Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Nero1688/claude-academic-skills --skill management-figuregit clone --depth 1 https://github.com/Nero1688/claude-academic-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nero1688/claude-academic-skills/management-figure)<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/management-figure"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/management-figure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nero1688/claude-academic-skills/management-figure"><img src="https://agentmods.dev/badge/skills/nero1688/claude-academic-skills/management-figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00463 | $0.03482 |
| Opus 5.5 | $0.00185 | $0.01393 |
| Sonnet 5.5 | $0.00093 | $0.00696 |
| Haiku 4.5 | $0.00046 | $0.00348 |
Grade A, and why
management-figure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
畫圖前先讀 research-framework-figure 的 references/visual-discipline.md
(兩支 skill 共用的視覺紀律:密度上限、單一強調色、Okabe-Ito 色盤、標籤經濟、
黑白可讀性),不要只看本檔的版面規範就動手。選圖與逐圖種的誠實紅線(含函式未涵蓋的
啞鈴圖、斜率圖、熱圖)、Okabe-Ito 實算對比與灰階撞色,讀 references/chart-honesty.md。
階段一:這張圖回答哪個假設(先診斷) 釐清圖要檢驗的假設(H1/H2…)、對應的迴歸式與表格。圖必須與假設、迴歸式、表格三方對齊(延續使用者的符號一致性紀律)。判準:能一句話說出「這張圖讓審查委員看到 H_k 成立/不成立」。
階段二:帶入真實數據,選對圖種
用 scripts/mgmt_figures.py(自包含,僅需 numpy+matplotlib;有 statsmodels 則用於信賴帶)。出圖前先讀 references/figure_style.md 確認版面規範。以使用者的真實迴歸輸出/係數帶入,勿用模擬值冒充:
quadratic_turning_point_plot(x, y, ...)— 二次式倒U/U,自動 OLS 二次擬合、95% CI、標轉折點 x*=-b1/(2b2)。用於非線性假設(如研發強度²、客戶集中度²)。回傳含p_b2。coefficient_forest_plot(names, coefs, ci_low, ci_high)— 係數森林圖,顯著上色、不顯著灰、零線虛線。主迴歸一圖總覽。interaction_plot(x_grid, lines, labels=...)— 交互作用/調節圖,低/中/高調節值各一斜率線,看斜率是否翻轉。調節假設(如客戶集中度調節研發強度→績效)。group_comparison_plot(groups, means, errors=...)— 分組比較(家族 vs 非家族),帶誤差線。trend_plot(years, series, labels)— 多組逐年趨勢。event_study_plot(rel_time, coef, ci_low, ci_high, ref_period=-1, pre_joint_p=None, breakdown_M=None, estimator=...)— 事件研究圖(交錯 DiD 的動態效果,causal-inference-architectrobustness-battery 的必做正文圖):逐期係數+95% CI、參考期空心點標 "ref."、處理時點垂直線、前期陰影;圖註自動印「Pre-period joint Wald p = …; robust to M̄ ≤ …」與估計量名稱,沒給的數字印 "not reported" 而不是編一個。係數來源:did::aggte(type = "dynamic")、fixest::sunab/iplot的輸出;pre_joint_p用did的 Wpval 或fixest::wald,breakdown_M用HonestDiD的 breakdown 值。回傳的info["note"]可直接貼進 caption(Windows 主控台印出含 M̄ 的字串要先PYTHONIOENCODING=utf-8)。car_plot(rel_time, series, labels=..., highlight_window=(-1, 1), lang="en", font="tw", note=None)— 短窗事件研究的平均累積異常報酬(CAAR)曲線(與上一項 DiD 動態係數圖不同):一組或多組(家族 vs 非家族)平均 CAR 路徑+95% CI 帶、事件日 t = 0 垂直線、主檢定窗淡灰底;series給逐事件 CAR 路徑矩陣(n_events × 相對日,函式算平均與橫斷面 t 型 CI,圖例自動標 N)或已算好的dict(caar, ci_low, ci_high, n)。字型預設英數 Times New Roman+中文標楷體(font="sans"改回 figure_style 的無襯線;缺字型會警告並在info["fonts_missing"]回報),lang="zh"出中文軸標。檢定數字(BMP、KP 調整 p)只在傳note=時才印,函式不代編。CAR 怎麼估、用哪個檢定見causal-inference-architect的references/event-study-estimation.md。- 邊際效果圖:調節模型下 X 對 Y 的邊際效果 ∂Y/∂X = β₁+β₃·M 隨調節值 M 變化。用
interaction_plot把 x_grid 設為 M 的取值範圍、lines 設為邊際效果(含 CI 上下界共三線)即可畫出,並在零線處標示效果轉正/負的 M 門檻。 - 函式未涵蓋的圖種(兩時點差距的啞鈴圖、斜率圖、熱圖):以 matplotlib 手寫,照
references/chart-honesty.md第三節的紅線;先過該檔「三道門」,一句話或一張表說得完的不畫。
階段三:輸出向量檔
一律用 save_fig(fig, name),同時產 png(預覽)+ pdf + svg(向量,投稿用),皆 300dpi。判準:三個檔都生成、圖內無標題(標題寫在 caption)、上右框線已 despine。
階段四:數字回溯(交付前必驗) 圖中每個數字(轉折點 x*、係數、CI 端點、分組平均、N)都要能指到來源統計輸出檔的哪一列。對不上就停,不准「先放著」。倒U圖必附 β₂ 的 p 值來源。
<matplotlib_中文字型> 軸標預設英文(投稿標準)。使用者要中文版(如口試簡報、中文期刊)時:
- 改 xlabel/ylabel/圖例字串為中文。
- 設定 CJK 字型,否則中文顯示為方框(tofu)。正式文件字型規範為標楷體(DFKai-SB / BiauKai):
標楷體檔名在 Windows 為import matplotlib matplotlib.rcParams["font.sans-serif"] = ["DFKai-SB", "BiauKai", "Microsoft JhengHei"] matplotlib.rcParams["axes.unicode_minus"] = False # 負號正常顯示kaiu.ttf;若 rcParams 設定不生效,用matplotlib.font_manager.FontProperties(fname="C:/Windows/Fonts/kaiu.ttf")逐元素套用。 - 數字與英文仍用 Times New Roman 系(西文襯線),符合中英混排規範;純圖內可維持 sans-serif 求清晰。 推測:若環境無標楷體字型檔,中文會 fallback;此時明講「本環境無標楷體,已用 <實際字型>,投稿前請於有字型的機器重出」,不要假裝已套標楷體。 </matplotlib_中文字型>
<output_contract> 交付含三部分:
- 圖檔路徑:png/pdf/svg 三份路徑,註明 300dpi、色盲友善。
- 圖說 caption 草稿:說明變數、樣本、N、關鍵統計量(轉折點值、β₂ 顯著性、調節斜率差)。
- 數字回溯表:圖中每個關鍵數字 → 來源輸出檔位置。倒U圖必列「β₂=…, p=…,來源:<檔>」;β₂ 不顯著時明確標「非線性證據不足」。 </output_contract>
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 47bb3437a08f
- 18d ago Changed · +4 lines · +29 tokens per session e1c01ad9a9d3
- 1mo ago Changed · +5 lines · +60 tokens per session 463c5e54ed8c
- 1mo ago First seen · 74 lines · 374 tokens per session scan A 5a544475bbbd
management-figure is a skill published in the GitHub repository Nero1688/claude-academic-skills (13 stars, last pushed 5d ago), licensed MIT. It adds 463 tokens to every session and 3,482 once invoked, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
alterlab-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…
alterlab-deep-research
Runs a 13-agent deep research pipeline for rigorous academic work on any topic across 7 modes (full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis), covering research-question formulation, Socratic mentoring, methodology…
alterlab-imaging-data-commons
Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for…
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-deeptools
Process and visualize deep-sequencing coverage with the deepTools CLI — convert BAM to bigWig (bamCoverage), build log2 ratio tracks (bamCompare), run QC (multiBamSummary correlation, PCA, plotFingerprint), apply the ATAC-seq Tn5 shift (alignmentSieve --ATACshift), and make TSS/peak heatmaps and profiles…
alterlab-esm
Run ESM protein language models — ESMC for embeddings and representations, ESMFold2 for structure prediction, and ESM3 for generative multimodal protein design across sequence, structure, and function — locally or through the hosted Biohub Platform API (formerly Forge). Use when working with protein sequences…