Search Answer Reviewer

Web search review. Use when an agent is about to search the web, receives web search results or retrieved pages, or checks an answer based on them. Activate before the first search; review results before using them, even without an explicit audit request. 中文：网页搜索前启用，结果返回后审查。

33 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add 57-H/search-answer-reviewer --skill search-answer-reviewer

Manual install

git clone --depth 1 https://github.com/57-H/search-answer-reviewer.git /tmp/search-answer-reviewer
mkdir -p ~/.claude/skills
cp -r /tmp/search-answer-reviewer/. ~/.claude/skills/search-answer-reviewer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Search Answer Reviewer

On a web-search task, start this workflow before the first search and review each returned batch before using it. Do this without waiting for the user to request a review. Return concrete evidence gaps and local correction suggestions when they matter to the answer.

Use the host's available search/read tools and model reasoning. The bundled Python CLI validates evidence records; it does not independently decide truth, browse, or invoke an LLM.

For ordinary search tools, keep one review record per returned batch and derive the user-visible coverage line from that record. For a host that exposes the experimental `SearchAuditGate`, use its gated search entry instead of the raw search backend. In hosts that expose an ungated search tool, this skill is guidance and cannot mechanically guarantee invocation after each tool result. Read [host-integration.md](references/host-integration.md) only when wiring a controlled search application.

## Mandatory gate for every ordinary search batch

Before using any returned result in reasoning or an answer, create `work/batch-review.json` using the ordinary batch format in [schema.md](references/schema.md), then run:

```bash
python /absolute/path/to/search-answer-reviewer/scripts/review.py ordinary-status --input work/batch-review.json
```

Read the full skill on GitHub

Details

Skill name: search-answer-reviewer
Repository: 57-H/search-answer-reviewer
License: MIT
Repo updated: 23 September 2026

FAQ

What does the Search Answer Reviewer skill do?

How do I install the Search Answer Reviewer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add 57-H/search-answer-reviewer --skill search-answer-reviewer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Search Answer Reviewer popular?

It lives in 57-H/search-answer-reviewer, which has 33 GitHub stars and 0 forks.

Related skills

Specification Website

tcsenpai/specification-website-skill

Apply The Website Specification — a platform-agnostic specification of what a good website does, with each item tagged required, recommended, optional, or avoid. Use when the user asks what their site should have, whether something is required, how to audit a URL, what's missing for agent readiness, or anything else where you'd otherwise be guessing at web best practice. Covers HTML foundations, SEO, accessibility, security, well-known URIs, agent readiness, performance, privacy, resilience, and internationalisation. Backs answers with primary sources (WHATWG, W3C, IETF RFCs, IANA, WCAG, schem

AI, LLMs & Agents

Skill Router

hussi9/skill-router

Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.

AI, LLMs & Agents

Agent Credit

aaronjmars/agent-credit

Borrow from Aave V3 via credit delegation. Agent draws against delegator collateral. Supports borrow, repay, health checks.

AI, LLMs & Agents

Ncm Listening Profile

dragonknightk/ncm-listening-profile

当用户想在 Windows 或 macOS 上采集网易云音乐/NetEase Cloud Music 桌面版听歌画像数据、导出主歌单和听歌排行、生成本地 JSONL/CSV/aggregate 文件与 AI 分析 prompt 时使用。此 Skill 通过 CDP 启动或连接本机网易云音乐客户端，在已登录页面上下文用网易云 `/api` 采集用户创建歌单、主歌单、最近一周听歌排行和所有时间听歌排行；本 Skill 不在采集会话内做人格或画像分析。

AI, LLMs & Agents10

Flowmaker

xntj-ai/flowmaker

生成单 HTML、零后端、可拖拽编辑的网页流程图。LLM 只产出 nodes/edges 的 JSON，引擎自动布局并渲染成浅色玻璃风、带判断菱形/起止圆角条/处理矩形三种形状的可交互流程图（拖节点、拖连线、双击改名、面板增删）。Use when 用户要"做流程图/画流程图/把流程画出来/流程可视化/flowchart/泳道/判断分支图"，尤其要可在浏览器里编辑、且要一个独立 HTML 文件不带后端。NOT for 纯静态示意图（直接 mermaid 即可）、需要服务端渲染的大批量图表。

AI, LLMs & Agents

Claude Md Optimizer

wrsmith108/claude-md-optimizer

Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.