Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos locally readable. Do not use for ordinary API/docs questions where @librarian is enough.
Prevent trivial helpers, wrapper layers, rename-only utilities, duplicate constants, and local reinvention. Enforce reuse of platform primitives, framework capabilities, shared utilities, and proven libraries. Use when adding or reviewing helper sprawl, object-vs-positional parameter decisions, arrow-vs-declaration choices, class-vs-functional design, god-file boundaries, schema-file boundaries, security/maintainability hardening, or UI structure so the agent keeps code disciplined and avoids technical debt.
Use this skill when the user asks to "commit code", "commit", "push code", "push", "commit and push", "commit changes", "push to remote", "help me commit", or "push the code up". This skill provides a standardized git commit and push workflow that automatically analyzes changes, generates commit messages that follow conventions, and performs the corresponding operations. By default, Co-authored-by is not appended; the signature is written only when the user explicitly passes --enable-co-authored-by.
When setting up commit message validation for a project. When project has commitlint.config.js or .commitlintrc files. When configuring CI/CD to enforce commit format. When extracting commit rules for LLM prompt generation. When debugging commit message rejection errors.
Create exactly one originating GitHub issue from a local specification, preserving its retrievable source identity and handing off to plan-acceptance. Use when a disk-based spec needs one source or parent issue; not for splitting work into multiple tickets.
Drop-in crypto subscription paywall for creator products (not fiat/Stripe). EVM wallet login (SIWE) + on-chain payment verification. Users sign in with their wallet, pay a monthly/yearly subscription by transferring tokens (ETH/Base/BSC, any ERC20 incl. custom tokens) to the creator's Starchild agent wallet, and get gated access — verified on-chain with no payment processor or third-party account. Use when a creator wants to add "sign up → pay → use" monetization to something they built (e.g. "add a paywall", "let users pay to subscribe", "gate my app behind a crypto payment", "收款", "订阅付费", "wallet login + subscription"). Not for fiat/Stripe, not for pay-per-use metering.
Use this skill to build, implement, and test Vizro dashboards (Phase 2). Activate when the user wants to create a working app, says "just build it", or has data ready for implementation. Requires spec files from the dashboard-design skill (Phase 1), or user confirmation to skip design.
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
Research-aligned self-consistency for debugging. Spawns independent solver agents that each explore and debug the problem from scratch. Uses majority voting. Based on "Self-Consistency Improves Chain of Thought Reasoning" (Wang et al., 2022). Use for critical bugs, algorithms, or when other approaches have failed.
Structured debug log analysis for Claude Code sessions — auto-discovers most recent log, runs reducer, extracts error patterns, correlates with full log, produces observability report. Fills 5 identified gaps: hook error body capture, agent identity, file path tracking, stall correlation, success visibility.
Use when writing or reviewing Python code in this repo that calls Deepgram Management APIs - projects, API keys, members, invites, usage, billing, models, and reusable Voice Agent configurations. Covers `client.manage.v1.projects`, project-scoped resources under `client.manage.v1.projects.*` (keys, members, members.invites, usage, billing, models, requests), global `client.manage.v1.models`, think-model discovery at `client.agent.v1.settings.think.models`, and `client.voice_agent.configurations.*`. Use `deepgram-python-voice-agent` when you want to run an agent interactively, this skill to PERSIST/LIST agent configs. Triggers include "management API", "list projects", "API keys", "members", "usage stats", "billing", "list models", "agent configurations", "manage.v1".
Use the DuskMoon CSS Art Elements (`<el-dm-art-*>` web components). Use when adding pure CSS art animations to web pages — atom, moon, sun, plasma-ball, gemini-input, synthwave-starfield, and more. Covers all 15 CSS art packages, registration patterns, size variants, and the @layer stripping technique required for Shadow DOM compatibility.
Write and rewrite textual system requirements using EARS (Easy Approach to Requirements Syntax). Use when converting ambiguous natural-language requirements into structured statements, classifying requirements into EARS patterns, or reviewing requirement quality for missing triggers, states, and measurable responses.
Use when the user provides API keys, tokens, or other configuration values that should persist across sessions, or when the user asks to query, list, or delete saved environment variables. Manages personal env by default and workspace env only when explicitly requested.
Use this skill when `biome migrate eslint` must preserve configurable ESLint rule options through source-option models, Biome conversions, typed rule variants, and migration fixtures. Do not use for generated severity-only mapping or general rule-option design.
Use when debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.
Guidance for extracting and processing data from ELF (Executable and Linkable Format) binary files. This skill should be used when tasks involve parsing ELF headers, reading program segments, extracting memory contents, or converting binary data to structured formats like JSON. Applicable to reverse engineering, binary analysis, and memory dump extraction tasks.
Build FastAPI applications using Clean Architecture principles with proper layer separation (Domain, Infrastructure, API), dependency injection, repository pattern, and comprehensive testing. Use this skill when designing or implementing Python backend services that require maintainability, testability, and scalability.
Write a feature flag management guide and lifecycle playbook for a service or team — covering flag taxonomy, creation checklist, rollout strategy, monitoring requirements, cleanup policy, and governance. Use when asked to document feature flag practices, create a flag rollout plan, write a feature flag policy, or guide a team on flag lifecycle management. Produces a flag lifecycle playbook, taxonomy reference, per-flag creation template, rollout decision tree, and cleanup checklist.
Design and audit feature request prioritization from support, sales, customer success, research, app reviews, community, analytics, and strategic accounts; covering evidence quality, segment fit, revenue risk, product strategy, effort, dependencies, fairness, duplicate clustering, communication, and close-the-loop decisions. Use when teams must decide what to build without overreacting to loud requests.
Guidance for filtering JavaScript and XSS attack vectors from HTML while preserving original formatting. This skill should be used when tasks involve removing script content, sanitizing HTML, filtering XSS payloads, or creating security filters that must preserve the original document structure unchanged.
Implement a whole backlog of tickets overnight, unattended. Give it the spec or parent issue whose build tickets you want built (or a local backlog folder); it pulls the linked tickets from the issue tracker, reads the spec and completed tickets for context, orders the open tickets by dependency, then runs one agent per ticket — each using /implement in its own git worktree, on a model matched to the ticket's difficulty, at high reasoning effort — and leaves you your chosen deliverable in the morning — a stack of reviewed branches, one integration branch, or a ready-to-review PR.
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Trigger words include: 'fix CI', 'debug GitHub Actions', 'gh pr checks', 'CI is red', 'GitHub Actions failed', 'fix the build', and similar phrases indicating a need to investigate and resolve CI failures in a GitHub-hosted repository.
Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
Run a rigorous planning interview that stress-tests a user's idea against the codebase, sharpens project terminology, and captures durable context in lightweight docs. Use when the user says "grill me", "grill me with docs", "stress-test this plan", "interview me on this design", or asks to turn a discussion into CONTEXT.md glossary entries or ADRs. Do NOT use for ordinary summaries, code review, or documentation-only cleanup when no interactive interrogation is requested.
Internationalization and localization. i18next (React, Node.js), next-intl, vue-i18n, ICU message format, pluralization, date/number formatting, and RTL support. USE WHEN: user mentions "i18n", "internationalization", "localization", "l10n", "i18next", "translation", "next-intl", "vue-i18n", "ICU format", "RTL" DO NOT USE FOR: character encoding - general programming; currency/payment formatting - use `stripe`
Technical implementation of GDPR Article 25(2) data protection by default. Covers strictest privacy settings as default configuration, minimum data collection, limited storage duration, restricted accessibility, and opt-in rather than opt-out patterns. Includes implementation checklist and system design requirements.
moomoo OpenD installation assistant. Automatically downloads and installs moomoo OpenD and upgrades the Python SDK. Supports Windows, macOS, and Linux. Triggered when the user mentions installing, downloading, launching, running, configuring OpenD, setting up the dev environment, upgrading SDK, or moomoo-api.
Update and maintain joelclaw.com — the Next.js web app at apps/web/. Use when writing blog posts, editing pages, updating the network page, changing layout/header/footer, adding components, or fixing anything on the site. Hard content triggers: 'write article about X' (draft in Convex), 'publish article <slug>' (set draft=false + revalidate tags/paths). Also triggers on: 'update the site', 'write a post', 'fix the blog', 'joelclaw.com', 'update network page', 'add a page', 'change the header', or any task involving the public-facing web app.
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.
