Install
$ agentstack add skill-docxology-template-academic-paper-reviewer ✓ 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 paper reviewer
Read-only review workflow for template manuscripts. Review reports are separate artifacts; this skill does not edit the manuscript directly.
Natural invoke
- "Review this manuscript like peer reviewers"
- "Focus only on methodology and statistics"
- "Check whether my revisions address the comments"
- "Calibrate the review rubric against a known decision set"
Inputs to confirm
- Manuscript - project manuscript directory or provided paper file.
- Mode - full, quick, methodology-focus, re-review, or calibration.
- Review lens - target venue, discipline, methods, and known reviewer comments.
- Evidence access - rendered PDF, source markdown, output artifacts, validation reports, and claim ledgers.
Workflow
- Read-only boundary - produce reports, matrices, and recommendations only; route edits to [academic-paper](../academic-paper/SKILL.md).
- Panel lenses - separate contribution, methods, evidence/citations, presentation, reproducibility, and adversarial-overclaim checks.
- Evidence audit - cite source file paths, generated artifacts, evidence registry entries, and validation reports when flagging issues.
- Revision traceability - in re-review mode, map each reviewer concern to author action, verification status, residual risk, and next owner.
- No sycophantic concession - do not soften a finding unless new evidence from the manuscript or artifacts resolves it.
Deliverables
- Review package: summary verdict, major issues, minor issues, evidence table, and recommended next actions.
- Methodology-focus mode: methods validity, data/analysis reproducibility, statistical or formalism concerns.
- Re-review mode: traceability matrix with comment, response, evidence checked, verified, and residual issue.
- Calibration mode: rubric, expected decision labels, observed disagreement, and confidence caveats.
Verification commands
uv run python -m infrastructure.validation.cli prerender projects//manuscript --repo-root .
uv run python -m infrastructure.validation.cli evidence projects/ --fail-on-issues
uv run python -m infrastructure.prose.cli report projects//manuscript
References
- [MODEREGISTRY.md](../MODEREGISTRY.md)
- [academic-paper](../academic-paper/SKILL.md)
- [manuscript-claim-verification](../manuscript-claim-verification/SKILL.md)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: docxology
- Source: docxology/template
- License: Apache-2.0
- Homepage: https://doi.org/10.5281/zenodo.19139090
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.