Write and configure custom agent definitions in Claude Code's agents/ directory. Use when you want to create a new agent .md file, define a specialized agent with its own system prompt and tools, set up an agent with isolated context, or configure agent capabilities and restrictions in your project's .claude/ configuration.

Guide for security-related Agent Skills including penetration testing, code auditing, threat hunting, and forensics skills.

Manually write response back to Claude. Use if read-task did not auto-complete or to finalize response.

Comprehensive framework for initializing new software projects with Claude Code, implementing 2025 best practices for LLM-based software engineering including TDD, multi-agent orchestration, and session management.

E2E test skill for validation

Use when creating a new Amplifier module (tool, hook, orchestrator, context, or provider). Covers the mount() contract, protocol compliance validation, placeholder patterns, and the module directory structure. Prevents the common mistake of creating no-op mount() stubs that fail protocol_compliance validation.

Write idiomatic Zig code following the Zen of Zig philosophy. Use for systems programming with Zig (.zig files), covering manual memory management with allocators, error unions and explicit error handling, compile-time programming (comptime), data-oriented design, and the new async/Io model. Applies functional programming parallels (Result types, ADTs, explicit effects) for C-free systems development.

Map permissible values in LinkML enums to ontology terms. Use this skill when: (1) Adding or updating ontology mappings (meaning: field) for enum permissible values, (2) Fixing validation errors from linkml-term-validator, (3) User asks to map enums to ontology terms or fix CURIE mappings. This skill covers OAK/runoak lookup, CURIE verification, and validation workflows.

Write or update duplojs-utils JSDoc documentation files under jsDoc/{namespace}/{function}/, including index.md structure, @example includes, and example.ts usage patterns (classic, curried, and predicate overloads).

Train yourself to automatically structure answers using:

Review recent changes and update CLAUDE.md to keep it relevant for future sessions. Use after significant changes or periodically to maintain context.

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

Write or update duplojs-utils documentation pages (FR/EN) including API function pages, namespace index pages, and guides, following the repo's structure, MonacoTSEditor examples, required sections, and prev/next metadata.

Decision guide for choosing the right specialized agent for each task type

Run CVlization examples on the `ssh l1` GPU host by copying only the needed example directory plus the shared `cvlization/` package into `/tmp`, then launching the example’s Docker scripts.

Senior Next.js 15+/16 Engineer skill for App Router. Use when scaffolding production apps, enforcing RSC patterns, auditing codebases, or optimizing performance.

Claude Code Skills and Agent Architecture in DiPeO

View Vercel deployment logs. Use when the user says "show logs", "check logs", "vercel logs", or "what went wrong with the deployment".

Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

Sync work between AI agents. Log actions, manage sessions, detect conflicts.