vscode-custom-agents
Best practices for VS Code custom agent placement rules, access control, and multi-agent design. Triggers on 'custom agent', 'agent not found', 'subagent', 'user-invokable', 'agent design', 'picker'.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
spawn-agent
Spawn a headless coding-agent CLI run (such as `agy -p`, `claude -p`, `agent -p`, or `codex exec`) for one scoped subtask. Use when the user asks to delegate…
create-skill
Guide for creating effective agent skills. Use when users want to create a new skill (or update an existing skill) that extends agent capabilities with…
interview
Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table +…
alibabacloud-agent-toolkit-install
Install Alibaba Cloud Agent Toolkit end-to-end: verify and set up prerequisites (uv, Alibaba Cloud CLI, authentication, CLI plugins, MCP Server Core, bearer…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
product-diagnosis
Diagnoses product health by cross-referencing Amplitude analytics (dashboards, charts, funnels, feedback, AI agent analytics), optionally Datadog (errors,…
extract-to-tickets
Convert transcript-extraction `extract.md` reports into an approved, deduplicated set of local tracer-bullet tickets. Use when asked to triage transcript…
workflow-callstack-simulation
Generate a source-grounded, callstack-style dry-run simulation of a workflow, procedure, algorithm, or function for a supplied scenario, showing nested frames,…
workflow-to-skill
Create a repository workflow skill as concise, dependency-driven, subagent-ready tasks with completion checks for a repeatable workflow. Use when the user asks…
context-gap-analyzer
Identify implicit context missing from a codebase that would most improve agent performance. Use whenever someone asks to audit, assess, or improve context for…
edd
Use when iterating on agent harnesses, system prompts, context pipelines, or any context artifact that will run repeatedly. Triggers on "how do I test my…
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user…
opencode-drive
Use when an agent needs to drive OpenCode with an Effect program or interact with an isolated instance
reflect
Extract learnings from today's Claude Code conversations and save them to CLAUDE.md or auto-memory. Use when asked to "reflect on today", "what did I learn…
update-instructions
Smart merge for CLAUDE.md and AGENTS.md instruction files that preserves user customizations while updating SpecWeave sections. Use after plugin refresh,…
add-ai-protection
Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses,…
renoise-setup
Set up, update, or diagnose Renoise on any agent host. Use when the user asks to install, upgrade, configure, connect, log in, check dependencies, enable the…
steward-continuity-boundary-lifecycle
Maintain stewardship protocol continuity and tool/personality boundaries. Use when a repo agent needs steward-mode threshold checks, self-model update…
validating-setup-commands
Use before creating worktrees or executing tasks - validates that CLAUDE.md defines required setup commands (install, optional postinstall) and provides clear…
ascendc-operator-code-gen
ascendc-operator-code-gen — an installable skill for AI agents, published by ascend/agent-skills.
library
Use ChatGPT Library when the user mentions their Library, asks to find or work with a Library-backed file, Site, or named file that may be in the Library, or…
maintain-space
Reconcile new evidence into existing ChatGPT Pages or a Space when the user requests upkeep. For a direct text correction, use write-page. Do not use for…
manage-schedules
Review a ChatGPT Space page and its schedules, recommend useful recurring work, and create, update, or remove scheduled automations.