Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Conduz o brainstorm da Fase 0 de um fluxo SDD/AgentSpec por interação com o usuário: explora contexto, faz perguntas de descoberta uma por vez, coleta amostras, compara 2–3 abordagens, aplica YAGNI, valida incrementalmente e gera um BRAINSTORM pronto para a fase /define. Use para ideias vagas de software, automações, agentes, produtos ou features que ainda precisam de exploração antes de formalizar requisitos; também quando o usuário pedir para transformar uma conversa, problema ou notas iniciais em um brainstorm estruturado.
Fecha um ciclo de trabalho e passa o bastão para a próxima sessão: registra o que foi feito, o que ficou pendente (separando o que está quebrado do que é melhoria), quais são os próximos passos e o que não pode quebrar — e gera um prompt de retomada que funciona sozinho, sem depender da conversa anterior. Mantém um único arquivo de handoff por feature, com cada etapa nova no topo. Use quando o usuário disser que vai parar, que o contexto está acabando, que terminou uma etapa, que quer documentar para continuar depois, ou ao final da fase de Build de um fluxo SDD.
Build a knowledge base (KB) that AI can genuinely query: organize what you know about a domain into concepts (for understanding) and recipes (for doing), with an entry point, quick lookup, and size limits that keep the material usable. Create the project index on first use and register each new domain. For legislation and standards (normative profile), record each rule’s validity, its source with SHA-256, conflicts between sources, and the rule → source → test map. Recommended before starting an SDD workflow. Content is always reviewed by a professional: AI organizes and drafts, while the person with technical responsibility is accountable for what gets recorded. Use when the user wants to teach their context to AI, catalog laws, standards, manuals or internal policies, document a process, or complains about having to explain the same things again in every conversation.
Guide for working through a Jira story efficiently by separating context gathering, immutable evidence collection, codebase exploration, human-in-the-loop specification refinement, execution planning, and implementation. Use when turning a ticket into a reliable engineering workflow instead of jumping straight to code.
Send short status descriptions in chat for long-running tasks. Use when providing periodic updates during multi-step operations, confirming task completion, or notifying users of failures. Includes automated monitoring that sends updates every 5 seconds, status message templates, and a helper function for consistent status reporting.
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the `agent-cu` CLI commands (open, snapshot, click, type, key, find, scroll, drag, batch, wait-for) instead of falling back to `open -a`, AppleScript, `osascript`, `xdotool`, `System Events`, or any other shell workaround — those can't read state back, don't verify, and are fragile across app updates. agent-cu is the canonical computer-use tool for controlling any macOS / Linux / Windows / Electron app via accessibility APIs. Trigger on prompts like "open Music and play X", "search for Y in Maps", "fill out this form", "compute in Calculator", "send a Slack message", "drag this file", "read what's in the current window", or anything where a human would click/type/look at a desktop app
Design agent-native applications where agents replace UI users as the primary actor. Use when designing MCP tools, agent-loop architectures, system prompt design, hooks policy, shared-workspace file patterns, or self-modifying agent systems.
Use when first installing Axiom, unsure which skill to use, want an overview of available skills, or need help finding the right skill for your situation — interactive onboarding that recommends skills based on your project and current focus
Expert knowledge for Azure Sre Agent development including troubleshooting, best practices, decision making, architecture & design patterns, security, configuration, integrations & coding patterns, and deployment. Use when integrating SRE Agent with DevOps/GitHub, Log Analytics/App Insights, AKS Java workloads, IaC deployments, or DR setups, and other Azure Sre Agent related development tasks. Not for Azure Monitor (use azure-monitor), Azure Service Health (use azure-service-health), Azure Reliability (use azure-reliability), Azure Resiliency (use azure-resiliency).
Translate natural-language requests about AI-agent behavior, skills, MCP tools/servers, prompts, routing, context loading, memory, hooks, plugins, permissions, delegation, portability, or other agentic-system behavior into the concrete runtime mechanism and change surface. Use when a request is phrased as what the AI should understand/do rather than how the target harness actually observes, triggers, routes, persists, or enforces that behavior
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts, and which session ran a given command in a known time window. Use when the user asks what was said, wants a session ID or original context, needs proof of what a session contained, or needs past-session runtime evidence about commands, tool calls and hook runs — query this index instead of raw-scanning transcript files. Not for Codex (use read-codex-history); with no platform or several named, start at local-conversation-history.
Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".
Run the Build phase of an SDD/AgentSpec workflow from the Brainstorm, Define, and Design Markdown files and user interactions. Use when the user wants to implement an already specified feature: read the three artifacts, extract and order the File Manifest, recommend and confirm the execution mode, change only the planned code, verify incrementally, handle drift and LLM prompts, apply the migration from the manifest to the database (with project name and ref confirmation and read-back proof), run the blocking Verify Gate from Define, and generate BUILD_REPORT_{FEATURE}.md with evidence. Requires write access to the project/code and must finish with the SDD workflow completed and the BUILD_REPORT validated.
Run the Define phase of an SDD/AgentSpec flow based on the Markdown file generated by Brainstorm and clarification interactions with the user. Extract and structure the problem, users, goals, metrics, scope, constraints, and technical context; write acceptance tests in EARS, resolve ambiguities, calculate a Clarity Score, and define an objective Verify Gate. Use after SDD Brainstorm by RDD to generate a DEFINE_{FEATURE_NAME}.md ready for the next gate.
Interview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, automation, shortcut, or any other automatable workflow. Runs a coverage-driven JTBD interview (text or voice), then exports a one-page markdown spec plus an SVG design map. Can also analyze Claude Code sessions (current or by ID) to extract workflows, subagent patterns, and skill usage, then propose new skills based on observed patterns. Use this skill whenever the user mentions analyzing a session, extracting workflows, proposing skills from past work, reviewing what tools or agents were used, or turning a session into a skill. Triggers on "analyze this session", "what skills could I build from this", "propose skills from session", "what workflows did I use", "what did I do in this session", "extract patterns", "turn this into a skill".
Desktop automation CLI for AI agents (macOS, Linux, Windows). Screenshot, click, type, scroll, drag with native Zig backend. Use this skill when automating desktop apps with computer use models (GPT-5.4, Claude). Covers the screenshot-action feedback loop, coord-map workflow, window-scoped screenshots, and system prompts for accurate clicking
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
Risk-scaled repo execution and code-evidence protocol. Skip architecture-only work, explanation, contract-preserving prose, and status. Use for contract changes, debugging, code review, implementation plans, and Git mutation; mixed tasks: only those parts.
Main entry point for the dontbesilent business toolkit. Dual mode: pre-task routing (which skill to use for your question) and post-task navigation (what to do next after a diagnosis). Triggers: /dbs, /商业, “帮我看看”, “下一步怎么走”. Main entry point for the dontbesilent business toolkit. Dual mode: pre-task routing + post-task navigation. Triggers: /dbs, /商业, “帮我看看”, “下一步怎么走”
Comprehensive threat modeling for multi-agent systems using CSA MAESTRO 7-layer framework and OWASP Multi-Agentic System Threat Modeling Guide v1.0. Systematically analyzes threats across all architectural layers from foundation models to agent ecosystems.
Gate an implementation plan BEFORE agents execute it — catch phantom paths and false reuse, not typos: read the full plan markdown and its companion JSON, reality-check every file path and reuse claim against the actual repo, challenge scope, architecture, the dependency graph, and risk and test coverage, then score each section and render an APPROVE / REVISE / REJECT verdict — runs as a forked review workflow with its own reasoning budget, isolated from the main execution flow. The verdict follows only from evidence-backed findings: never rubber-stamps a non-trivial plan and never invents findings, but a genuinely clean section is allowed to pass; read-only, never edits the plan. Use when the user asks to review or gate a plan before execution.
Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and rollout identity/fork lineage. Use when the user asks what they told Codex, wants a Session ID, or evidence of what a run did. Not for Claude Code (use read-claude-code-history); with no platform named, start at local-conversation-history.
Structured session analysis and project instruction refinement using a five-type intervention taxonomy (Correction, Repetition, Role Redirect, Frustration Escalation, Workaround) with severity scoring. Refines project instructions (CLAUDE.md, AGENTS.md) with structural language, maintains WORKING_STATE.md for crash recovery, and implements a self-reminder protocol to prevent role drift. Includes advisory-to-structural promotion for recurring gaps. Use after milestones, repeated user corrections, session restarts, crash recovery, every 5 completed tasks, or on request. Triggers on: “reflect on this session”, “why do I keep correcting you”, “update project instructions”, “session retrospective”, “crash recovery”, “context compaction”, “role drift”, “analyze my corrections”. Also relevant when noticing repeated corrections or resuming after compaction.
Expert system for designing, creating, and validating PCL skills with comprehensive domain knowledge extraction. Use when the user mentions skill creation, meta programming, domain modeling, knowledge engineering, or PCL development, or when the task involves Skill Design Principles, Skill Architecture Patterns, Quality & Validation, or Domain Analysis Template.
BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from skills is a concern, or when skill discovery quality matters.
Spec-driven feature work that freezes obligations instead of the plan: one human-reviewed plan with EARS criteria, path, entities, interface and one-way doors, then proof-backed checks, then build, then an independent Verifier. Use when the user says "tlc-spec-lean", "plan feature", "specify feature", "write the checks", "build this plan", or "verify work". Do NOT use for standalone design documents unattached to a feature, architecture decomposition analysis, or work that already has a task list or checklist to execute.
Master prompt for analyzing and generating an AGENTS.md governance system. Analyze the current project and immediately generate a root AGENTS.md and subordinate AGENTS.md files; incorporate team-specific knowledge found in the code (asymmetries, test boundaries, hard constraints, defense in depth, security boundaries) into Golden Rules with supporting evidence; and add an @AGENTS.md link to CLAUDE.md. Must run when called with “Create AGENTS.md,” “Create agent rules,” or “/agents-md.”
AI SDK for Python (the `ai` package). Use for Python model calls (LLMs, image, video, speech, embedding, transcription, reranking, or evaluation), agents, model interaction tests, tool calling, subagents, approvals, durable execution, telemetry, AI SDK UI backends, and custom providers.
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Features predictive budget monitoring, context health indicators, and priority-based retention. Use when approaching token limits or needing to preserve essential context. Complements /transcripts and PreCompact hook with proactive optimization
Agent workspace migration. Turn any project into a maintainable workspace consistent across Claude Code, Codex, and Grok by auditing rule files, identifying the source of truth, normalizing names, and generating bridges. Triggers: /dbs-agent-migration, /agent迁移, “migrate to Codex,” “migrate to Claude Code,” “migrate to Grok,” “unify AGENTS.md,” “organize skill bridges,” “my Agent workspace is a mess,” “help me unify Claude, Codex, and Grok.” Agent workspace migration. Turn any project into a maintainable Claude Code / Codex / Grok three-host workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration, /agent-migration, “migrate to Codex”, “migrate to Claude Code”, “migrate to Grok”, “fix AGENTS.md”, “organize skill bridges”
Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how is my MCP doing?", "what should I look at?", "explore my tool calls", "who uses my MCP tools?", "what are agents doing with the MCP?", or pastes an MCP analytics URL without a specific question. Offers a menu of questions, each backed by a query tool, then hands off to the focused skill.
Use the Hyper CLI to run Hyper marketing skills from a terminal. Use when the user wants to use `hyperai`, inspect live tool schemas, run a tool by its canonical name, switch connected accounts, or run marketing tools outside an MCP-native agent host.
Manage Letta AI agent fleets declaratively with a kubectl-style CLI. Use when creating, updating, or managing multiple Letta agents with shared configurations, memory blocks, tools, folders, canary deployments, multi-tenancy, and bulk operations.
Analyze any API for AI agent compatibility. Scans OpenAPI specs across 8 pillars (48 checks), scores agent-readiness 0-100, and provides prioritized fix recommendations. Use this skill when the user asks: “Is my API agent-ready?”, “Scan my API”, “Analyze my OpenAPI spec”, “What’s wrong with my API for AI agents?”, “How agent-friendly is my API?”, or wants to improve their API for AI consumption. Works with local specs and Postman collections via MCP.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.