New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Chinese Thesis Workbench

by ZyhSechub in ZyhSechub/chinese-thesis-workbench-skill

Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output.

MITAuto-check passedDocuments & Office

Install Chinese Thesis Workbench

skills CLI
$ npx skills add ZyhSechub/chinese-thesis-workbench-skill --skill chinese-thesis-workbench -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZyhSechub/chinese-thesis-workbench-skill chinese-thesis-workbench --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chinese-thesis-workbench
GitHub stars
578
Token cost
~2.9k tokens
SKILL.md length
1,211 words
Files
89 (incl. scripts, references, assets)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output.

  • Works in 12 steps: intake_materials: collect materials and… → init_workspace: initialize… → resolve_standards: fill… → …
  • Writing a Chinese undergraduate thesis from project source code and screenshots
  • SKILL.md covers Operating Model, Required Workflow, Phase + Status State Model and Decision Tree, plus 4 more sections
  • Reformatting a thesis draft to a school template

What it does

The workbench handles Chinese undergraduate theses and graduation-design papers. It treats school templates, task books, proposals, sample papers, source code, databases, APIs, tests, literature PDFs, screenshots, Word comments and existing drafts as materials to resolve into structured state before any formal prose is written. Standards and evidence act as the control layer, and the drafting pipeline is the output layer.

State is split in two. The paper-context folder holds workflow state, standards, evidence, literature, AIGC reports and Word comment revisions, while paper-output holds the thesis Markdown, DOCX, appendix DOCX, figures, screenshots and reference verification files. Dashboard, content-decision, blocker and user-decision files show progress and the choices needed from you. The workflow runs in order from material intake and workspace setup through standards resolution, sample and template analysis and evidence building, and the folder includes draw.io templates for algorithm, architecture, ER, sequence and business flow diagrams.

When your agent uses it

  • Writing a Chinese undergraduate thesis from project source code and screenshots
  • Reformatting a thesis draft to a school template
  • Reducing AI-sounding style and checking references in a draft
  • Delivering a thesis as DOCX with an appendix DOCX

Example prompts

  • “Draft my graduation thesis from this project's source code, database and screenshots, following the school template.”
  • “Check the references and figures in my thesis draft and list what is missing.”
  • “Revise the thesis according to the advisor's Word comments.”

Requirements

  • The school template, task book and other source materials supplied by you

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. intake_materials: collect materials and record priority, gaps, missing impact, continuation limits, and user next steps in…
  2. init_workspace: initialize thesis-ai-standard/, paper-context/, and workflow logs.
  3. resolve_standards: fill thesis-ai-standard/templates/standard-profile.yaml.
  4. analyze_sample_and_template: normalize school template and sample-paper parser outputs into lightweight analysis reports, outline…
  5. build_evidence: extract project facts into paper-context/evidence/.
  6. stop_and_report: stop or limit only the affected scope whenever evidence, standards, figures, citations, or DOCX delivery cannot be…
  7. build_thesis_spec: fill thesis-ai-standard/templates/thesis-ai-spec.yaml.
  8. build_figure_registry: fill thesis-ai-standard/templates/figure-registry.yaml.
  9. confirm_outline: confirm chapter structure, word counts, sample/template observations, and any available content emphasis/exclusion…
  10. draft_chapters: write only from confirmed structured facts and evidence.
  11. produce_assets: generate or collect figures, diagrams, screenshots, tables, and appendix sources.
  12. produce_docx: generate or edit the main DOCX and appendix DOCX into paper-output/ using the recorded delivery path.

What it can do on your machine

Read from SKILL.md and the folder at commit 1dac3f8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chinese Thesis Workbench loads about 2.9k tokens when it runs, and up to ~20k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 1,211 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~20k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ZyhSechub/chinese-thesis-workbench-skill at commit 1dac3f8, republished under its MIT licence (© ZyhSechub). 1,211 words, ~2,949 tokens.

Download SKILL.mdSave it as .claude/skills/chinese-thesis-workbench/SKILL.md (or your agent's skills folder). This skill also uses 88 other files; get the full folder from GitHub.
name
chinese-thesis-workbench
description
Standardize, draft, revise, check, and package Chinese undergraduate thesis or graduation-design papers from school templates, task books, proposals, sample papers, source code, screenshots, databases, APIs, tests, literature PDFs, Word comments, and existing drafts. Use when the user asks to write, generate, refactor, polish, reduce AIGC style, verify, format, or deliver a Chinese thesis with evidence traceability, figure registries, workflow logs, chapter word control, screenshots, references, DOCX output, and appendix DOCX.

Chinese Thesis Workbench

Operating Model

Use standards and evidence as the control layer, then use the Chinese thesis drafting pipeline as the output layer. Treat school templates, advisor requirements, task books, sample papers, source code, databases, APIs, tests, literature PDFs, screenshots, Word comments, and existing drafts as materials that must be resolved into structured state before formal prose is written.

The workbench has two sides:

  • Governance side: paper-context/ stores workflow state, standards, evidence, literature, AIGC reports, and Word comment revisions.
  • Delivery side: paper-output/ stores thesis Markdown, DOCX, appendix DOCX, figures, screenshots, image maps, and reference verification artifacts.
  • User-facing visibility and decision side: paper-context/workflow/user-dashboard.md summarizes current progress, missing materials, user decisions needed, and the next recommended action. paper-context/workflow/content-decisions.md records optional content emphasis and exclusion decisions when candidate content is available. paper-context/workflow/blocker-report.md records the latest blocker, options, recommendation, and limited-continuation status. paper-context/workflow/user-decisions.md records user-approved choices that affect scope, evidence, standards, outline, delivery, or limitations. These files improve transparency; they do not override standards, evidence, or delivery quality gates.

Required Workflow

Run the workflow in this order unless the user is only asking for a narrow inspection or revision:

  1. intake_materials: collect materials and record priority, gaps, missing impact, continuation limits, and user next steps in paper-context/workflow/material-inventory.md.
  2. init_workspace: initialize thesis-ai-standard/, paper-context/, and workflow logs.
  3. resolve_standards: fill thesis-ai-standard/templates/standard-profile.yaml.
  4. analyze_sample_and_template: normalize school template and sample-paper parser outputs into lightweight analysis reports, outline suggestions, and word budgets before drafting; parser output does not drive DOCX formatting unless the user explicitly selects sample-style generation via --sample-analysis or template-copy filling via --from-template.
  5. build_evidence: extract project facts into paper-context/evidence/.
  6. stop_and_report: stop or limit only the affected scope whenever evidence, standards, figures, citations, or DOCX delivery cannot be verified; record options in blocker-report.md.
  7. build_thesis_spec: fill thesis-ai-standard/templates/thesis-ai-spec.yaml.
  8. build_figure_registry: fill thesis-ai-standard/templates/figure-registry.yaml.
  9. confirm_outline: confirm chapter structure, word counts, sample/template observations, and any available content emphasis/exclusion decisions before writing.
  10. draft_chapters: write only from confirmed structured facts and evidence.
  11. produce_assets: generate or collect figures, diagrams, screenshots, tables, and appendix sources.
  12. produce_docx: generate or edit the main DOCX and appendix DOCX into paper-output/ using the recorded delivery path.
  13. quality_gates: run standards, evidence, reference, figure, DOCX, and AIGC checks.
  14. delivery_report: report outputs, limitations, remaining human decisions, and verification evidence.

stop_and_report is a global blocking mechanism, not just step 6. Read references/workflow/stop-and-report.md whenever continuing may require guessing.

Phase + Status State Model

Use this two-layer state model in paper-context/workflow/workflow-status.md, and mirror the user-facing summary in paper-context/workflow/user-dashboard.md:

FieldAllowed values
phaseintake_only, workspace_ready, standards_resolved, sample_analysis_done, evidence_built, spec_confirmed, outline_confirmed, writing_allowed, delivery_done
statuspending, in_progress, blocked, needs_review, done, deprecated

When status becomes blocked, write blocked_reason, missing_materials, next_action, and can_continue_with_limitations in the status file. Do not hide blockers in chat only.

After any meaningful phase, blocker, material, outline, or delivery-scope change, update user-dashboard.md so the user can see:

  • current phase and status
  • completed work
  • decisions waiting for user confirmation
  • missing materials and their impact
  • next recommended action
  • limited-continuation options, if any

Decision Tree

  1. If there is no workspace, run scripts/workspace/init_thesis_workspace.py.
  2. If school/advisor/template rules are missing or conflicting, resolve standards first.
  3. If sample/template analysis is missing, analyze it before thesis-ai-spec.yaml.
  4. If source evidence or literature is missing, build evidence and reference pools before writing.
  5. If thesis-ai-spec.yaml is not confirmed, do not write formal thesis body.
  6. If figure-registry.yaml is not ready, do not claim figures/tables/screenshots are complete.
  7. If asked to revise Word comments, extract comments and route back to writing_allowed.
  8. If asked for final delivery, run quality gates and produce both main and appendix DOCX.
Show full SKILL.md (620 more words)Show less

Hard Rules

  • School and advisor requirements override default rules.
  • Do not write formal thesis body before materials are collected or the user explicitly confirms there are no more materials.
  • During intake, classify materials as required, strongly_recommended, or optional, and explain the effect of each missing required or strongly recommended material.
  • Use content-decisions.md when the user provides feature/module/experiment/appendix candidates, but do not block the main workflow only because no candidate content has been provided yet.
  • Record user-approved scope, material-unavailable, limited-continuation, standard-conflict, content-exclusion, outline, word-count, DOCX, appendix, and filename decisions in user-decisions.md.
  • User-facing workflow files are decision aids only. They must not weaken school/advisor requirements, evidence requirements, citation verification, figure provenance, or DOCX delivery checks.
  • Do not write formal thesis body before standards, sample/template analysis, and evidence building are complete.
  • When evidence is insufficient, trigger stop_and_report; do not guess missing facts.
  • When blocked, classify the issue as hard_blocker, limited_continue, or user_choice_needed, then provide user options and a recommended path.
  • thesis-ai-spec.yaml is the single entry point for thesis facts.
  • figure-registry.yaml is the single entry point for figures, tables, screenshots, and diagram sources.
  • Thesis prose may consume structured facts and evidence only; do not expand directly from README files or old notes.
  • Do not write content that content-decisions.md marks as rejected, excluded, or waiting for evidence.
  • Do not invent features, fields, APIs, test results, experiment data, or references.
  • AIGC style governance runs after the evidence chain is complete and may only improve academic expression, evidence density, and vague wording.
  • Thesis body must not expose AI workflow language.
  • Chapter 4 implementation must bind to real modules, screenshots, core code, SQL, or equivalent evidence.
  • System-design theses without an E-R diagram or equivalent data-design evidence cannot be marked complete.
  • Generate both the main thesis DOCX and appendix DOCX. For strict school formatting, prefer template-copy filling via scripts/docx/apply_textual_edits.py --from-template; otherwise use default or sample-style generation. Do not promise full template reproduction. Preserve diagram source, E-R source, flowchart source, and related assets in the appendix.
  • Formula delivery must be explicit: latex_text preserves source formula text, while formula_image requires matching image assets.
  • Output filenames must use the thesis title, not generic names such as final, draft, paper-final, or doc1.
  • Literature workflow must be: build pool -> verify -> filter -> format -> generate verification checklist.

Resource Map

NeedResource
Intake and fast workflowreferences/workflow/intake.md, references/workflow/rapid-thesis-workflow.md
Workflow state, blockers, and sparse-material handoffreferences/workflow/workflow-state-management.md, references/workflow/stop-and-report.md, references/workflow/material-gap-handoff.md
Standards and template resolutionreferences/standards/standards-and-template-resolution.md, references/standards/style-extraction.md, references/standards/default-style.md
Evidence extractionreferences/evidence/source-to-thesis-workflow.md, references/evidence/fact-extraction.md
Literature/PDF workflowreferences/evidence/literature-and-pdf-workflow.md, scripts/literature/
Writing and chapter controlreferences/writing/writing-pipeline.md, references/writing/chapter-patterns.md, references/writing/sample-analysis.md
AIGC style governancereferences/writing/aigc-style-governance.md, scripts/review/analyze_aigc_style.py
DOCX delivery and Word commentsreferences/delivery/docx-delivery.md, references/delivery/word-comment-revision-workflow.md, scripts/docx/
Figures and screenshotsscripts/figures/, scripts/screenshots/, thesis-ai-standard/templates/figure-registry.yaml
Merge provenancereferences/merge-map.md

Quality Gates

Before claiming delivery quality, check:

  • standard-profile.yaml, thesis-ai-spec.yaml, and figure-registry.yaml exist and are internally consistent.
  • Every major factual claim has a source in paper-context/evidence/ or verified literature.
  • Every figure/table has source_kind, source_path, image_path, evidence_source, first_mention, and status.
  • References are real, selected from a verified pool, and have a generated verification checklist.
  • AIGC style changes do not add facts.
  • Main DOCX and appendix DOCX exist in paper-output/.
  • Screenshot, diagram, and image-map paths resolve on Windows.
  • Workflow logs reflect the current phase, status, blockers, and delivery limitations.
  • user-dashboard.md reflects the user-visible progress, pending decisions, missing materials, and next action.
  • blocker-report.md reflects the latest blocker, affected scope, user options, recommended path, and whether limited continuation is allowed.
  • user-decisions.md records user-approved choices that affect scope, missing-material handling, limitations, standards, outline, or delivery.
  • If content-decisions.md has active candidates, their approved/deferred/excluded status is consistent with the outline, thesis spec, and figure registry.

Delivery Contract

Deliver thesis artifacts under paper-output/:

  • <论文标题>.md
  • <论文标题>.docx
  • <论文标题>-附件.docx
  • <论文标题>-image-map.json
  • <论文标题>-文献核验清单.json
  • figures/
  • screenshots/

Report what was verified, what could not be verified, and what still needs human confirmation. If verification cannot run, state the command and the reason.

© ZyhSechub, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 88 other files (scripts, references, assets) in the repository root of ZyhSechub/chinese-thesis-workbench-skill.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • agents/openai.yaml
  • assets/thesis-ai-standard/01-本科论文标准化最佳实践.md
  • assets/thesis-ai-standard/02-公开标准与高校规范来源.md
  • assets/thesis-ai-standard/README.md
  • assets/thesis-ai-standard/drawio/algorithm-workflow-template.drawio
  • assets/thesis-ai-standard/drawio/backend-layered-architecture-template.drawio
  • assets/thesis-ai-standard/drawio/business-flow-template.drawio
  • assets/thesis-ai-standard/drawio/er-diagram-template.drawio
  • assets/thesis-ai-standard/drawio/sequence-diagram-template.drawio
  • assets/thesis-ai-standard/drawio/system-architecture-template.drawio
  • assets/thesis-ai-standard/templates/ai-prompts.md
  • assets/thesis-ai-standard/templates/ai-review-rubric.json
  • … and 73 more

Open the folder on GitHubat commit 1dac3f8

Compare with similar skills

Chinese Thesis Workbench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chinese Thesis Workbench compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chinese Thesis Workbench this skillZyhSechub/chinese-thesis-workbench-skill578—~2.9kAutomated safety check: PassMIT
Academic Paper ComposerAAASS554/codex-academic-paper-skills5391 repos~3.2kAutomated safety check: PassMIT
Thesis DOCXcatlog22/maestro-flow5641 repos~2.5kAutomated safety check: PassMIT
Master Thesis Studiodarksider-9/master-thesis-studio-skill129—~3.1kAutomated safety check: PassMIT
Biomedical PaperLeoYeAI/openclaw-master-skills2.2k—~3.3kAutomated safety check: PassMIT
Aigc Detectorfree-revalution/AIGC-Detector-Pro142—~2.8kAutomated safety check: PassMIT

Similar skills

  • Academic Paper Composer

    AAASS554/codex-academic-paper-skills

    A skill your agent uses when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript.

    539 GitHub starsUsed in 1 repo~3.2k tokens
    Documents & OfficeAuto-check passed

  • Thesis DOCX

    catlog22/maestro-flow

    Create, revise, and format thesis or dissertation Word documents with strict academic formatting control.

    564 GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

  • Master Thesis Studio

    darksider-9/master-thesis-studio-skill

    A skill your agent uses for Southeast University-style master's thesis projects from a Word template or existing draft, including optional reverse parsing of an existing DOCX, user intake, outline…

    129 GitHub stars~3.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed

  • Biomedical Paper

    LeoYeAI/openclaw-master-skills

    AI-powered biomedical manuscript generation with docx output.

    2.2k GitHub stars~3.3k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

  • Aigc Detector

    free-revalution/AIGC-Detector-Pro

    Academic paper AI content detection, rewriting, and thesis writing assistant.

    142 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed

  • Master Thesis Studio

    Jinze-Lee/codex-skills-workbench

    Guides the writing of a Chinese master's thesis and generates the Word file from a template, only when you invoke it by name.

    109 GitHub stars~3.5k tokensUpdated 5 mo ago
    EducationAuto-check passed

Works with

Categories

Questions about Chinese Thesis Workbench

What does Chinese Thesis Workbench do?

Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output. The workbench handles Chinese undergraduate theses and graduation-design papers. It treats school templates, task books, proposals, sample papers, source code, databases, APIs, tests, literature PDFs, screenshots, Word comments and existing drafts as materials to resolve into structured state before any formal prose is written.

When should I use Chinese Thesis Workbench?

Chinese Thesis Workbench fits situations like: writing a Chinese undergraduate thesis from project source code and screenshots; reformatting a thesis draft to a school template; reducing AI-sounding style and checking references in a draft; delivering a thesis as DOCX with an appendix DOCX.

How do I install Chinese Thesis Workbench in Claude Code?

Run `npx skills add ZyhSechub/chinese-thesis-workbench-skill --skill chinese-thesis-workbench -a claude-code`. Or copy the skill folder (the ZyhSechub/chinese-thesis-workbench-skill repository) into .claude/skills/chinese-thesis-workbench in your project. Claude Code loads it when a task matches its description.

How do I install Chinese Thesis Workbench in Codex?

Run `npx skills add ZyhSechub/chinese-thesis-workbench-skill --skill chinese-thesis-workbench -a codex`. Or copy the skill folder (the ZyhSechub/chinese-thesis-workbench-skill repository) into .agents/skills/chinese-thesis-workbench in your project. Codex loads it when a task matches its description.

Can I use Chinese Thesis Workbench in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZyhSechub/chinese-thesis-workbench-skill --skill chinese-thesis-workbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chinese-thesis-workbench, .gemini/skills/chinese-thesis-workbench, .github/skills/chinese-thesis-workbench and .opencode/skills/chinese-thesis-workbench in your project.

What does Chinese Thesis Workbench need to run?

SKILL.md names no scripts, command-line tools or credentials: Chinese Thesis Workbench is instructions for the agent only. Our summary lists: The school template, task book and other source materials supplied by you.

Does Chinese Thesis Workbench access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Chinese Thesis Workbench safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Chinese Thesis Workbench use?

Chinese Thesis Workbench is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chinese Thesis Workbench use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.

What are the alternatives to Chinese Thesis Workbench?

Skills that share tags, products or a category with Chinese Thesis Workbench: Academic Paper Composer (AAASS554/codex-academic-paper-skills, 539 stars), Thesis DOCX (catlog22/maestro-flow, 564 stars), Master Thesis Studio (darksider-9/master-thesis-studio-skill, 129 stars) and Biomedical Paper (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chinese Thesis Workbench?

ZyhSechub (a GitHub user) maintains it in ZyhSechub/chinese-thesis-workbench-skill, which has 578 GitHub stars. The repository was last updated on May 7, 2026.

Source: ZyhSechub/chinese-thesis-workbench-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.