shape
Writes what a ticket needs before an agent can build it — the spec triad, or the root cause for a bug — and stops at your approval. Run it with /shape
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
adobe-reference-architecture
Define a production Adobe architecture spanning identity, service adapters, async workers, asset custody, I/O Events, App Builder, evidence, and recovery. Use…
anth-reference-architecture
Implement Claude API reference architectures for common use cases. Use when designing a Claude-powered application, choosing between direct API vs queue-based,…
mistral-migration-deep-dive
Migrate an existing model workload to Mistral through semantic mapping, dual-run evaluation, bounded canary, and provider rollback. Use when re-platforming…
validate-plugin
Validate a Claude Code plugin directory against the official Anthropic spec and Intent Solutions enterprise standard. Runs structural validation…
asking-user-questions
Use when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a…
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail…
naval-perspective
Naval Ravikant's thinking operating system. Based on in-depth research of his writings, podcasts, tweets, decision records, and external criticism, distilling 5 core mental models, 8 decision heuristics, and a complete expression DNA. Once activated, immersively role-play as Naval, responding to questions directly from the "I" perspective. When the user mentions "from Naval's perspective," "how would Naval see it," "Naval mode," "Naval...
doubao-multimodal
Async audio/video understanding with Doubao-Seed (Volcano Ark). Handles ASR (plain / per-character timestamps / multispeaker), AST translation, speaker…
claude-light
Expert assistant for conducting remote experiments with Claude-Light - a web-accessible RGB LED and spectral sensor instrument for statistics, regression,…
local-convex
Operate Joel's local self-hosted Convex setup with Central Postgres and NAS-backed Garage/S3-compatible object storage. Use when: 'local convex', 'self-hosted…
minio
Operate Joel's MinIO legacy/rollback services and S3-compatible object storage checks. Use for MinIO, ASUSTOR MinIO CE, custom Docker/Compose MinIO, Convex…
openclaw-messaging
Send messages, system events, and agent notifications through the openclaw CLI. Use when an agent needs to notify a user (Telegram, Slack, Discord), trigger…
todoist
Manage Todoist tasks, projects, comments, reminders, and activity via the todoist-cli agent CLI. Use when: 'add a task', 'what's due today', 'check my inbox',…
lore-recall
Plans and executes bounded Lore memory recall with status checks, query expansion, context drill-down, freshness labels, cited evidence packets, and…
andy-post
Draft and publish social posts through Andy MCP. Use when the user wants to post, tweet, schedule, or create an X, LinkedIn, or Instagram post; when they give…
claude-cli-runtime
Claude Code headless runtime contract. Use when a non-Claude runtime delegates one task, review, question, or one-vendor second opinion to Claude/Fable.…
shared-memory
Manage persistent cross-agent knowledge across agents, skills, and repos. Trigger to assess, retrieve, validate, or deprecate shared conventions, prompts, and…
doc-gardening
Use when writing or updating AGENTS.md, CLAUDE.md, README, or any project docs; when a change seems to "need documenting"; or when instruction files have grown…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
pua-2-0
This skill should be used when the user asks to "use PUA-style pressure", "roast the AI hard", "do a high-pressure retro", "coach the agent with profanity",…
error-recovery
Structured error classification and recovery during autonomous operation. Classify runtime errors, apply retry strategies with backoff, maintain error logs,…
context-network
Bootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or…
mastra-hono
Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers. This skill should be used when creating Mastra agents, defining tools with Zod…