joshua-zyy/academic-reviser
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.
npx skills add https://github.com/joshua-zyy/academic-paper-writer --skill 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。
manifest.yaml. It declares always_load files, axes, and references.on_demand.always_load. These are the skill's binding rules — not reference material.stance.md defines non-negotiable rules, bounded assessment, termination conditions, and scope.red-lines.md defines absolute prohibitions. Do not negotiate these.output-contract.md defines deliverables, debt types, and Verification Status format.anti-patterns.md defines known failure modes, correct alternatives, and self-deception signals.mode axis. When input materials are incomplete, declare a Bounded Assessment before proceeding.references/ only when the manifest's references.on_demand condition 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.
| 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 |
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.
| 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 |
Take joshua-zyy/academic-reviser from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.