Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
This skill should be used when implementing features from Linear issues with full TDD workflow, automated planning, parallel code reviews (security and Rails best practices), systematic feedback implementation, and automated PR creation with Linear integration. Use when the user provides a Linear issue ID (e.g., "TRA-9", "DEV-123") and wants a complete implementation workflow from issue to PR.
Run parallel reviewer subagents across a target repo or diff to surface findings across correctness, security, maintainability, performance, tests, dead code, and dependency health, dedup them against a persistent ledger and Linear, then triage survivors into Linear tickets. Use when the user wants a code review, repo health audit, or to turn review findings into tickets.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Expert guidance for building MCP (Model Context Protocol) servers using the TypeScript SDK. Use when developing MCP servers, implementing tools/resources/prompts, or working with the @modelcontextprotocol/sdk package. Covers server initialization, request handlers, Zod schemas, error handling, and JSON-RPC patterns.
Molten OS Core — manage agent skills with the skills.sh CLI (`npx skills`). Use to install, add, update, upgrade, remove, list, or find skills, restore from a lockfile, or scaffold a new skill. Trigger when the user mentions skills.sh, the skills CLI, `npx skills`, or asks to add/install/update/remove/list skills.
(NS) Create or improve project-local agent skills in a NextStage harness project — draft SKILL.md under .agents/skills/, run evals, then harness sync. Use whenever the user asks to create a skill, add a custom skill to this project, author SKILL.md, iterate on skill evals/benchmarks, or optimize skill descriptions — even if they say "make a skill for our repo" or "skill-creator". Do NOT use for contributing to the nextstage-brasil/skills catalog (that repo has its own maintainer workflow in AGENTS.md).
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Run a local multi-model code review through the user's OpenCode setup BEFORE a pull request is opened. Use this right after finishing an implementation or bug fix in Claude Code, while the changes are still local — uncommitted, or committed on a branch but not yet turned into a PR — and the user wants an independent review pass before pushing. Trigger whenever the user says things like "review my changes", "review before I open the PR", "run the opencode review", "multi-model review", "review this diff", "second opinion on this", or asks for a pre-PR review of work that was just completed, even if they don't name OpenCode explicitly. Returns a consolidated review report on stdout for Claude Code to act on. Do NOT use this for reviewing an already-open GitHub PR — that path is handled interactively in the OpenCode TUI and uses gh.
Use when auditing, trimming, or restructuring AI instruction files (CLAUDE.md, SKILL.md, AGENTS.md) to reduce context-window consumption. Trigger whenever CLAUDE.md is bloated or Claude ignores instructions, a SKILL.md exceeds 120 lines, skills share duplicated content, AGENTS.md has large inline blocks, or the user asks to optimize, slim down, or reduce token usage.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Diagnose why Claude Code is (or isn't) prompting for permission. By default reads only repo-local layers (CLI project, CLI project-local, VSCode workspace). Host-global layers (CLI user `~/.claude/`, VSCode user settings) are read ONLY when the user explicitly confirms — those files may contain unrelated paths or secrets. Use when user says "why is it asking me to approve?", "permission check", "why am I getting prompts?", "bypass isn't working", "check my permissions". Read-only diagnostic.
Use when working in one of the *-polite-mcp personal automation repos (olx-polite-mcp, emag-polite-mcp, altex-polite-mcp, freshful-polite-mcp, temu-polite-mcp) or product-research-pipeline — implementing a new tool, running a live spike/CDP exploration against a real logged-in site, deciding whether an action needs confirmation before running it, or asking the user for several small per-item decisions (quantities, yes/no per item) during a reorder/shopping flow. Covers: confirming before the first live mutating action against a real personal account, batching interactive AskUserQuestion decisions instead of asking for a typed list, and writing spike/research findings into PLAN.md before or alongside implementing.
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file and optionally published as a GitHub sub-issue. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets". Accepts an optional GitHub issue reference (e.g. `#123` or a full issue URL) to link the plan as a sub-issue of that PRD-epic.
Proactively find books based on the user's actual problem, obtain and read the relevant body text, turn the methods in the book into independently callable skills, then test them with a task. Use when the user is unfamiliar with a field, wants to build a workflow with the help of books, or needs to read the body text and methodological basis for an existing skill.
Recall, search, continue, or analyze past conversations. Triggers on recall phrases ("what did we discuss", "continue where we left off", "we decided"), retrospective phrases ("do a retro", "post-mortem", "what went well", "lessons learned", "find antipatterns"), and implicit signals (past-tense references, possessives without context, assumptive questions like "do you remember").
Use this skill when the user asks to "repair an agent", "audit an agent", "fix my agent", "review agent quality", "check if my agent is well-written", "diagnose agent problems", "what's wrong with this agent", "improve this agent", or "what's wrong with this agent file". Not for skills — use repair-skill.
Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.
Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal workflow. Evaluates clarity, specificity, and completeness to suggest prompt-optimizer when needed. Identifies UI design tasks for ui-analyzer and component requests for react-component-generator. Acts as intelligent skill coordinator.
Gate 0 research phase for pre-dev workflow. Dispatches 4 parallel research agents to gather codebase patterns, external best practices, framework documentation, and UX/product research BEFORE creating PRD/TRD. Outputs research.md with file:line references and user research findings.
A command guide for operating the ROCK platform with rockcli (rc): manage sandboxes, run and view agent evaluations, manage experiments, dump images, manage datasets, and more. Use when the user wants to look up rc command usage or use rockcli to start or stop sandboxes, run commands in sandboxes, transfer files, run agent evaluations, manage experiments, move images, or manage datasets.
A lightweight AI Agent harness / checkpoint-driven coding skill for strong models such as GPT-5.4 and expert users. It assumes the user has already sliced the task down to the smallest executable unit of chaos; the model decomposes, explores and pushes forward on its own, while the human keeps low-interference control through the final goal, minimal spec, restatement, checkpoints, evidence verification and write-back.
Set up a Claude Code PreCompact hook that blocks compaction until a fresh handoff exists in .agents/handoffs/, so a session reaching its context limit never loses the conversation to auto-compact. Use when the user wants automatic handoff on context-limit, or to protect long sessions from compaction data loss.
Set up the `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain docs layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills seem to lack context about the issue tracker, triage labels, or domain docs.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
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.