anthropics/skills
Public repository for Agent Skills
https://skillcdn.ai/gh/anthropics/skillsConnect this address to your AI to use these skills. How to connect
- Unverified
- Default branch
main - Commit
ca45fc4 - License
None declared - Searchwords and meaning
Explore this repository
Searches the original text of skills and documents by words and by meaning; display translations are not searched.
Folders
Documents
- Admin API (Organization Management)Read this file when the user wants to manage their Anthropic organization programmatically: members and roles, invites, workspaces and workspace members, API keys, rate limit reports, service account…skills/claude-api/shared/admin-api.md
- Agent Design PatternsThis file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs. For per-…skills/claude-api/shared/agent-design.md
- Anthropic CLI (`ant`)The ant CLI exposes every Claude API resource as a shell subcommand. Compared to curl: request bodies are built from typed flags or piped YAML instead of hand-written JSON, @path inlines file content…skills/claude-api/shared/anthropic-cli.md
- Claude Platform on AWSAnthropic-operated access to the Claude Developer Platform through AWS infrastructure - SigV4 authentication, AWS IAM access control, and AWS Marketplace billing. Because Anthropic operates it, the A…skills/claude-api/shared/claude-platform-on-aws.md
- Cost Optimization - Cutting Spend per Completed TaskAPI spend is optimized in units of cost per completed task, not cost per token. A model with a higher sticker price can be the cheaper option if it finishes the job in fewer turns, and a cheaper mode…skills/claude-api/shared/cost-optimization.md
- HTTP Error Codes ReferenceThis file documents HTTP error codes returned by the Claude API, their common causes, and how to handle them. For language-specific error handling examples, see the python/ or typescript/ folders.skills/claude-api/shared/error-codes.md
- Live Documentation SourcesThis file contains WebFetch URLs for fetching current information from platform.claude.com and Agent SDK repositories. Use these when users need the latest data that may have changed since the cached…skills/claude-api/shared/live-sources.md
- Managed Agents - Endpoint ReferenceAll endpoints require x-api-key and anthropic-version: 2023-06-01 headers. Managed Agents endpoints additionally require the anthropic-beta header.skills/claude-api/shared/managed-agents-api-reference.md
- Managed Agents - Common Client PatternsPatterns you'll write on the client side when driving a Managed Agent session, grounded in working SDK examples.skills/claude-api/shared/managed-agents-client-patterns.md
- Managed Agents - Core ConceptsManaged Agents is built around four core concepts:skills/claude-api/shared/managed-agents-core.md
- Managed Agents - Environments & ResourcesCreating a session requires an environment_id. Environments are reusable configuration templates for spinning up containers in Anthropic's infrastructure - you might create different environments for…skills/claude-api/shared/managed-agents-environments.md
- Managed Agents - Events & SteeringSend events to a session via POST /v1/sessions/{id}/events.skills/claude-api/shared/managed-agents-events.md
- Managed Agents - Memory StoresSessions are ephemeral by default - when one ends, anything the agent learned is gone. A memory store is a workspace-scoped collection of small text documents that persists across sessions. When a st…skills/claude-api/shared/managed-agents-memory.md
- Managed Agents - Multiagent SessionsA coordinator agent can delegate to other agents within one session. All agents share the container and filesystem; each runs in its own thread - a context-isolated event stream with its own conversa…skills/claude-api/shared/managed-agents-multiagent.md
- Managed Agents - Onboarding From a Bundled QuickstartThis guide holds the questions. shared/managed-agents-onboarding-from-url.md holds the mechanics: §3 the proposal checklist, §4 the file layout and ant apply filename rules, §5 apply, credentials, pa…skills/claude-api/shared/managed-agents-onboarding-from-quickstart.md
- Managed Agents - Onboarding From a URLThe job is five beats - fetch -> extract -> propose -> write -> apply - and the output is a directory the user can commit, not SDK code. The setup itself runs through the ant CLI. A language the proj…skills/claude-api/shared/managed-agents-onboarding-from-url.md
- Managed Agents - Onboarding FlowClaude Managed Agents is a hosted agent: Anthropic runs the agent loop and provisions a sandboxed container per session where the agent's tools execute (or your own worker, with a self_hosted environ…skills/claude-api/shared/managed-agents-onboarding.md
- Managed Agents - OutcomesAn outcome elevates a session from conversation to work: you state what "done" looks like, and the harness runs an iterate -> grade -> revise loop until the artifact meets the rubric, hits max_iterat…skills/claude-api/shared/managed-agents-outcomes.md
- Managed Agents - OverviewManaged Agents provisions a container per session as the agent's workspace. The agent loop runs on Anthropic's orchestration layer; the container is where the agent's tools execute - bash commands, f…skills/claude-api/shared/managed-agents-overview.md
- Managed Agents - Scheduled DeploymentsA scheduled deployment runs an agent on a recurring cron schedule - each firing creates a session autonomously. Use it for predictable-cadence work: nightly triage, weekly compliance scans, hourly mo…skills/claude-api/shared/managed-agents-scheduled-deployments.md
- Managed Agents - Self-Hosted SandboxesWith config.type: "self_hosted", the agent loop stays on Anthropic's orchestration layer but tool execution moves to infrastructure you control - bash, file ops, and code run inside your container, s…skills/claude-api/shared/managed-agents-self-hosted-sandboxes.md
- Managed Agents - Tools & SkillsRecommendation: Enable the prebuilt tools via agent_toolset_20260401 with web_fetch and web_search disabled and auto as the toolset's permission policy, and turn a web tool on only when the job needs…skills/claude-api/shared/managed-agents-tools.md
- Managed Agents - WebhooksAnthropic can POST to your HTTPS endpoint when a Managed Agents resource changes state - an alternative to holding an SSE stream or polling. Payloads are thin (event type + resource IDs only); on rec…skills/claude-api/shared/managed-agents-webhooks.md
- model-migration.mdskills/claude-api/shared/model-migration.md
- Claude Model CatalogOnly use exact model IDs listed in this file. Never guess or construct model IDs - incorrect IDs will cause API errors. Use aliases wherever available. For the latest information, WebFetch the Models…skills/claude-api/shared/models.md
- Platform AvailabilityWhich features work on which provider platform. This table is the single source of truth in this skill - per-feature sections elsewhere point here instead of restating availability. When writing code…skills/claude-api/shared/platform-availability.md
- Preserved Thinking - Keeping Earlier Reasoning Valid Across a ConversationPreserved thinking is measured in units of conversations that keep their reasoning, not requests that pass. One edit to an earlier turn invalidates every thinking block after it, and the same stale b…skills/claude-api/shared/preserved-thinking-migration.md
- Prompt Audit - Finding and Removing Dated Prompting PatternsPrompts, skills, and tool descriptions accumulate instructions tuned to older models: emphasis added because an old model under-triggered, step-by-step scripts added because an old model planned poor…skills/claude-api/shared/prompt-audit.md
- Prompt Caching - Design & OptimizationThis file covers how to design prompt-building code for effective caching. For language-specific syntax, see the ## Prompt Caching section in each language's README or single-file doc.skills/claude-api/shared/prompt-caching.md
- Token CountingUse the count_tokens endpoint (POST /v1/messages/count_tokens) for accurate token counts against Claude models. Token counts are model-specific - pass the same model ID you'll use for inference.skills/claude-api/shared/token-counting.md
- Tool Use ConceptsThis file covers the conceptual foundations of tool use with the Claude API. For language-specific code examples, see the python/, typescript/, or other language folders. For decision heuristics on w…skills/claude-api/shared/tool-use-concepts.md
Skipped (2)
These manifests were not served. Fix them and push: the next commit is indexed again.
skills/academy-guide/SKILL.mdlink_missinga link names no file of the repository (URL)README.mdlink_missing7 links name no file of the repository (./skills/docx, ./skills/pdf, ./skills/pptx, ...)