DeepSeek Harness Plugin

Signalight/law-thesis-review

Stars ★ 0 Category Skills Added 2026-09-19

DeepSeek Harness skill plugin that reviews law theses (international economic law and other legal topics): reads a student Word .docx, checks it against a bundled common-issue checklist, applies definite fixes as tracked changes, and adds Word comments for overall/section problems and missing-basis issues, then emits a short objective overall review plus a fix list.

Install

# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)

dsh plugin --profile web add github:Signalight/law-thesis-review

Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).

README

A DeepSeek Harness skill plugin that reviews student law theses (国际经济法/法学论文) and outputs a Word review draft with tracked changes + Word comments.

What it does

  • Reads a student Word (.docx) thesis (single file or a folder).
  • Checks against a bundled common-issue checklist (硕士/本科自查清单合并版 + 国际经济法/法学论文高发问题).
  • Applies definite fixes as Word tracked changes (w:ins / w:del).
  • Writes Word comments for issues the student must handle themselves (overall section problems, missing basis/clarification, etc.).
  • Emits a short, objective overall review + a fix list.

Install (local / from npm)

# local path
dsh plugin --profile web add link:D:/Coding/Creating/dsh-law-thesis-review
# or from npm (once published)
dsh plugin --profile web add @signalight/dsh-law-thesis-review

Restart the web profile. The skill is then auto-discovered; trigger it with phrases like “批改学生论文”, “审阅这篇论文”, “以修订+批注检查论文”.

Usage

The skill runs the bundled script:

# 1) extract text + paragraph indices
python skills/iet-law-thesis-review/scripts/review_docx.py extract 论文.docx --out ./work

# 2) review: apply tracked edits + comments from a spec
python skills/iet-law-thesis-review/scripts/review_docx.py review 论文.docx --spec spec.json --out 论文_审查稿.docx [--author "教师名"]

Spec shape shown in skills/iet-law-thesis-review/examples/spec-template.json.

Notes

  • Self-contained: apply_edits.py / models.py / add_comment.py are vendored; the skill does not require an external word-docx plugin.
  • Checklist is bundled (skills/iet-law-thesis-review/references/checklist.md); no dependency on any local Obsidian vault path.
  • The output preserves the original title and any student info; revision/comment author defaults to the local Office/WPS username or can be set via --author.
  • Word: open the _审查稿.docx to see the redline + comment bubbles.

License

MIT

Thesis level

The skill detects the paper level and routes to the matching checklist:

  • Undergraduate thesis -> references/checklist-undergraduate.md (with format/editing checks)
  • Master's thesis -> references/checklist-master.md (with format/editing checks)
  • Academic training / term paper -> references/checklist-academic-training.md (no format requirements)
  • Level unspecified -> references/checklist.md (general requirements only; no format nitpicks)

Content from the project README on GitHub ↗

Links

More in this category

View the whole category →

Community comments

Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.