Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mronkko/claude-academic-research/plugin install editorial-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mronkko/claude-academic-research/suggesting-reviewers)<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/suggesting-reviewers"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/suggesting-reviewers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mronkko/claude-academic-research/suggesting-reviewers"><img src="https://agentmods.dev/badge/skills/mronkko/claude-academic-research/suggesting-reviewers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.03059 |
| Opus 5 | $0.00079 | $0.01529 |
| Sonnet 5 | $0.00032 | $0.00612 |
| Haiku 4.5 | $0.00016 | $0.00306 |
Grade A, and why
suggesting-reviewers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suggesting reviewers or associate editors
Given a manuscript abstract, propose either peer reviewers or an associate editor (AE) to handle the paper, and explain each candidate's fit. Default journal: Organizational Research Methods (ORM).
Mode — reviewer vs. AE
Detect the mode from the request and announce which one you are running.
- Reviewer mode (default — "suggest reviewers", "find referees", …). Two pools: editorial-board members (filtered by eligibility, matched against pre-built profiles) and external experts (found live from the abstract's topics).
- AE mode ("suggest an AE", "assign an associate editor", "who should handle this paper", …). One pool: the journal's current associate editors. No external search — an AE must be a sitting board officer.
The two modes share everything below except the two steps that explicitly branch (Step 2 eligibility, Step 4 candidate lists). If the request is ambiguous, ask which is wanted before proceeding.
Core principle — combine knowledge with retrieval
Training knowledge is a useful starting point: it maps the field and knows established scholars. But it has two blind spots — lesser-known / junior researchers and very recent work — and those are exactly where this skill adds value. So every run must augment training recall with retrieval: the pre-built board profiles plus live OpenAlex / Semantic Scholar searches that deliberately reach for recent and less-visible names.
Ground each final suggestion in a retrieved publication record wherever one exists — and especially for the less-famous names, where training recall is least reliable. Never put a junior or unfamiliar person in the output on memory alone.
Step 1 — Load the roster and check staleness
The bundled ORM data lives under the plugin root:
${CLAUDE_PLUGIN_ROOT}/skills/suggesting-reviewers/rosters/orm/
index.md # membership + role + eligible: yes/no, with snapshot_date
profiles/<surname>.md
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rosters/orm/index.md 11 KB
- rosters/orm/profiles/abdallah.md 2.1 KB
- rosters/orm/profiles/aguinis.md 4.0 KB
- rosters/orm/profiles/alessandri.md 2.0 KB
- rosters/orm/profiles/alvesson.md 2.0 KB
- rosters/orm/profiles/amis.md 2.1 KB
- rosters/orm/profiles/antonakis.md 2.5 KB
- rosters/orm/profiles/baltes.md 2.2 KB
- rosters/orm/profiles/banks.md 2.3 KB
- rosters/orm/profiles/beal.md 2.8 KB
- rosters/orm/profiles/bednarek.md 2.0 KB
- rosters/orm/profiles/bergh.md 2.6 KB
- rosters/orm/profiles/bliese.md 3.2 KB
- rosters/orm/profiles/blumberg.md 2.1 KB
- rosters/orm/profiles/bodner.md 2.2 KB
- rosters/orm/profiles/bohon.md 2.1 KB
- rosters/orm/profiles/bowen.md 2.1 KB
- rosters/orm/profiles/braun.md 2.7 KB
- rosters/orm/profiles/breitsohl.md 2.1 KB
- rosters/orm/profiles/brown.md 2.5 KB
- rosters/orm/profiles/busenbark.md 2.1 KB
- rosters/orm/profiles/butts.md 1.8 KB
- rosters/orm/profiles/carlson-kevin.md 2.1 KB
- rosters/orm/profiles/carter-nathan.md 2.0 KB
- rosters/orm/profiles/cassell.md 1.9 KB
- rosters/orm/profiles/certo.md 2.3 KB
- rosters/orm/profiles/chen.md 2.0 KB
- rosters/orm/profiles/cheung.md 3.0 KB
- rosters/orm/profiles/cilesiz.md 2.0 KB
- rosters/orm/profiles/cole.md 2.5 KB
- rosters/orm/profiles/corley.md 2.1 KB
- rosters/orm/profiles/cortina-jose.md 3.6 KB
- rosters/orm/profiles/cortina-kai.md 2.1 KB
- rosters/orm/profiles/culpepper.md 2.2 KB
- rosters/orm/profiles/cunliffe.md 2.4 KB
- rosters/orm/profiles/dalal.md 2.3 KB
- rosters/orm/profiles/davidsson.md 1.9 KB
- rosters/orm/profiles/davison.md 2.2 KB
- rosters/orm/profiles/dawson.md 3.7 KB
- rosters/orm/profiles/dejordy.md 1.9 KB
- rosters/orm/profiles/deshon.md 2.5 KB
- rosters/orm/profiles/desimone.md 4.4 KB
- rosters/orm/profiles/dietz.md 1.8 KB
- rosters/orm/profiles/drasgow.md 3.0 KB
- rosters/orm/profiles/dul.md 1.9 KB
- rosters/orm/profiles/eckardt.md 1.7 KB
- rosters/orm/profiles/edwards.md 3.1 KB
- rosters/orm/profiles/fiss.md 1.8 KB
- rosters/orm/profiles/gill.md 1.9 KB
- rosters/orm/profiles/goodman.md 1.8 KB
- rosters/orm/profiles/gooty.md 2.0 KB
- rosters/orm/profiles/gove.md 1.9 KB
- rosters/orm/profiles/graffin.md 1.9 KB
- rosters/orm/profiles/greckhamer.md 3.5 KB
- rosters/orm/profiles/hansen.md 2.2 KB
- rosters/orm/profiles/harley.md 1.8 KB
- rosters/orm/profiles/hernandez.md 2.0 KB
- rosters/orm/profiles/hibbert.md 1.7 KB
- rosters/orm/profiles/hickman.md 2.8 KB
- rosters/orm/profiles/hofmans.md 1.8 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 248 lines · 158 tokens per session scan A 5a06f2064d3a
suggesting-reviewers is a skill published in the GitHub repository mronkko/claude-academic-research (23 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 3,059 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…