Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when the user needs code quality review, refactoring guidance, SOLID principles application, or help identifying and fixing code smells. Triggers: code smell detection, refactoring planning, naming convention review, complexity reduction, DRY analysis, error handling improvement.
Rules for canister code on a cloud engine (CloudEngine subnet, e.g. OpenCloud). Engine canisters hold 0 cycles: never attach cycles you computed: drop `(with cycles = …)` clauses (IC0504). Cross-subnet calls must be bounded-wait and cycle-free (`(with timeout = N)`, `Call::bounded_wait`) or rejected: 'Unbounded-wait calls and calls with cycles are not allowed to CloudEngine subnets'. HTTPS outcalls use the ordinary wrapper and are free; never via the proxy ('Replicas had different responses', InsufficientCycles). XRC, threshold ECDSA/Schnorr, vetKD, the Bitcoin API and EVM/SOL RPC (Bitcoin, Ethereum, VetKeys) go via the engine's proxy canister: before writing that code, ask the user for its id or to deploy one in the console. Hand-encode arguments: ic-vetkeys and ic-cdk chain-key helpers attach cycles. Derived keys belong to the proxy. Use when planning, writing or debugging engine canister code, signing or deriving keys, or on these errors. Do NOT use for deploying a proxy (deploy-to-cloud-engine).
This skill should be used when the user asks to "understand a codebase", "get code context", "research a library", "explore a repository", "find code examples", "look up documentation", asks a natural-language code/technology question (e.g. "how does X work", "X vs Y", "best practice for Z"), or wants to understand how a specific project, library, or concept works before making changes.
Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research prior art, reference or author it, add examples, regenerate the manifest, open a PR.
Scaffold a VeChain dApp with Next.js, VeChain Kit, Chakra UI v3, and GitHub Pages deployment. Supports standalone (frontend-only) or monorepo (Turbo + Hardhat contracts) modes. Use when creating a new VeChain project, scaffolding a dApp, setting up a VeChain frontend, or bootstrapping a VeChain monorepo.
Refactor code to reduce cyclomatic complexity so it stays readable, maintainable, and aligned with the long-term vision of the codebase, not just optimized for AI comprehension. Use whenever the user asks to refactor, simplify, clean up, or review code quality; mentions complexity, maintainability, readability, spaghetti code, deeply nested logic, or god functions; or asks to check AI-generated code before merging. Also use proactively after writing any nontrivial function with heavy branching.
"Safely deploys Move contracts to Aptos networks (devnet, testnet, mainnet) with pre-deployment verification. Triggers on: 'deploy contract', 'publish to testnet', 'deploy to mainnet', 'how to deploy', 'publish module', 'deployment checklist', 'deploy to devnet'."
Audit a codebase against well-known software design principles: SOLID, DRY, YAGNI, KISS, Law of Demeter, Separation of Concerns, Composition over Inheritance, and the code-relevant 12-Factor subset. Scores findings by impact and effort, runs adversarial debate on contested violations, and generates a prioritized DESIGN_AUDIT.md. Use when reviewing code quality beyond what linters catch, assessing design health before a refactor, or onboarding to an unfamiliar codebase. Can be invoked standalone or delegated from tech-debt.
Produces this framework's ADR and system-design artifacts from bundled templates with trade-off analysis. Use when designing a system or component, choosing between architectures, or recording an architecture decision in the planning flow.
Look up CE.SDK Vue.js reference docs, guides, and configuration pages. Use when the user needs CE.SDK docs for Vue.js — configuration, UI customization, export options, feature guides, or getting-started instructions. Also triggered by "IMG.LY", "CreativeEditor", "CE.SDK", or "cesdk" when the user needs an existing Vue.js doc page. Not for writing code (use build) or concept explanations (use explain). <example> Context: User asks about Vue.js configuration user: "How do I configure the editor in Vue.js?" assistant: "I'll use /imgly-sdk:docs-vue to look up configuration options." </example> <example> Context: User asks about Vue plugin registration user: "How do I register CE.SDK as a Vue plugin?" assistant: "Let me use /imgly-sdk:docs-vue to find the relevant documentation." </example>
Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, deletes small UI and purely mechanical records, classifies other implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
ALWAYS-ON: audits plans and code for KISS, YAGNI, DRY, SOLID, and testability; maintains .heyeddi/docs/engineering/. Use on every chat that plans or changes code, before merge, refactor, ADRs, or reuse-catalog work. Not for visual UX (ux-flow-auditor) or full CI (pre-merge-gate includes this audit).
Roadmap and delivery artifact management in Linear or GitHub. Use when creating, editing, decomposing, moving, or updating roadmaps, epics, stories, or bugs, including sizing an explicit feature PRD or feature design doc into an epic or a standalone story. Not for implementing a named story, feature documents, project overviews, or quick fixes.
Guide the agent on creating visually distinctive, polished Vaadin 25 interfaces that go beyond default theme styling. This skill should be used when the user asks to "make it look good", "improve the design", "style the view", "make it visually appealing", "add polish", "design a UI", "create a beautiful interface", or when building a new view where visual quality matters. Also trigger when the user wants to add animations, visual effects, or build polished component compositions in a Vaadin application.
Automatically stage, commit, and push with Git. Use this skill when the user asks to commit code, push code, commit, push, commit and push, auto-commit, stage-commit-push, or any operation involving git commit/push. Also applies to colloquial phrasings such as "提交一下", "推一下代码", "帮我提交", "push 上去", "仅提交", or "只 commit".
Handle GitCode PR workflow for OpenHarmony - commit changes, push to fork remote, create issue, create PR from fork to upstream using repo's .gitee/PULL_REQUEST_TEMPLATE.zh-CN.md with issue linking via #number. Use when user wants to submit/create PR or commit changes. Auto-checks if PR exists and only pushes when PR already exists.
Embed screenshots, images, diagrams, GIFs, and screen recordings in GitHub PRs and issues — or stage them ahead of a PR, collect them into one attachments comment, or get a durable public link to share a visual with a person. Use this whenever a visual needs to end up in a PR description, issue body, or PR/issue comment, in front of a teammate, or saved for a PR that doesn't exist yet. Triggers include "attach a screenshot to the PR", "add a before/after to the issue", "include a screenshot of …", "share a GIF of the flow", "record the bug and put it in the issue", "get me a link I can paste in Slack", "share a live feed of this PR's screenshots", "create a change feed", "stage screenshots for the PR", "attach this when I open the PR", "save this for the PR", "collect the PR's media", or having just captured or changed something visual that a shot would make clearer — even mid-task, before a PR exists. Also applies when an agent has no local filesystem and is uploading via the hosted MCP (agents.uploads.sh). Reach for this instead of drag-and-drop or hand-rolling cloud-storage uploads. GitHub CLI 2.99+ can attach a single image to an existing PR or issue with `gh … --attach`, and `gh issue artifact create --attach` can hold GitHub-only media on an issue plan; this skill says when that is enough and when it is not. Capture the visual with whatever browser or screenshot tooling you have; this skill covers hosting and embedding it
Use when a task involves Halo CLI, Halo CMS command-line operations, or terminal-based Halo management. Also use when you need shared rules for profiles, JSON output, help discovery, config paths, and destructive actions. Trigger this skill whenever the user mentions 'halo', 'Halo CLI', or terminal operations for Halo CMS, even if the specific command area is not yet clear.
Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler, hedging, and pleasantries while keeping code, identifiers, and technical terms exact. Use whenever writing, modifying, refactoring, reviewing, or explaining code, or any response where output volume drives token cost — even if the user never says "minimal" or "concise". Especially in agentic coding, where the volume of generated code and prose runs up the bill.
Generates implementation plans with milestones and tasks from business and technical requirements. Supports AI, human, and hybrid audiences with appropriate detail levels. Embeds best practices including task sizing (30m-2.5h), style anchors, TDD requirements, and quality constraints. Outputs milestones.yaml and milestone-m*.tasks.yaml files ready for development.
Real-time communication patterns for live updates, collaboration, and presence. Use when building chat applications, collaborative tools, live dashboards, or streaming interfaces (LLM responses, metrics). Covers SSE (server-sent events for one-way streams), WebSocket (bidirectional communication), WebRTC (peer-to-peer video/audio), CRDTs (Yjs, Automerge for conflict-free collaboration), presence patterns, offline sync, and scaling strategies. Supports Python, Rust, Go, and TypeScript.
Full-dimension log analysis skill. Automatically identifies log types (Java application / MySQL Binlog / Nginx / Trace / alerting), extracts key entities (IP, thread_id, trace_id, user, table names, etc.), and performs root cause localization, alert analysis, and anomaly insights. Supports 100M+ large files. Trigger words: analyze logs, log troubleshooting, root cause localization, alert analysis, anomaly analysis.
Guide for maintaining the MassGen model and backend registry. This skill should be used when adding new models, updating model information (release dates, pricing, context windows), or ensuring the registry stays current with provider releases. Covers both the capabilities registry and the pricing/token manager.
Run Claude Code or Codex CLI on Muapi (api.muapi.ai) using Muapi credits instead of a separate vendor account. Use when the user wants a local coding agent to use Muapi as its model provider, asks which Muapi models work with Claude Code or Codex, or needs the base URL, API key variable, provider block or model name for either agent. Covers Claude Code (Anthropic Messages) and Codex CLI (OpenAI Responses), model discovery, verification and troubleshooting.
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities. Consult this skill whenever a validate_node or validate_workflow call returns errors or warnings — it knows which warnings are false positives and which errors need real fixes.
Use for real projects that combine a Next.js frontend/BFF with a NestJS API. Covers ownership boundaries, OpenAPI client generation, session and auth propagation, CORS/proxy contracts, Server Component data fetching, shared environment contracts, and split deployment/runtime alignment.
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.