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 shidigit 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/shidi)<a href="https://agentmods.dev/skills/icycreamdas/shidi-skill/shidi"><img src="https://agentmods.dev/badge/skills/icycreamdas/shidi-skill/shidi/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/shidi"><img src="https://agentmods.dev/badge/skills/icycreamdas/shidi-skill/shidi.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 | $0.05702 |
| Opus 5 | $0.00063 | $0.02851 |
| Sonnet 5 | $0.00025 | $0.01140 |
| Haiku 4.5 | $0.00013 | $0.00570 |
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 10d 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 — 330 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。不替师兄做决策——所有关键决策点（角度选择、参数确认、方向取舍）一律返回给师兄确认。宁可多问一次，不可自作主张。
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 |
| 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 |
公共流程：文献调研与阅读（步骤 1~5）
适用范围：文献调研与实验方案设计共用。 设计/修改实验方案必须先过文献调研——方案的每一步都要有文献支撑。
步骤 1：一次性问完三个参数（一轮交互，禁止分多次问）
- 领域：基于用户输入，生成该问题可能涉及的子领域/研究方向候选列表（5-10 个），请用户增删改
- 数量：总共 N 篇（用户指定总数，非每角度 N 篇）
- 特殊要求：必含作者/文献/期刊、其他要求
- IF / 中科院分区 = 标注项 + 可筛选项，默认不硬性过滤；用户可要求"只留一区"等
- 支持用户自主上传 PDF：用户可在此阶段直接上传已有文献/参考论文，师弟纳入检索、阅读与引用范围
步骤 2：发散 3×3=9 个角度
- 固定角度模板：A 机理（为什么能行）/ B 方法工艺（怎么做出来的）/ C 应用性能（用在哪、效果如何）
- 每个角度再发散 3 个子角度 → 共 9 个
- 向用户展示全部 9 个角度，用户选择：整组 ABC（3 组选 1 组或多组），或 9 个角度中任选任意数量
- 角度模板可按领域调整，但必须在这次交互中一次性定死，之后执行不得自行变更
What ships with it
12 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/experiment-log.md 1.8 KB
- references/figure-guidelines.md 1.9 KB
- references/journal-list.md 3.7 KB
- references/paper-card.md 1.9 KB
- references/paper-reading.md 2.4 KB
- references/scoring-system.md 1.8 KB
- references/search-fallback.md 2.6 KB
- scripts/extract_pdfs.py 4.8 KB runs code
- scripts/fetch_pdfs.py 5.7 KB runs code
- scripts/render_report.py 4.5 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.
- 10d ago First seen · 330 lines · 126 tokens per session scan A 19345e3ee707
shidi is a skill published in the GitHub repository IcyCreamDAS/shidi-skill (7 stars, last pushed 18d ago), licensed MIT. It adds 126 tokens to every session and 5,702 once invoked, about $0.0006 per session on Opus 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
analyze-stats
Statistical analysis for medical research papers. Generates reproducible Python/R code with publication-ready tables and figures. Supports diagnostic accuracy, inter-rater agreement, meta-analysis, survival analysis, survey data, group comparisons, regression, propensity score, and repeated measures.
present-paper
Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and…
self-review
Pre-submission self-review for the user's own manuscripts, applying a reviewer perspective. Systematic check across 10 categories with research-type branching. Outputs Anticipated Major/Minor Comments with severity framing and optional R0 numbering for /revise pipeline integration.
check-reporting
Check manuscript compliance with medical research reporting guidelines. Supports 49 guidelines including STROBE, STROBE-MR, RECORD, REMARK (prognostic tumor-marker studies), TARGET (target trial emulation), GATHER (burden-of-disease / health-estimate modeling), CONSORT, CONSORT-AI, STARD, STARD-AI, TRIPOD, TRIPOD+AI…
make-figures
Generate publication-ready figures and visual abstracts for medical research papers. Supports ROC curves, forest plots, CONSORT/STARD/PRISMA flow diagrams, calibration plots, Kaplan-Meier curves, Bland-Altman plots, confusion matrices, pipeline diagrams, and journal-specific visual/graphical abstracts (python-pptx…
meta-analysis
Systematic review and meta-analysis pipeline for medical research. Covers protocol registration (PROSPERO), search strategy, screening, data extraction, risk of bias assessment (QUADAS-2/ROBINS-I), statistical synthesis (bivariate/HSROC for DTA, random-effects for intervention), and PRISMA-compliant reporting.…