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 handsomeZR-netizen/zhuoyu-workshop-skill --skill zhuoyu-workshopgit clone --depth 1 https://github.com/handsomeZR-netizen/zhuoyu-workshop-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/handsomezr-netizen/zhuoyu-workshop-skill/zhuoyu-workshop)<a href="https://agentmods.dev/skills/handsomezr-netizen/zhuoyu-workshop-skill/zhuoyu-workshop"><img src="https://agentmods.dev/badge/skills/handsomezr-netizen/zhuoyu-workshop-skill/zhuoyu-workshop/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/handsomezr-netizen/zhuoyu-workshop-skill/zhuoyu-workshop"><img src="https://agentmods.dev/badge/skills/handsomezr-netizen/zhuoyu-workshop-skill/zhuoyu-workshop.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 | $0.00081 | $0.01245 |
| Opus 5 | $0.00041 | $0.00622 |
| Sonnet 5 | $0.00016 | $0.00249 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
zhuoyu-workshop 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 13d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
琢玉工坊
把学生项目从“能跑、能讲一点”打磨成“材料完整、表达可信、答辩可交付”的工作流。
核心原则：玉不琢，不成器；项目不理，不成章。
Operating Rules
- Ground the work in supplied artifacts first: repo files, report drafts, screenshots, logs, datasets, rubrics, competition notices, or teacher requirements.
- Do not invent awards, users, metrics, experiments, patents, software copyright status, deployment results, model accuracy, or paper conclusions.
- Prefer honest enhancement: clarify value, repair structure, expose evidence, improve wording, and add missing verification.
- Use student-appropriate language: credible, specific, not over-commercialized, not inflated with terms like "world-leading" unless evidence exists.
- For code tasks, use minimum viable changes, preserve user work, and define validation before claiming completion.
- If critical inputs are missing, ask only for the missing material that changes the deliverable; otherwise proceed with clearly stated assumptions.
Route The Task
Classify the user request, then load only the matching reference file:
- 项目诊断与定位: read
references/project-diagnosis.mdwhen the user needs to understand project value, current gaps, technical route, innovation points, or how to turn rough materials into a coherent story. - 成果包装与交付材料: read
references/delivery-packaging.mdwhen creating closing reports, achievement matrices, GitHub README, software copyright material drafts, competition submissions, or project portfolios. - 答辩与展示: read
references/presentation-defense.mdwhen generating PPT outlines, speaker notes, demo scripts, judge Q&A, or defense rehearsals. - 论文与报告: read
references/paper-report.mdwhen polishing papers, course reports, abstracts, references, LaTeX/Word structure, formatting checks, or academic wording. - AI 编程辅助: read
references/ai-coding-workflow.mdwhen using Codex for bug diagnosis, feature implementation, code review, refactoring, tests, or project cleanup.
When a request spans multiple routes, start with project diagnosis, then add the most relevant delivery route. Do not load every reference by default.
What ships with it
6 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.
- 13d ago First seen · 109 lines · 81 tokens per session scan A 26be3c263e38
zhuoyu-workshop is a skill published in the GitHub repository handsomeZR-netizen/zhuoyu-workshop-skill (52 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,245 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
x-insight-cards
Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and Xiaohongshu review, with optional private delivery to a pinned WeChat iLink bot review chat or confirmed File Transfer Assistant self-chat. Use when Codex needs to discover, verify…
chinese-reference-formatter-skill
A reference-formatting skill creates Chinese academic bibliography entries and BibTeX, a machine-readable format for citation tools, from literature titles.
mem-reading-report
A reading-report and literature-review assistant for master's students, especially ZJU MEM students. It works from several papers plus report and student details to produce or review reports in the required format.
mem-midterm-report
A Chinese-language workflow for preparing a ZJU MEM midterm report. ZJU is Zhejiang University, and MEM is a Master of Engineering Management degree; the workflow covers the report, registration form, presentation outline, and submission guidance.
thesis-deai-review
A review guide for Chinese degree theses, especially evidence-based engineering-management theses. It checks for formulaic wording, weak evidence, and writing that may appear machine-generated.
thesis-defense
A preparation guide for ZJU MEM thesis defenses, covering midterm reviews, preliminary defenses, blind review, and the final defense. It organizes review checks, presentation planning, likely questions, video-based question analysis, and compact preparation notes.