claude

messages-api-features

Use Claude API platform features correctly: thinking and effort, prompt caching, long context and context management, memory tool, code execution, web search and fetch, and computer use. Version-neutral guidance with links to the official docs. 7 skills.

6 on GitHubby latestaiagentsv2.1.0MITupdated 9 days agoAI Platform
/

Plugin messages-api-features from marketplace latestaiagents in latestaiagents/agent-skills. Commands read from the repo's manifest — 8 days ago.

What it installs

Skills (7)

  • code-execution

    Use the Claude API code execution tool so the model runs Bash and Python in an Anthropic-hosted sandbox during a response — for calculation, data analysis, file generation, and checking its own work. Covers tool versions, file upload, retrieving generated files, container reuse, limits, and data-ret

  • computer-use

    Build desktop and browser automation agents with the Claude API computer use toolset — screenshots, clicks, typing, scrolling — run by your own harness inside an isolated VM or container. Covers choosing the toolset version, the agent loop, batch actions, sandboxing, prompt-injection risk, and when

  • long-context

    Work with large Claude context windows deliberately — check the window for your model, count tokens before sending, structure long inputs for recall, cache the stable part, and manage growing conversations with compaction, context editing, or memory instead of stuffing everything in. Use this skill

  • memory-tool

    Give Claude agents persistent memory across conversations with the Claude API memory tool — a client-side file store under /memories that Claude reads and writes through commands your application executes. Covers setup, the six commands, SDK helpers, path-traversal protection, and pairing memory wit

  • prompt-caching

    Use Claude API prompt caching to reuse processed prompt prefixes across requests — automatic vs explicit breakpoints, 5-minute and 1-hour TTLs, minimum cacheable lengths, what invalidates the cache, and how to measure hit rate from usage fields. Use this skill when building apps with large repeated

  • thinking-and-effort

    Configure Claude's thinking and the effort parameter correctly — adaptive vs legacy budget-based thinking, the display setting, effort levels, thinking with tool use, cost control with max_tokens, and how thinking settings interact with prompt caching. Model behavior differs, so the skill shows how

  • web-search-and-fetch

    Give Claude live web access with the Claude API web search and web fetch server tools — choosing tool versions, domain filtering, max_uses, citations, dynamic filtering, handling errors that arrive inside a 200 response, multi-turn requirements, cost, and data-exfiltration safeguards. Use this skill

View source on GitHub latestaiagents.com

More from latestaiagents/agent-skills

All 29 plugins →

developer-toolkit

claude

Developer plugin: the 19 developer skills + 2 commands. MCP servers: GitHub, Sentry, Linear, Atlassian (each needs your own account).

19 skills · 2 commands · 4 MCP servers

6

security-guardian

claude

Security plugin: all 16 security skills (OWASP-category and common practices) + 2 commands. MCP server: GitHub. For the same skills without commands or MCP, install the security entry.

16 skills · 2 commands · 1 MCP server

6

devops-sre

claude

DevOps/SRE plugin: incident response, runbooks, on-call, Kubernetes troubleshooting, observability, SLOs. 8 skills + 6 commands. MCP servers: Datadog, PagerDuty, GitHub (each needs your own account).

8 skills · 6 commands · 3 MCP servers

6

agent-plugin

claude

Multi-agent plugin: the 13 agent-architect skills + 2 commands (design-agent, debug-agent). No MCP servers.

13 skills · 2 commands

6

agent-architect

claude

Multi-agent system design: supervisor and mesh patterns, handoffs, memory, tool routing, error recovery, cost budgets, testing, LangGraph, durable state, human-in-the-loop, checkpointing, A2A. 13 skills. Same skills as agent-plugin, without its commands.

13 skills

6

qa-testing

claude

QA/Testing plugin: test strategy, test writing, Playwright automation, API and performance testing. 6 skills + 3 commands. MCP servers: BrowserStack, Atlassian, GitHub (each needs your own account).

6 skills · 3 commands · 3 MCP servers

6

Similar plugins

claude-security

claude

Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents, that you apply when you choose.

1 skill · 9 agents · hooks

anthropics/claude-plugins-official 47,076

Synthflow

claude

Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search connector.

7 skills · 2 MCP servers

anthropics/knowledge-work-plugins 35,601

executive-mentor

claude

Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, navigates hard calls, runs postmortems. 5 sub-skills with slash commands.

6 skills · 1 agent

alirezarezvani/claude-skills 29,725

ideation

claude

Research ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.

98 skills

Orchestra-Research/AI-Research-SKILLs 14,502

insforge

claudecodex

The backend platform for AI-native developers. A Postgres-based backend with auth, storage, compute, hosting, and AI gateway — built for coding agents. This plugin gives agents the full InsForge surface: database CRUD with RLS, authentication, storage, edge functions, AI, realtime, Stripe payments, and deployments. Includes CLI infrastructure management, debugging diagnostics, and integration guides for third-party auth providers (Auth0, Clerk, Kinde, Stytch, WorkOS).

4 skills

InsForge/InsForge 13,326

dbs-jtbd

claude

用 Jobs to Be Done 识别具体情境中用户想推进的进展、切换方案的力量和选择标准，解释产品、服务或内容为何被选择。用户要求分析顾客任务、购买动机、替代方案或明确用 JTBD 重写提示词时使用；普通任务验收标准澄清无需套用该框架。

1 skill

dontbesilent2025/dbskill 11,416

Maintain messages-api-features?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins29 plugins