Academic Thesis Review
v1.1.0Multi-round review skill for Chinese management-oriented master's theses, especially MBA, MEM, and MPA, with applicability to similar professional and applie...
⭐ 1· 190·1 current·1 all-time
by@wmpluto
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (multi-round thesis review) align with the requirements and instructions: the skill asks for a .docx input, uses local text extraction, and writes review artifacts. No unrelated credentials, binaries, or services are requested.
Instruction Scope
SKILL.md instructs the agent to extract text from a provided .docx, split by chapters, run three review passes, and write markdown/artifact files. These operations are proportional to a thesis-review task. It does read local files (thesis and optional review_results.md) and writes outputs to review_artifacts/ and review_results.md — expected for this purpose.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. The README suggests copy-based installs into user skill dirs (user-initiated). No downloads or executable installs are specified.
Credentials
The skill declares no environment variables or credentials. It does require a local Python runtime (for docx text extraction) and filesystem read/write access to the working directory — both reasonable for the stated purpose.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modify other skills. It will create and write local files (review_artifacts/, review_results.md) in the working directory when run — normal for a file-processing review workflow.
Assessment
This skill appears coherent and limited to local thesis review: it reads the .docx you provide, may detect an existing review_results.md and run iterative checks, and writes outputs to review_artifacts/ and review_results.md. It does not request network access or credentials. Before installing/using: (1) ensure you are comfortable letting the agent access the .docx contents (don’t include unrelated secrets in the document); (2) run it in an environment with a Python interpreter available if you want automated extraction; (3) if you copy the skill into a global agent skills directory, remember the skill (when invoked) will be able to read/write files in the agent’s working directories; and (4) review SKILL.md yourself — it contains the exact extraction code and file paths the agent will use. If any of these behaviors are unacceptable, do not install or run the skill.Like a lobster shell, security has layers — review code before you run it.
latestvk9719ah6mewc4j7pa2qpg1m9yh83v7nk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.