checker
claudeA checker agent tests claims, numbers and captions against the files they came from. Each objection quotes a file and line, and a hook checks the quote.
1 skill · 1 agent · hooks
0
claude
reviewers
Two or three reviewer agents read research in progress or a draft and give every item a verdict such as fix, develop or cut. A hook checks every quote they cite.
/
Plugin reviewers from marketplace research-skills in joverwiening/research-skills. Commands read from the repo's manifest — 10 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (1)
reviewersReferee-style review of research work in progress or a finished draft. Use for "review this", "is this promising", "is this going anywhere", "is this figure good", "is this result good enough", "what's missing", "review the draft", "judge the plan". Also before a figure or section goes into a paper
Subagents (1)
reviewerReads what exists and judges it, in one of two stages set by the brief. direction: work in progress, is it promising, what story could it tell, what does it need (no slot squeeze, nothing cut). final: a paper draft, final figure or submission as a journal referee with scarce slots (accept / minor /
Hooks (3)
- PreToolUse
node "${CLAUDE_PLUGIN_ROOT}/hooks/review-hooks.mjs" reviewer pre
- SubagentStop
node "${CLAUDE_PLUGIN_ROOT}/hooks/review-hooks.mjs" reviewer stop
- PostToolUse
node "${CLAUDE_PLUGIN_ROOT}/hooks/review-hooks.mjs" reviewer post
More from joverwiening/research-skills
All 6 plugins →brainstorm
claudeFor open questions: several agents each work out one different route, then the routes are compared and one is picked.
1 skill · 1 agent
0
theory
claudeDerivations one step at a time, each step tested numerically in a Python script. A hook refuses a test that asserts nothing.
1 skill · hooks
0
writing-rules
claudeRules for papers, grant text and essays, with a lint for words that tell the reader how to feel. The lint runs after every write to a .tex or .md file.
1 skill · hooks
0
lit-search
claudeLiterature search on OpenAlex and arXiv that follows citations. A small model reads the top papers in full, and code checks every quote it returns against the paper.
1 skill
0
Similar plugins
mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
mattpocock/skills 323,108
academic-research-skills
claude5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Imbad0202/academic-research-skills 56,698
open-code-review
claudePerform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
alibaba/open-code-review 50,068
agent-teams
claudecodexOrchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
wshobson/agents 42,461
codex
claudeUse Codex from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
openai/codex-plugin-cc 35,098
openseo
claudecodexWithout good data, your agent gives generic advice. Keyword research, competitor research, backlinks, and site audits. All for $10/month.
12 skills · 1 MCP server
every-app/open-seo 27,513
Maintain reviewers?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins6 plugins