Install
$ agentstack add skill-mr-fang-vlsi-edagent-academic-writing-quality-assessor ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Academic Writing Quality Assessor
When to use
Use this skill when the user asks to:
- check thesis/paper/proposal formatting and manuscript consistency,
- run grammar review with minimal false positives,
- unify terminology, equation/citation style, or figure/table conventions,
- clean LaTeX hygiene issues such as case-mismatched graphics paths, stale chapters, or front-matter drift.
Do not use this skill for slide drafting/refinement; use academic-presentation-crafter or academic-slide-refiner instead.
Scope Boundary
This skill owns manuscript quality assurance and writing-side consistency. It does not own domain experiment execution, paper search, or physical-design conclusions.
Knowledge And Tool Interaction
- Treat the active manuscript source tree as the primary evidence source.
- Use
scripts/common/latex_writing_audit.pybefore large cleanup or when active-file boundaries are unclear. - When the manuscript task also requires shared KB/tool retrieval, delegate lookup to
eda-context-accessor. - Prefer minimal-intrusion edits: fix correctness and consistency first, then style.
- Archive or remove stale chapters/assets only after confirming they are outside the active include/input closure.
Workflow
- Build or inspect the current LaTeX project state.
- Determine the active chapter/input/bibliography/graphics closure.
- Review in this order:
- build blockers and references,
- front matter correctness,
- chapter naming/structure consistency,
- terminology consistency,
- must-fix grammar errors,
- low-risk style cleanup.
- Only after active assets are known, clean stale chapters or duplicate figures.
Operational References
- Load
references/writing-qa-playbook.mdfor the full manuscript QA checklist and review order. - Load
references/thesis-writing-onboarding.mdwhen the task is dissertation/thesis assembly from proposal + papers. - Load
references/scripts/scripts__common__latex_writing_audit.pywhen you need exact behavior of the audit script or want to mirror/patch it.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Mr-Fang-VLSI
- Source: Mr-Fang-VLSI/EDAgent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.