academic-reviser
Skill111 starsChanged 5 months agoMITView on GitHub
Self-review, audit, or verify CS/AI/ML paper drafts as a critical peer reviewer. Three-round review (evidence→argument→style) with Verification Status and debt tracking. Use when: reviewing a paper draft before submission, checking evidence compliance of claims, simulating peer reviewer feedback, verifying citation closure and evidence debts, performing cross-section consistency checks. Triggers on: self review, 自查, verification, 审稿, evidence compliance, peer review, 论文审查, draft audit, 验证论文, 检查引用, cross-section review, 审修, draft verification.
In this repository7 other files it gives its agents.
- academic-citationSkill
- academic-experimentsSkill
- academic-figureSkill
- academic-latex-layoutSkill
- academic-paper-writerSkill
- academic-polishingSkill
- academic-venue-researchSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read manifest.yaml. It declares always_load files, axes, and references.on_demand.
- Very specific: line 13
Read every file listed under always_load.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Academic Reviser
将此 skill 视为"挑剔审稿人代理"——像 peer reviewer 一样审查草稿,按证据→论证→风格三轮顺序执行。
Router Protocol
- Read
manifest.yaml. It declaresalways_loadfiles,axes, andreferences.on_demand. - Read every file listed under
always_load. These are the skill's binding rules — not reference material. - Apply the loaded material as constraints:
stance.mddefines non-negotiable rules, bounded assessment, termination conditions, and scope.red-lines.mddefines absolute prohibitions. Do not negotiate these.output-contract.mddefines deliverables, debt types, and Verification Status format.anti-patterns.mddefines known failure modes, correct alternatives, and self-deception signals.
- Detect the mode using the manifest's
modeaxis. When input materials are incomplete, declare a Bounded Assessment before proceeding. - Echo the selected mode to the user before executing.
- Reach for
references/only when the manifest'sreferences.on_demandcondition is satisfied.
Debt types tracked: prose_debt, section_contract_debt, citation_debt, evidence_debt, figure_debt, protocol_debt, result_debt, rationale_debt. Schema: skills/shared/schemas/verification-report.md.
Modes
| Mode | Use when |
full-section-review | Complete 3-round review + Verification for a single section |
cross-section-review | Cross-section consistency check |
verification-only | Verdict only, no re-review |
targeted-review | Specific issue (e.g. citation closure only) |
targeted-evidence-mode | Evidence compliance only (orchestrator Step 9.5) |
mock-reviewer-package | Optional pre-submission 3-reviewer package |
Agent Dispatch
agents/reviser_agent.md dispatched by orchestrator at Step 9.5 or Step 9.8. Subagent returns structured review content; must not modify project files or invent reviewer identities, experiments, citations, or unprovided evidence.
Independent Use
| Input | Mode | Priority | Behavior |
| Section draft | full-section-review | 2 (path trigger) | Full 3-round review |
| Multiple sections | cross-section-review | 2 (path trigger) | Consistency only |
| "只用 verdict" | verification-only | 1 (explicit) | Verdict only |
| Specific issue | targeted-review | 1 (explicit) | Targeted check |
| Evidence focus | targeted-evidence-mode | 1 (explicit) | Evidence compliance |
| "审稿包" / pre-submission | mock-reviewer-package | 1 (explicit) | Optional reviewer package |
| Scenario | Recommended |
| Just reviewing a draft | This skill (standalone) |
| During paper drafting | academic-paper-writer orchestrator |
| After polishing pass | academic-polishing → this skill |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

