量化关键词时。 不主动在普通股市聊天中触发，仅在用户有明确因子研究/选股需求时使用。 本技能依赖 QuantAll（全A解析）MCP 计算引擎，使用前需先安装并启动它。

ClawHub Agent Skills author: mifochen v1.3.0 MIT-0 39 files body ≈ 7 707 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

股票因子（Stock Factor）技能 —— 当前已收录 1101 个因子（18 个因子族），为 AI 提供一套已收集、已转写、可由 QuantAll（全A解析）直接运行的 A 股因子清单（含 IC / IR / timepotential…

As a process F 33/100 · Will not run — References files that are not bundled: scripts/task/*.json, scripts/因子初始参考文件/TA_Indicators_跳过汇总.txt, scripts/output/*.xlsx

ProcedureExcelData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
95
Quality 40%
49
Run on models
none yet
Process rating
F
33/100
Will not run
References files that are not bundled: scripts/task/*.json, scripts/因子初始参考文件/TA_Indicators_跳过汇总.txt, scripts/output/*.xlsx
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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 · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token scripts/因子分析报告.html:63
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    <img class="chart" src="data:image/png;base64,iVBO…toD+AAAA…Q6w
    quoted
  • low Secrets in code secret-high-entropy-token scripts/因子分析报告.html:64
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    <img class="chart" src="data:image/png;base64,iVBO…toD+AAAA…Q6w
    quoted
  • low Secrets in code secret-high-entropy-token scripts/因子分析报告.html:72
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    <img class="chart" src="data:image/png;base64,iVBO…jO1/AAAA…toD+AAAA…Q6w
    quoted
  • low Secrets in code secret-high-entropy-token scripts/因子分析报告.html:73
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    <img class="chart" src="data:image/png;base64,iVBO…toD+AAAA…Q6w
    quoted
  • low Secrets in code secret-high-entropy-token scripts/因子分析报告.html:80
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    <img class="chart" src="data:image/png;base64,iVBO…toD+AAAA…Q6w
    quoted

Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 7707 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/task/*.json
  • warning missing-ref reference to a missing file: scripts/因子初始参考文件/TA_Indicators_跳过汇总.txt
  • warning missing-ref reference to a missing file: scripts/output/*.xlsx
  • warning missing-ref reference to a missing file: scripts/output/facotr-Qlib_alpha158.xlsx
  • warning missing-ref reference to a missing file: scripts/output/facotr-Qlib_alpha360.xlsx
  • warning missing-ref reference to a missing file: scripts/output/factor-GTJA_Alpha191.xlsx
  • warning missing-ref reference to a missing file: scripts/output/factor-Alpha101.xlsx
  • warning missing-ref reference to a missing file: scripts/output/factor-Indicators.xlsx
  • warning missing-ref reference to a missing file: scripts/output/factor-stock_daily.xlsx
  • warning missing-ref reference to a missing file: scripts/output/factor-stock_report.xlsx
  • warning missing-ref reference to a missing file: scripts/output/
  • warning missing-ref reference to a missing file: scripts/task/factor-TA_Indicators.json
  • warning missing-ref reference to a missing file: scripts/Create_DuckDB.py
  • warning missing-ref reference to a missing file: scripts/UpdateStock_script.py
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: scripts/task/*.json, scripts/因子初始参考文件/TA_Indicators_跳过汇总.txt, scripts/output/*.xlsx
  • 0Tools and files. 14 referenced file(s) missing: scripts/task/*.json, scripts/因子初始参考文件/TA_Indicators_跳过汇总.txt, scripts/output/*.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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 70Execution cost. Instruction body is 7707 tokens
  • 100Steps. 96 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress

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
  • -2localhost URLs: will not work for another user
  • -236 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 640: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 96 items
  • +4Has examples (6 code blocks)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.

External checks

ClawHub: clean
This skill is a disclosed stock-factor research helper that uses local QuantAll analysis files and scripts without evidence of hidden data access or unsafe behavior.
LLM: benign (high) · VirusTotal: · 13 Aug 2026