Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AndyZhuang/Opentest --skill review-writinggit clone --depth 1 https://github.com/AndyZhuang/OpentestWrote 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/andyzhuang/opentest/review-writing)<a href="https://agentmods.dev/skills/andyzhuang/opentest/review-writing"><img src="https://agentmods.dev/badge/skills/andyzhuang/opentest/review-writing/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/andyzhuang/opentest/review-writing"><img src="https://agentmods.dev/badge/skills/andyzhuang/opentest/review-writing.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 | $0.00000 | $0.04847 |
| Opus 5 | $0.00000 | $0.02423 |
| Sonnet 5 | $0.00000 | $0.00969 |
| Haiku 4.5 | $0.00000 | $0.00485 |
Grade A, and why
review-writing 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 8d 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.
This is a copy
100% identical to review-writing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Writing — 学术综述逐节写作方法论
Use this skill when the user asks to write a literature review, review article, or 综述 based on an outline. Trigger keywords: "写综述", "write review", "综述写作", "按大纲写", "逐节写", "review section", "写第N节". This skill orchestrates the ENTIRE review writing process from outline to finished manuscript.
This skill calls academic-literature-search skill for all search and citation operations. Read that skill first if not already loaded.
Tool routing: PubMed operations → MCP tools (pubmed_search_articles, pubmed_fetch_contents, pubmed_article_connections). arXiv search, GB/T 7714 formatting, citation processing → Python code. See academic-literature-search for the complete routing table and code templates.
Architecture: Why Section-by-Section
A full review (12,000–15,000 words, 100–130 references) CANNOT be written in one pass due to context window limits. The correct approach:
Outline
→ [Phase 0: Validate & Revise outline]
→ [Phase 1..N: Per-section pipeline]
→ [Final: Assemble full review]
Each section is an independent unit of work:
Search → Filter → Group → Write → Cite → Save to file
↓
section_N.md (persisted immediately)
Final assembly reads all section files → cross-section dedup → unified numbering
Phase 0: Outline Validation & Revision (大纲验证与修订)
DO NOT skip this phase. No outline is perfect before reading the literature.
Step 0.1: Read the outline
Read the user's outline file. Parse each section's title, sub-topics, and any pre-identified references.
Step 0.2: Scout search (侦察检索)
For each section, run ONE quick search using the section title/topic as query:
- MCP
pubmed_search_articles(maxResults=10, fetchBriefSummaries=5) - For CS/AI-heavy sections: also Python
search_arxiv()(max_results=5) - For sections with known seed papers: MCP
pubmed_article_connections(similar, maxRelatedResults=5)
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.
- 8d ago First seen · 503 lines · 0 tokens per session scan A 316b20610fde
review-writing is a skill published in the GitHub repository AndyZhuang/Opentest (22 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,847 tokens. A static security scan graded it A with 0 findings. It is 100% identical to review-writing, differing in 0 lines, and is treated as a copy.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…