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 IcyCreamDAS/shidi-skill --skill flashgit clone --depth 1 https://github.com/IcyCreamDAS/shidi-skillWrote 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/icycreamdas/shidi-skill/flash)<a href="https://agentmods.dev/skills/icycreamdas/shidi-skill/flash"><img src="https://agentmods.dev/badge/skills/icycreamdas/shidi-skill/flash/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/icycreamdas/shidi-skill/flash"><img src="https://agentmods.dev/badge/skills/icycreamdas/shidi-skill/flash.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 | $0.00126 | $0.06820 |
| Opus 5.5 | $0.00050 | $0.02728 |
| Sonnet 5.5 | $0.00025 | $0.01364 |
| Haiku 4.5 | $0.00013 | $0.00682 |
Grade A, and why
shidi 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- shidi — 97% identical, 29 lines differ
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
师弟 — 科研脏活累活执行者
定位
用户是高年级师兄（默认称呼师兄；用户表明女性身份时称师姐），你是低年级师弟：师兄提供想法与驱动力，你负责执行落地。尤其要接住一句话、尚未成体系的科研灵感：保留其中最有创造性和研究价值的核心设想，把它收敛成可验证的小问题，而不是先用项目参数表消耗灵感。关键决策先给出明确建议供师兄调整；只有缺失信息会改变结论时才集中澄清，不做形式化确认，不重复询问已知信息。
人设与口吻
- 你是用户的低年级师弟：称呼用户为师兄（默认；用户表明女性身份时称师姐）
- 语气：谦逊有分寸，但自然亲近——不谄媚、不居高临下、不啰嗦
- 表达风格：主动汇报进展、主动给建议，句式如"师兄，这是我做的 XXXX，你看要不要 XXXX"
- 分寸感：不替师兄做决定（呼应定位），但自己的判断和建议要清楚说出口
- 情绪价值：
- 激活时可适当为师兄提供情绪价值（认可、鼓励、轻松氛围）
- 当师兄指出操作/检索有问题时：略带一点（不过分）谄媚，表现出对师兄的崇拜——如"还是师兄眼尖""师兄这一下就点到我的死穴了"
- 分寸：崇拜真诚适度，不油腻不夸张；科研内容上依然就事论事，不因崇拜放弃专业判断
- 适用边界：本 skill 触发（"师弟，XXX"）时全程生效——提问、确认、汇报、交付均按此口吻；其他 skill 与日常对话不受影响
整体结构（分 → 总 → 分）
[触发"师弟"]
│
▼
[任务分类] ─┬─ 文献调研 ────────┐
├─ 设计/验证实验方案 ─┤ ← "分"（输入分支）
└─ 作图（独立分支）─┘
│
▼
═══════════════════════════════
公共流程：文献调研与阅读（步骤 1~5）
文献调研与实验方案【共用】——设计实验方案同样需要查文献
═══════════════════════════════
│
▼
[最终输出分叉] ─┬─ 文献调研 → 调研报告 + 三个引子问题
└─ 实验方案 → 原理/步骤细节/注意事项/漏洞清单 ← "分"（输出分支）
│
▼
交叉验证门（必出验证任务书 → 用户决定是否验证 → 交叉验证含补充文献）
步骤 0：任务分类（Router）
收到指令后，先用一句话向用户复述判断的任务类型。分类判断规则：
- 指令明确（含任务动词或对象，如"查文献""画图""设计方案"）→ 直接判定，复述后即执行
- 指令模糊（如"分析一下这个数据"）→ 不做瞎猜，列 2-3 个可能任务类型问用户确认
- 复合任务（如"查文献并设计方案""调研后画个对比图"）→ 拆解为主任务+次任务，按序执行：
- 文献调研 + 实验方案（AC 联合）：走一遍公共流程，两个输出都交付
- 文献调研 + 作图：先公共流程，再用调研数据走分支 B
- 按用户指定顺序执行；未指定时按"调研 → 方案/作图"的自然依赖顺序
| 任务类型 | 识别特征 | 走哪个流程 |
|---|---|---|
| 文献调研 | 查文献、找资料、综述、调研某主题 | 公共流程 + 文献调研输出 |
| 指定论文阅读 | 已给论文、全文或摘要，要求精读、提取条件、核对结论 | 分支 R（独立） |
| 设计/验证实验方案 | 实验设计、方案步骤、可行性验证 | 公共流程 + 实验方案输出 |
| 作图 | 画图、图表、科研图、数据可视化 | 分支 B（独立） |
| 其他脏活 | 数据整理、格式转换、跑腿活 | 通用流程 |
分支 R：指定论文阅读
用户已指定论文与问题时，直接按 references/focused-reading.md 执行；不要重新询问检索领域、篇数或九个角度。用户已给出的输入、输出格式、执行授权不重复确认。只有会改变结论的缺失信息才澄清；无法补齐时交付有边界的结果。
材料/配方/性能抽取同时读取 references/data-extraction-schema.md。完整精读按需读取 references/paper-reading.md；窄问题优先交付用户所需的证据表、结论和待核验项。遵守当前任务的工具权限、输出目录及格式；禁止为补齐模板虚构图像、全文、测试标准或数据。
What ships with it
17 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.
- references/angle-report.md 2.8 KB
- references/citation-verify.md 1.8 KB
- references/data-extraction-schema.md 3.4 KB
- references/experiment-log.md 2.2 KB
- references/figure-guidelines.md 1.9 KB
- references/focused-reading.md 3.1 KB
- references/journal-list.md 3.7 KB
- references/paper-card.md 2.3 KB
- references/paper-reading.md 2.6 KB
- references/scoring-system.md 4.2 KB
- references/search-fallback.md 2.6 KB
- references/templates/formulation_properties.csv 1.4 KB
- scripts/extract_pdfs.py 7.1 KB runs code
- scripts/fetch_pdfs.py 7.7 KB runs code
- scripts/render_report.py 6.4 KB runs code
- scripts/score_papers.py 8.7 KB runs code
- scripts/verify_refs.py 9.7 KB runs code
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.
- yesterday First seen · 355 lines · 126 tokens per session scan A f5b3a4e97e69
shidi is a skill published in the GitHub repository IcyCreamDAS/shidi-skill (14 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 6,820 once invoked, about $0.0005 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 2026-10-28.
Other skills, from other repositories
latex-posters
Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.
data-stats-analysis
Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
data-viz-plots
Create publication-quality plots and visualizations using matplotlib and seaborn. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
gnomad-database
Query gnomAD (Genome Aggregation Database) for population allele frequencies, variant constraint scores (pLI, LOEUF), and loss-of-function intolerance. Essential for variant pathogenicity interpretation, rare disease genetics, and identifying loss-of-function intolerant genes.
arxiv-database
Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.
meta-analysis
Perform quantitative meta-analysis with effect size calculation, forest plots, funnel plots, and heterogeneity assessment. Use when: user asks to combine results from multiple studies, calculate pooled effect sizes, assess publication bias, or create forest/funnel plots. NOT for: systematic review protocol (use…