claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
Skill by sweetloser
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sweetloser-claude-api
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, ml, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
claude-api- Description
- Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
- License
- Complete terms in LICENSE.txt
- Instructions
- 541 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Agent Skills spec issues
- description: longer than 1024 characters
- body: 541 lines (spec recommends under 500)
Files (67)
- CONTRIBUTORS
- LICENSE.txt
- SKILL.md
- README.md · csharp/claude-api/
- batches.md · csharp/claude-api/
- files-api.md · csharp/claude-api/
- streaming.md · csharp/claude-api/
- tool-use.md · csharp/claude-api/
- examples.md · curl/
- managed-agents.md · curl/
- README.md · go/claude-api/
- files-api.md · go/claude-api/
- streaming.md · go/claude-api/
- tool-use.md · go/claude-api/
- README.md · go/managed-agents/
- README.md · java/claude-api/
- files-api.md · java/claude-api/
- streaming.md · java/claude-api/
- tool-use.md · java/claude-api/
- README.md · java/managed-agents/
- README.md · php/claude-api/
- batches.md · php/claude-api/
- files-api.md · php/claude-api/
- streaming.md · php/claude-api/
- tool-use.md · php/claude-api/
- README.md · php/managed-agents/
- README.md · python/claude-api/
- batches.md · python/claude-api/
- files-api.md · python/claude-api/
- streaming.md · python/claude-api/
- tool-use.md · python/claude-api/
- README.md · python/managed-agents/
- README.md · ruby/claude-api/
- streaming.md · ruby/claude-api/
- tool-use.md · ruby/claude-api/
- README.md · ruby/managed-agents/
- agent-design.md · shared/
- anthropic-cli.md · shared/
- claude-platform-on-aws.md · shared/
- error-codes.md · shared/
- live-sources.md · shared/
- managed-agents-api-reference.md · shared/
- managed-agents-client-patterns.md · shared/
- managed-agents-core.md · shared/
- managed-agents-environments.md · shared/
- managed-agents-events.md · shared/
- managed-agents-memory.md · shared/
- managed-agents-multiagent.md · shared/
- managed-agents-onboarding.md · shared/
- managed-agents-outcomes.md · shared/
- managed-agents-overview.md · shared/
- managed-agents-scheduled-deployments.md · shared/
- managed-agents-self-hosted-sandboxes.md · shared/
- managed-agents-tools.md · shared/
- managed-agents-webhooks.md · shared/
- model-migration.md · shared/
- models.md · shared/
- platform-availability.md · shared/
- prompt-caching.md · shared/
- token-counting.md · shared/
- …and 7 more
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from sweetloser/teamai
- 0.525score
blocked-page-recovery
sweetloser
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
SkillBFreshness: BClaude Code +9 - 0.524score
bugly-dingtalk-sync
sweetloser
自动统计 Bugly 异常并同步到钉钉 AI 表格：按时间范围和可选版本读取异常列表与详情，提取设备、系统版本和完整堆栈，计算跨次同步增量，合并同类问题，累加发生次数和设备数，回写钉钉，并给已纳入统计的问题添加‘已统计’标签。Use when the user asks to 执行 Bugly…
SkillBFreshness: BClaude Code +9 - 0.520score
box
sweetloser
Box manages cloud files, sharing, search, and metadata.
SkillBFreshness: BClaude Code +9 - 0.519score
code-simplifier
sweetloser
Simplify and refine code for clarity, consistency, and maintainability while preserving observable behavior.
SkillBFreshness: BClaude Code +9 - 0.494score
brand-guidelines
sweetloser
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillBFreshness: BClaude Code +9 - 0.494score
algorithmic-art
sweetloser
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
SkillBFreshness: BClaude Code +9 - 0.494score
canvas-design
sweetloser
Create beautiful visual art in .png and .pdf documents using design philosophy.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Complete terms in LICENSE.txt
- Repository
- github.com/sweetloser/teamai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.865score
claude-api
anthropicsOfficial
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 183.5KClaude Code +9 - 0.377score
claude-api
guanyang
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 980Claude Code +9 - 0.367score
claude-api
boisenoise
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 12Claude Code +9 - 0.363score
claude-api
leeno7786-coder
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 4Claude Code +9 - 0.356score
claude-api
justinlietz93
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillBFreshness: B★ 23Claude Code +9 - 0.356score
claude-api
justinlietz93
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillBFreshness: B★ 23Claude Code +9 - 0.351score
claude-api
nafeeur
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 2Claude Code +9 - 0.345score
claude-api
romanyukzhenya82-sketch
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillBFreshness: B★ 11Claude Code +9 - 0.341score
claude-api
philding123
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillAFreshness: A★ 1Claude Code +9 - 0.321score
claude-api
tassiovale
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillCFreshness: C★ 12Claude Code +9 - 0.307score
claude-api
VibishnathanG
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillBFreshness: BClaude Code +9 - 0.307score
claude-api
Neuroca-Inc
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
SkillBFreshness: BClaude Code +9
More from sweetloser
- 0.525score
blocked-page-recovery
sweetloser
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
SkillBFreshness: BClaude Code +9 - 0.524score
bugly-dingtalk-sync
sweetloser
自动统计 Bugly 异常并同步到钉钉 AI 表格：按时间范围和可选版本读取异常列表与详情，提取设备、系统版本和完整堆栈，计算跨次同步增量，合并同类问题，累加发生次数和设备数，回写钉钉，并给已纳入统计的问题添加‘已统计’标签。Use when the user asks to 执行 Bugly…
SkillBFreshness: BClaude Code +9 - 0.520score
box
sweetloser
Box manages cloud files, sharing, search, and metadata.
SkillBFreshness: BClaude Code +9 - 0.519score
code-simplifier
sweetloser
Simplify and refine code for clarity, consistency, and maintainability while preserving observable behavior.
SkillBFreshness: BClaude Code +9 - 0.494score
brand-guidelines
sweetloser
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
SkillBFreshness: BClaude Code +9 - 0.494score
algorithmic-art
sweetloser
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
SkillBFreshness: BClaude Code +9
Cite this page
claude-api skill. Agent Mart. https://agentmart.dev/skills/sweetloser-claude-api (last updated 2026-10-24)