1. Nullable vs Non-Null : Start nullable, make non-null when guaranteed 2. Input Types : Always use input types for mutations 3. Payload Pattern : Return errors in mutation payloads 4. Pagination : Use cursor-based for infinite scroll, offset for simple cases 5. Nam. Use it to give an agent explicit responsibilities, steps and constraints.
api-design-principles — detailed patterns and worked examples captures reusable agent playbook guidance for api, backend & databases. Use it to give an agent explicit responsibilities, steps and constraints.
Best practices for composing multi-agent teams, selecting team sizes, choosing agent types, and configuring display modes for Claude Code's Agent Teams feature. Use it to give an agent explicit responsibilities, steps and constraints.
Strategies for decomposing features into parallel work streams, establishing file ownership boundaries, avoiding conflicts, and integrating results from multiple implementer agents. Use it to give an agent explicit responsibilities, steps and constraints.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration. Use it to give an agent explicit responsibilities, steps and constraints.
This marketplace follows industry best practices with a focus on granularity, composability, and minimal token usage. Use it as a repeatable review, validation or hardening pass.
Complete reference for all 203 local specialized AI agents organized by category with model assignments. Use it as a repeatable review, validation or hardening pass.
Top-level architectural map for the claude-agents marketplace. Detail lives in docs/architecture.md; this file is the index per the OpenAI harness-engineering pattern. Use it to ground design choices in named patterns, trade-offs and examples.
Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. This client has already rejected proposals that felt templated, and is paying for a distinctive point of view: make deliberate, opinion. Use it to make implementation decisions and avoid common dead ends.
For operator instructions that arrive mid-conversation (mode switches, injected state), append {role: "system", ..} to messages instead of editing top-level system — this preserves the cached prefix and carries operator authority. Must follow a user message (or an assista. Use it as a repeatable review, validation or hardening pass.
This 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. Use it as a repeatable review, validation or hardening pass.
Override defaults for individual tools. This example enables everything except bash:. Use it to ground design choices in named patterns, trade-offs and examples.
Managed 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, file operations, code. You create a persisted Agent config (model, system pr. Use it to ground design choices in named patterns, trade-offs and examples.
An 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 iterations, or is interrupted. A separate grader (independent context windo. Use it to ground design choices in named patterns, trade-offs and examples.
Claude 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 environment — see shared/managed-agents-self-hosted-sandboxes.md). You supply an a. Use it to ground design choices in named patterns, trade-offs and examples.
Every session has a live trace view in the Anthropic Console at https://platform.claude.com/workspaces/{workspace}/sessions/{session id}. Print this URL immediately after creating a session so the user can watch tool calls and messages stream in real time. {workspace} is th. Use it to ground design choices in named patterns, trade-offs and examples.
This 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 content was last updated. Use it to ground design choices in named patterns, trade-offs and examples.
This 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-tool mechanics and code examples, see tool-use-concepts.md and the language-spe. Use it as a repeatable review, validation or hardening pass.
Use with options() to override client settings for a single call without mutating the client:. Use it as a repeatable review, validation or hardening pass.
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation. Use it to make implementation decisions and avoid common dead ends.
1. Nullable vs Non-Null : Start nullable, make non-null when guaranteed 2. Input Types : Always use input types for mutations 3. Payload Pattern : Return errors in mutation payloads 4. Pagination : Use cursor-based for infinite scroll, offset for simple cases 5. Nam. Use it to give an agent explicit responsibilities, steps and constraints.
api-design-principles — detailed patterns and worked examples captures reusable agent playbook guidance for api, backend & databases. Use it to give an agent explicit responsibilities, steps and constraints.
Best practices for composing multi-agent teams, selecting team sizes, choosing agent types, and configuring display modes for Claude Code's Agent Teams feature. Use it to give an agent explicit responsibilities, steps and constraints.
Strategies for decomposing features into parallel work streams, establishing file ownership boundaries, avoiding conflicts, and integrating results from multiple implementer agents. Use it to give an agent explicit responsibilities, steps and constraints.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration. Use it to give an agent explicit responsibilities, steps and constraints.
This marketplace follows industry best practices with a focus on granularity, composability, and minimal token usage. Use it as a repeatable review, validation or hardening pass.
Complete reference for all 203 local specialized AI agents organized by category with model assignments. Use it as a repeatable review, validation or hardening pass.
Top-level architectural map for the claude-agents marketplace. Detail lives in docs/architecture.md; this file is the index per the OpenAI harness-engineering pattern. Use it to ground design choices in named patterns, trade-offs and examples.
Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. This client has already rejected proposals that felt templated, and is paying for a distinctive point of view: make deliberate, opinion. Use it to make implementation decisions and avoid common dead ends.
For operator instructions that arrive mid-conversation (mode switches, injected state), append {role: "system", ..} to messages instead of editing top-level system — this preserves the cached prefix and carries operator authority. Must follow a user message (or an assista. Use it as a repeatable review, validation or hardening pass.
This 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. Use it as a repeatable review, validation or hardening pass.
Override defaults for individual tools. This example enables everything except bash:. Use it to ground design choices in named patterns, trade-offs and examples.
Managed 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, file operations, code. You create a persisted Agent config (model, system pr. Use it to ground design choices in named patterns, trade-offs and examples.
An 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 iterations, or is interrupted. A separate grader (independent context windo. Use it to ground design choices in named patterns, trade-offs and examples.
Claude 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 environment — see shared/managed-agents-self-hosted-sandboxes.md). You supply an a. Use it to ground design choices in named patterns, trade-offs and examples.
Every session has a live trace view in the Anthropic Console at https://platform.claude.com/workspaces/{workspace}/sessions/{session id}. Print this URL immediately after creating a session so the user can watch tool calls and messages stream in real time. {workspace} is th. Use it to ground design choices in named patterns, trade-offs and examples.
This 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 content was last updated. Use it to ground design choices in named patterns, trade-offs and examples.
This 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-tool mechanics and code examples, see tool-use-concepts.md and the language-spe. Use it as a repeatable review, validation or hardening pass.
Use with options() to override client settings for a single call without mutating the client:. Use it as a repeatable review, validation or hardening pass.
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation. Use it to make implementation decisions and avoid common dead ends.