Claude Cookbooks Reference
2025Emma/vibe-coding-cn
Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns.
Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。
Install Aivis
$ npx skills add onism1767-creator/potato --skill aivis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install onism1767-creator/potato aivis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .claude/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add onism1767-creator/potato --skill aivis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install onism1767-creator/potato aivis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .agents/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add onism1767-creator/potato --skill aivis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install onism1767-creator/potato aivis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .cursor/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add onism1767-creator/potato --skill aivis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install onism1767-creator/potato aivis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .gemini/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install onism1767-creator/potato aivisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add onism1767-creator/potato --skill aivis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .github/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add onism1767-creator/potato --skill aivis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install onism1767-creator/potato aivis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "aivis" agent skill from https://github.com/onism1767-creator/potato/tree/main into .opencode/skills/aivis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "aivis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
aivis- GitHub stars
- 166
- Token cost
- ~757 tokens
- SKILL.md length
- 232 words
- Files
- 111
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。
- Works in 7 steps: 收集输入:焦点品牌全名(明确请用户给全名,别用简称)+ 常见简称(aliases)+ → 建议竞品集:按品类提候选(名+域名,可用 web_search 落地)→… → 盲起草 24 题(严格 8 发现 + 6 比较 + 6 本地 + 4 防御) → …
- Tasks that involve Web search
- SKILL.md covers 两种模式, 成本闸门(每次真实运行前) and 红线提醒(对 Skill 使用者同样生效)
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Aivis is an agent skill from onism1767-creator/potato. Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。 仅观测,不生成"照做就能提升 AI 提及"的建议。
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 117 other files (for example `.github/workflows/ci.yml`, `.pre-commit-config.yaml` and `ARCHITECTURE.md`).
It sits in AI & LLM Engineering, covering Web search, LLM API integration and AI search optimization. It works with Anthropic API and Python. The repository describes itself as: Free Easy AI visibility check - measure how often a brand is mentioned & cited in Claude's web-search answers. Deterministic, reproducible, runs 100% locally, $0 mock by default. The licence is MIT.
When your agent uses it
- Tasks that involve Web search
- Tasks that involve LLM API integration
- Tasks that involve AI search optimization
Example prompts
- “照做就能提升 AI 提及”
- “/aivis”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 收集输入:焦点品牌全名(明确请用户给全名,别用简称)+ 常见简称(aliases)+
- 建议竞品集:按品类提候选(名+域名,可用 web_search 落地)→ 用户加/删/确认。
- 盲起草 24 题(严格 8 发现 + 6 比较 + 6 本地 + 4 防御)
- 草稿质检:aivis validate --config-dir --phase draft → 必须 0 硬错(此档配比严格);有错你自己改、重起草,不打扰用户。
- 给用户看 / 改(用户最终拍板):按桶展示 24 题 + 竞品集,你在旁给意见;用户有完全修改权。
- 冻结
- 交棒 MONITORING。
What it can do on your machine
Read from SKILL.md and the folder at commit 6357acd. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Aivis loads about 757 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 232 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from onism1767-creator/potato at commit 6357acd, republished under its MIT licence (© onism1767-creator). 232 words, ~757 tokens.
Download SKILL.mdSave it as
.claude/skills/aivis/SKILL.md (or your agent's skills folder). This skill also uses 110 other files; get the full folder from GitHub.- name
- aivis
- description
- Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(web_search), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。 仅观测,不生成"照做就能提升 AI 提及"的建议。
aivis — Claude API web-search 可见度(代理测量)
薄入口:本文只编排流程,逻辑全在
aivis库 / CLI 里。 起草问题的逐桶原则见 docs/question-drafting-principles.md; SETUP 完整流程与决策见 docs/setup-flow-spec.md。
不在对话里、想自助? 跑
aivis gui启动本机网页向导(只监听 127.0.0.1), 用图形化 3 步走完同一套 SETUP→run→报告;免费档零成本、不用 key。 本 Skill 是同一能力的对话式入口(AI 帮你起草、你拍板),适合需要 AI 协作起草时用。
原理一句话:用 24 道固定题(8 发现 / 6 比较 / 6 本地 / 4 防御;前 20 道不点名品牌以免引导 AI)反复提问(每题问到"提及品牌集稳定"为止),再用确定性规则(非 AI 判官、保守计数、 三档证据 mentioned→cited→verified)计分,每个数字带不确定区间。可复现、可审计。 🟥 成本诚实:本工具开源免费、作者不收任何费用;你花的钱是付给 Anthropic 跑 Claude 的 AI 费用(自带 key,A 社直接计费),不经作者。全程本机运行、不上传任何数据。
两种模式
SETUP(一次性 · 建一条新基线)
触发:用户想测某个品牌在 Claude 里的可见度,或说 "setup"。照下面 7 步走; AI(=对话中的你)只在本模式起草问题/建议竞品,且必须人工确认后冻结(CLAUDE.md §7.1)。
- 收集输入:焦点品牌全名(明确请用户给全名,别用简称)+ 常见简称(aliases)+
歧义简称(进 ambiguous_aliases,只记录不计分);官网域名;品类/行业描述(驱动起草);
locale/region/档位(默认 en-US / US / standard);(可选)用户已知的种子竞品。
- 🔒 推荐用户另起一个新对话窗口专做起草 —— 新窗口里焦点品牌没进上下文,起草中立题时更接近"真盲",不易被焦点强项带偏(盲起草是程序性盲,非密码学级)。
- 建议竞品集:按品类提候选(名+域名,可用 web_search 落地)→ 用户加/删/确认。
- 诚实:SOV 只代表"声明的 N 个品牌内的份额",不是绝对市场份额;漏的竞品跑完后由中立题自审计、下一基线补。
- 盲起草 24 题(严格 8 发现 + 6 比较 + 6 本地 + 4 防御):
- 前 20 中立题只依据品类、绝不点名任何品牌;4 防御题起草中立双面骨架 + 注入焦点品牌名。
- 逐桶照 question-drafting-principles.md 的原则与句式模板。
- 草稿质检:
aivis validate --config-dir <dir> --phase draft→ 必须 0 硬错(此档配比严格);有错你自己改、重起草,不打扰用户。 - 给用户看 / 改(用户最终拍板):按桶展示 24 题 + 竞品集,你在旁给意见;用户有完全修改权。
改完
aivis validate --phase final,把结果当意见呈现:🟡 告警(如配比)只提醒;🔴 硬错(中立题点名品牌等红线)大声红色警告并解释危害。 - 冻结:
aivis init <name> --focal-name "品牌全名" --focal-domain <域名> [--category "品类"]生成焦点模式骨架(24 槽 + 版本号)。- 把确认后的 24 题填进
configs/<name>/questions.yml、竞品填进brands.yml。 - 末次
aivis validate --config-dir configs/<name> --phase final复核。 - 🔴 红错不拦冻结:若仍有红错,最后一次大声警告"这样冻结会让测量不诚实,确认是你的决定吗?"——用户确认即冻结,责任归用户(工具是观测器,不是守门人)。
- 改配置 = 版本号 bump(新基线),不许静默混入旧趋势。
- 交棒 MONITORING。
MONITORING(重复 · 跑基线出报告)
只重放冻结配置,不再起草:
- 先 mock 跑通(零成本):
aivis run --config-dir configs/<name> - 真实运行:
aivis run --config-dir configs/<name> --provider anthropic --yes(过成本闸门) - 流程 probe → extract → verify → score → report,产出 Markdown + CSV(默认离线核验;
--check fetch真抓被引页面)。
成本闸门(每次真实运行前)
- 开跑前先估(零成本、不联网):
aivis estimate --config-dir configs/<name> --provider anthropic [--tier standard|high]→ 打印"≈N 次调用 ≈ $X(保守上界)"并对比budget_cap_usd,告诉你会不会被拦。 - mock(默认)估价为 0,静默通过;
- 真实 provider:估算"≈N 次调用 ≈ $X"并要求人工确认;超
budget_cap_usd开跑前直接阻断; - 运行中按真实累计花费硬封顶:逼近
budget_cap_usd即阻断,已完成部分保留、可--run-id续跑(估算只是上界,真实通常更低)。
红线提醒(对 Skill 使用者同样生效)
- 输出一律是"此引擎此配置下的代理测量",不是 AI 排名真相;
- 行动层只给线索(leads),不给保证;
- 核心指标全由确定性规则算;AI 只许在 SETUP 起草(人工确认后冻结),不进测量轨;
- 改配置 = 版本号 bump(新基线),不许静默混入旧趋势。
© onism1767-creator, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 110 other files in the repository root of onism1767-creator/potato.
- SKILL.md
- .github/workflows/ci.yml
- .gitignore
- .pre-commit-config.yaml
- ARCHITECTURE.md
- CLAUDE.md
- LICENSE
- README.md
- README.zh.md
- configs/demo/brands.yml
- configs/demo/questions.yml
- configs/smoke/brands.yml
- configs/smoke/questions.yml
- docs/assets/gui-wizard.png
- … and 97 more
Open the folder on GitHubat commit 6357acd
Compare with similar skills
Aivis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Aivis this skillonism1767-creator/potato | 166 | — | ~757 | Automated safety check: Pass | MIT | |
| Claude Cookbooks Reference2025Emma/vibe-coding-cn | 23k | 1 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Claude APIloulanyue/awesome-claude-notes | 272 | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Claude API Developmentwarpdotdev/warp | 65k | 3 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Claude APIloulanyue/awesome-claude-notes | 272 | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Agent Framework Azure AI Pymicrosoft/skills | 3.1k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Claude API
loulanyue/awesome-claude-notes
Anthropic Claude API patterns for Python and TypeScript. An agent skill from loulanyue/awesome-claude-notes.
Claude API Development
warpdotdev/warp
Guides building, debugging and tuning apps on the Claude API and Anthropic SDK, including prompt caching, and migrating code between Claude model versions.
Claude API
loulanyue/awesome-claude-notes
Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。
- Official
Agent Framework Azure AI Py
microsoft/skills
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai).
Anth Hello World
jeremylongshore/tons-of-skills-marketplace
Create a minimal working Anthropic Claude Messages API example.
Related
Works with
Questions about Aivis
What does Aivis do?
Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。. Aivis is an agent skill from onism1767-creator/potato.
When should I use Aivis?
Aivis fits situations like: tasks that involve Web search; tasks that involve LLM API integration; tasks that involve AI search optimization.
How do I install Aivis in Claude Code?
Run `npx skills add onism1767-creator/potato --skill aivis -a claude-code`. Or copy the skill folder (the onism1767-creator/potato repository) into .claude/skills/aivis in your project. Claude Code loads it when a task matches its description.
How do I install Aivis in Codex?
Run `npx skills add onism1767-creator/potato --skill aivis -a codex`. Or copy the skill folder (the onism1767-creator/potato repository) into .agents/skills/aivis in your project. Codex loads it when a task matches its description.
Can I use Aivis in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add onism1767-creator/potato --skill aivis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aivis, .gemini/skills/aivis, .github/skills/aivis and .opencode/skills/aivis in your project.
What does Aivis need to run?
SKILL.md names no scripts, command-line tools or credentials: Aivis is instructions for the agent only.
Does Aivis access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Aivis safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Aivis use?
Aivis is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Aivis use?
About 757 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Aivis?
Skills that share tags, products or a category with Aivis: Claude Cookbooks Reference (2025Emma/vibe-coding-cn, 23k stars), Claude API (loulanyue/awesome-claude-notes, 272 stars), Claude API Development (warpdotdev/warp, 65k stars) and Claude API (loulanyue/awesome-claude-notes, 272 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Aivis?
onism1767-creator (a GitHub user) maintains it in onism1767-creator/potato, which has 166 GitHub stars. The repository was last updated on June 22, 2026.
Source: onism1767-creator/potato on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.