菜单
Produce a publication-ready correlation heatmap (PDF+PNG) from a CSV or in-memory dataframe. Triggers when the user asks for "correlation heatmap", "corr matrix figure", or uploads a *.csv with numeric columns and asks for a heatmap.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Produce a publication-ready summary-statistics table from a CSV or in-memory dataframe. Triggers when the user asks for "summary stats", "describe data", or uploads a *.csv with numeric columns and asks for a table.
Read a corpus of the user's published papers (PDFs) and produce a VOICE.md style guide capturing recurring phrasing, sentence rhythm, hedging style, structural moves, and a ban list. Triggers when the user asks to "extract my voice", "build a voice file from these papers", or runs /voice-extractor.
Produce a multi-perspective referee report on a working paper PDF. Spawns three reviewer subagents (empirical, theory, methods), then consolidates their memos into a single editor-facing report. Triggers on commands like /referee-report or when the user uploads a PDF and asks for a "referee" / "review".
Create a rigorous, dependency-mapped revision master plan from peer review reports with computational DAG validation using NetworkX. Use when academic authors receive reviewer comments (R&R, revise-and-resubmit) and need a coherent revision strategy with validated dependency graphs, parallel execution schedules, critical path analysis, and bottleneck identification. Triggers include requests to analyze reviewer comments with DAG validation, plan a revision with dependency checking, create a computationally validated revision roadmap, validate revision dependencies, or identify critical paths in a revision plan. Designed for empirical research papers in accounting, finance, economics, management, and information systems.
Stage 3. Emit a LaTeX table of the regression coefficients. Triggers when state.stage == "regressed".
Stage 1 of the pipeline. Fetch a small CRSP return panel from WRDS and write it to data/returns.csv. Update state.json. Verify schema. Triggers when state.stage == "init".
| name | edhec-corr-heatmap |
| description | Produce a publication-ready correlation heatmap (PDF+PNG) from a CSV or in-memory dataframe. Triggers when the user asks for "correlation heatmap", "corr matrix figure", or uploads a *.csv with numeric columns and asks for a heatmap. |
| args | {"input":"path to CSV or name of in-memory dataframe","output":"optional stem for the figure (default figures/corr_heatmap) -- writes <stem>.pdf and <stem>.png","method":"pearson | spearman | kendall (default pearson)"} |
A four-phase skill. Each phase ends with a checkpoint the user can interrupt.
Read the input. Identify numeric columns. For each column report:
Stop and surface anything with > 5% missing, constant values (zero variance),
or non-numeric dtype that survived coercion. Note that pairwise-complete
observations are used by default (the pandas.corr default).
Print:
pearson)figures/corr_heatmap)If the proposed matrix would have > 15 columns, stop and ask for confirmation.
Compute the correlation matrix. Use:
df.corr(method=method, numeric_only=True)np.triu(np.ones_like(corr, dtype=bool), k=1)
so the diagonal is hidden tooEmit a heatmap figure:
seaborn.heatmap(corr, mask=mask, annot=True, fmt=".2f", cmap="RdBu_r", vmin=-1, vmax=1, square=True, cbar_kws={"shrink": 0.7})plt.tight_layout()<stem>.pdf (vector, for LaTeX) and <stem>.png (dpi=200, for previews)figures/corr_heatmap