Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Config-first setup wizard for a remindb MCP server — run it as `/remindb-setup` (interactive), `/remindb-setup automode` (hands-off), or `/remindb-setup only-config` (bridge hosts: author `.remindb/` only, no env wiring). Two passes. First-time (no server attached yet): detect the host, author the `.remindb/` config (ignore/pinned/temperatures/config.json) BEFORE compiling, compile the source, seed adjacent context, install the MCP plugin, then wire the MCP env. Verify (server attached): MemoryStats + `remindb://doctor`, reconfigure, and reseed onto existing nodes. Use on first-time workspace memory setup, when remindb tools are missing/misconfigured, on "no results"/wrong-workspace symptoms, to reconfigure an existing brain, or for bridge hosts that own env wiring externally (e.g. Hermes Agent).
Use for anything involving a roadmap (a phased multi-checkpoint plan tracked with markdown checkboxes under docs/<feature-slug>/) — creating one for a task too large for a single spec/plan (“roadmap”/“дорожная карта”, multi-week migration, multi-release rollout, phased rewrite), a generic “let's continue the roadmap” request that doesn't say whether that means documentation or implementation, taking the next unfinished checkpoint (“возьми следующую задачу в роадмапе”, “take the next roadmap task”, “next roadmap checkpoint”), or batch-drafting and validating several of its steps' specs/plans at once (“напиши несколько планов”, “пройтись по роадмапу”, “на все задачи роадмапа”). This skill is the single entry point for all of that — it reads the situation and routes to the right reference file itself
Restores full context when user says "hi-ai" or starts a new conversation. Searches project files, loads memory indexes, reads session state, and creates visual dashboard showing current project, recent decisions, active blockers, and quick actions. Use when user says "hi-ai", "continue", "restore context", or starts a fresh conversation.
Orchestrate any code change from requirements to review-ready branch — scope-calibrated from small fixes to full features. Composes /spec, /implement, and /research with depth that scales to the task: lightweight spec and direct implementation for bug fixes and config changes, full rigor for features. Produces tested, locally reviewed, documented code on a feature branch. The developer pushes the branch and creates the PR. Use for ALL implementation work regardless of perceived scope — the workflow adapts depth, never skips phases. Triggers: ship, ship it, feature development, implement end to end, spec to PR, implement this, fix this, let's implement, let's go with that, build this, make the change, full stack implementation, autonomous development.
Creates, audits, and consolidates Agent Skills that follow the Agent Skills open standard, and hands back a drafted or repaired skill with the review checklist for its branch applied. Use for "create a skill", "draft a SKILL.md", "package this expertise as a skill", "why does this skill never trigger", "audit this SKILL.md", "improve this skill", or merging overlapping skills into fewer deeper modules. Covers frontmatter, descriptions that trigger, progressive disclosure, completion criteria, and bundled scripts.
Create or refactor Ship Faster-style skills (SKILL.md + references/ + scripts/). Use when adding a new skill, tightening trigger descriptions, splitting long docs into references, defining artifact-first I/O contracts, or packaging/validating a skill.
Guide creating and reviewing skills that extend Claude with specialized knowledge, workflows, or tool integrations. Covers SKILL.md structure, frontmatter quality, trigger design, eval pipelines, and packaging. Triggers on create a skill, review this skill, new skill, optimize skill, skill quality.
Design, build, and maintain standalone AI skills from a canonical source package, with prose for judgment and declared tools for exact work, built deterministically into skill folders. Use when creating, changing, splitting, testing, or delivering an AI skill as a source package (`skill-package.json`), including starting a project's first one, or when a built skill's delivery or evidence is in question.
Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements. Runs quick_validate.py, checks line limits, verifies cross-references, and tests hook scripts. Use when skills have been added or modified and you want to verify everything passes before committing or submitting.
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.
Write approved implementation plans in one of two modes. Explicit Inline mode creates a conversational plan for bounded work. Spec-backed Plan converts an approved design.md into plan.json. Both modes stop after producing their plan output. Trigger after atelier-orchestrator selects a mode, when the user asks to plan work, or after spec-brainstorm completes. Direct invocation without a selected mode uses Spec-backed Plan. Do NOT use for research or execution.
Diagnose and operate Spring AI projects with version-aware Maven or Gradle checks for ChatClient, advisors, retrieval, conversation memory, tool/MCP boundaries, streaming, configuration, and observability. Use for setup compatibility, local smoke checks, and failure triage; do not use for provider-specific model evaluation, general Java/Spring development, security threat modeling, or production rollout governance.
Manage tasks on the Squad board. Supports task CRUD (add, edit, move, complete, cancel, reopen, remove), board viewing, session context persistence, and statistics. For pipeline orchestration use /squad-run, for requirements refinement use /squad-refine. Run /squad-init first to register the project.
Agent development workflow and discipline skills. Use when developing features, debugging issues, managing code branches, writing plans, or ensuring code quality through TDD and systematic processes. Triggers on any software development task that benefits from structured workflows.
Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.
Create, refactor, audit, and maintain a multi-agent TASK-PLAN v2 as a canonical Markdown control document with a pre-implementation feature gate, sequential per-task agent orchestration, explicit test/review/rollback fields, wiki sync rules, and a derived HTML dashboard contract. Use when Codex needs to turn loose plans or checklists into structured planning docs, add agent handoff contracts, prepare plans for Codex, Claude Code, Gemini, or Antigravity, or keep Markdown as the source of truth and HTML as a generated dashboard.
TRIGGER for `.flow` / `.flow.ts` files and UiPath Flow / Maestro Flow / Maestro Automate requests: build, edit, run, debug, fix, or evaluate a flow. Author with the TypeScript builder SDK (`@uipath/maestro-builder-sdk`): nodes, triggers, schedules, connectors, IXP document extraction (add or list IXP models), inline agents, HITL, chat/voice flows, bindings, brownfield edits, and the check/compile/validate loop. Operate: upload, publish, deploy, debug a real run, trigger a process, job status/traces, pause/resume/cancel/retry an instance. Diagnose: faulted runs, incidents, runtime variables, why validate passed but the run failed. Evaluate: eval sets, evaluators, simulations, eval runs. Case plans (`caseplan.case` / `caseplan.json`) → uipath-maestro-case; BPMN (`.bpmn`, `.bpmn.ts`) → uipath-maestro-bpmn. DO NOT TRIGGER for raw IXP labelling or prompt tuning outside a Flow → uipath-ixp; standalone agents → uipath-agents; C#/XAML → uipath-rpa
Create concise handoff artifacts for moving work between agent sessions, coding agents, or tools such as Codex and Claude Code. Use when pausing work, switching agents, splitting work across sessions, preserving current state, pointing to specs/plans/evidence, or preparing the next agent to continue without copying the whole conversation.
All network operations must be handled through this skill, including: searching, web scraping, post-login operations, dynamic page interaction, and more. Trigger scenarios: the user asks to search for information, view web page content, access sites requiring login, operate web interfaces, scrape social media content (Xiaohongshu, Weibo, Twitter, etc.), read dynamically rendered pages, and any network task requiring a real browser environment.
Generative multi-approach design or solution panel. Generates N independent candidate solutions from different angles (MVP-first, risk-first, user-first, performance-first, etc.), has parallel judges score them on multiple dimensions against re-read evidence, then synthesizes the winner by grafting the best ideas from the losers. Use for "which approach?", architecture decisions, design problems, "best way to implement X". Settles by direct oracle / throwaway prototype before convening the panel where possible. Invoke via /work-judge.
Implement a task N ways in parallel and pick the best — by OUTCOME, not by pitch. Spawns N sub-agents in isolated git worktrees, each from a DISTINCT angle, gates every candidate through a per-candidate oracle (build + typecheck + test + lint), grades survivors from the ACTUAL diff (never the self-report), runs a completeness sweep on the winner, applies it to main, and re-verifies the oracle green before declaring a winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/work-tournament", or "/bon".
Personal solo-dev coding workflow, run only on an explicit "workflow COMMAND" or "/workflow COMMAND" message; never on casual mentions of brainstorm, plan, execute, review or learn elsewhere in a message. Commands: brainstorm, improve, plan, execute, review, park, wrap, status, next, learn, log, todo, bootstrap, realign; bare "workflow" = next.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Use when the user wants to build, initialize, validate, optimize, or refactor a model-powered assistant, internal tool, automation, evaluator, or workflow from a business scenario or common problem statement, including project-structure refactors or starter skeletons that may separate model setup, prompt config, and orchestration, even if the request also mentions a UI, app shell, or local model service such as Ollama, and it is still unclear whether the solution should stay a single request, add supporting capabilities, or become orchestration. The user does not need to mention Agently explicitly.
Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Route Arduino and embedded-system requests across Arduino IDE, Arduino CLI, PlatformIO, and vendor-specific tools. Use when a request combines firmware, board constraints, electronics, power, networking, calibration, enclosure, upload, debugging, OTA, or maintenance, or when the exact board or toolchain is not yet clear.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
百度网盘(Baidu Drive)文件管理与正文能力 — 上传、下载、转存、分享、搜索文件、搜索正文片段、读取文件全文、移动、复制、重命名、创建文件夹；查询网盘容量、已用和剩余空间。 同时支持 Agent 记忆备份/恢复（kimiclaw/maxclaw/qclaw/openclaw）。 TRIGGER: 用户提及"百度网盘/bdpan/网盘/云盘/baidu drive/Baidu Drive"并涉及文件操作或查询网盘容量、剩余空间、使用率； 或用户提及"备份记忆"、"恢复记忆"、"查看记忆备份"等记忆相关操作。 DO NOT TRIGGER: 非文件存储操作，或使用其他云盘服务时；本地记忆整理/清理操作；PPT 生成操作（已独立为 baidu-wenku-aippt skill）。
You MUST use this before any creative work — creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using research-validated prompt patterns.
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.