phone-mockup-board
Builds a single-file HTML comparison board of interactive phone mockups shown side by side. Each phone scrolls on its own, filters and tabs actually work, tapping an item opens it in a detail phone, a colour-shade picker recolours every screen, and each phone has a caption, so a designer can screen-record the options (Loom etc.) and send them to a client. Use this whenever someone wants to compare app or mobile-web screen options, show a client several home-screen layouts, turn a sketch or Dribbble-style references into clickable phone mockups, make "three versions side by side", or prepare a design review recording. Use it even when they don't say "board", e.g. "show me 3 mobile layouts I can send the client" or "make these references into clickable phone screens".
refactor
Before refactoring, this process must be used. Through collaborative dialogue, we will explore user intent, requirements, and design solutions in depth.
character-profile
小说人物档案创建工具，帮助作者在创作小说前构建完整、结构化的人物角色档案。使用markdown格式输出，包含基本信息、外貌特征、性格特点、背景故事、人物关系、发展弧线等完整角色信息。当用户讨论小说创作、人物塑造、角色档案创建时触发此skill。
typescript-best-practices
Apply TypeScript best practices when writing or reviewing TypeScript code, including strict typing, generics, error handling, and common patterns.
offline-sync
Expert in data persistence, local-first architectures, and synchronization strategies for Capacitor/Android applications.
capacitor-android
Expert in Capacitor cross-platform development and Android native Java code for background services and battery optimization.
bcn-transport
Expert in Barcelona's transportation geography (El Prat Airport, Sants Station) and taxi sector operational patterns.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
supabase-backend
Expert in Supabase architecture, SQL optimization (PostgreSQL), and backend security (RLS) for real-time tracking systems.
swarm-discussion
|
confluence-deep-reader
Read a Confluence page and recursively explore its child pages up to 3 levels deep. Use when users want to comprehensively read a Confluence page tree, understand hierarchical documentation, or analyze content across parent and child pages.
speak-natural
>
skill-creator
>
playwright-use
>
html-presentation
>
channel-setup
Use when the user asks how to connect or configure Slack, Telegram, or Discord in KiraClaw, including which token or settings field to fill in, what platform-side setup is required, and when an engine restart is needed.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
web-navigation-strategies
Strategic navigation patterns and selector guides for thorough web exploration using Playwright MCP. Provides decision trees, navigation strategies, and site-specific selectors for reading multiple pages systematically. Use when planning how to navigate websites, determining reading depth, or finding the right selectors for Playwright MCP commands.
slack-proactive-intervention-patterns
메모리에서 7가지 개입 기회 패턴을 감지하는 지식 베이스. 조사 제안, 스케줄링, 문서화, 초안 작성, 연결 조율, 예측적 제안, 루틴 자동화 패턴의 시그널과 점수 계산 방법.
slack-memory-store
Comprehensive memory storage system for AI employees in IT companies who communicate via Slack. Automatically classifies and stores diverse information types (Slack messages, Confluence docs, emails, meetings, projects, decisions, feedback) in an organized folder structure with efficient indexing and retrieval. Use when managing or searching employee memory, storing conversations, documenting decisions, tracking projects, or organizing any work-related information.
slack-memory-retrieval
Retrieve and utilize stored memories for AI employees in Slack environments. Efficiently searches and loads relevant context (channels, users, projects, decisions, meetings) from organized memory storage to inform responses. Use this when answering questions that require historical context, user preferences, project status, or any previously stored information. Works with slack-memory-store storage system.
slack-memory-cleanup
Memory cleanup and organization skill for AI employees. Provides guidelines for detecting duplicates, fixing misclassified files, and removing stale information from memory storage.
scratch-pad
|
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
it-role-expert
Provides role-specific expertise for 26+ IT company positions. Use when responding from a specific role's perspective, providing role-based advice, or when specialized knowledge is needed for engineering, product, design, data, marketing, sales, operations, HR, legal, finance, leadership, or academic functions.
email-action-extractor
Extract actionable tasks assigned to the user from email text. Filters out informational emails (announcements, newsletters, ads, automated reports) and only processes emails with clear action requests. Handles group emails by identifying user-specific assignments.
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
managing-claude-code-meta
MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md into new projects, migrating existing CLAUDE.md content to READMEs (progressive disclosure), and auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files.
developing-opencode-meta
Build OpenCode plugins, agents, hooks, and tools. Use when creating, reviewing, or debugging OpenCode extensions. Covers plugin architecture, agent configuration, lifecycle hooks, custom tools, and distribution. Invoke PROACTIVELY when user mentions OpenCode plugins, agents, hooks, or wants to extend OpenCode functionality.
managing-skills
Install, update, list, and remove Claude Code skills. Supports GitHub repositories (user/repo), GitHub subdirectory URLs (github.com/user/repo/tree/branch/path), and .skill zip files. Use when user wants to install, add, download, update, sync, list, remove, uninstall, or delete skills.
website-screenshot
Capture screenshots of live websites and web pages via API. Use when users need to screenshot a URL, capture website previews, archive web pages, generate thumbnails of sites, or document web content. Ideal for monitoring, archiving, sharing website previews, or creating visual references of web pages.
og-image
Generate Open Graph (OG) images and social media preview cards for websites, blog posts, and products. Use when creating social share images, Twitter/X cards, LinkedIn post images, or any visual preview that appears when sharing links on social platforms. Produces properly sized images (1200x630, 1200x675, etc.) with crisp typography and professional layouts.
html-to-image
Generate crisp, high-quality images with perfect typography and precise geometric layouts using HTML/CSS. Use when creating social cards, diagrams, certificates, UI mockups, code screenshots, or any image requiring sharp text rendering, exact alignment, or vector-like precision. AI excels at designing symmetric, pixel-perfect layouts as HTML rather than generating raster images directly. Supports Tailwind CSS, Google Fonts, icon libraries, and any web-based design resource.
code-to-image
Generate beautiful code snippet images with syntax highlighting. Use when users want to share code as an image, create code screenshots for social media, documentation, or presentations. Produces crisp, syntax-highlighted code with customizable themes, window chrome, and professional styling.
strategy
>
paul-graham
|
founder-coach
|
negotiation
>
commit
Create and execute Git commits in Conventional Commits format with a required body. Use when the user asks to commit changes, write commit messages, or prepare a clean commit. Always run a pre-commit safety guard first, abort on log files or untracked high-risk binary extensions, then stage with `git add . -A`.
repo-wiki
Generate and maintain a living repo wiki, specs, PRDs, and architecture docs in .repo-wiki/ so coding agents can navigate the codebase with strong context. Use for codebase discovery, PR-driven documentation updates, module docs, architecture maps, domain models, feature specs, and deleting stale knowledge when code changes.
Manual read-only Q&A. Answer question using inspection only: no edits, writes, patches, git changes, or clarifying questions.
implement-verified
Implement, code, refactor, migrate, or delete something with an adversarial verification pass. A coder agent writes the implementation, then an independent verifier agent re-runs every check itself and must prove the stated invariant with its own command output before it ships. Use when implementing anything a green test suite can still hide a bug in — billing, credits or charging, concurrency and locking, idempotency and retries, data migrations, behavior-preserving refactors, or removing a guard.
babysit
Watch the pull request of the current branch and keep it ready to merge. Read the checks, the merge state, and the unresolved review threads on each pass. Fix a failed check and update a stale branch, then push without a question. Make the code change for a review comment, but ask before the push and before the reply. Use when a pull request is open and needs supervision until the checks pass and the reviews get an answer.
verify-gate
Runs project compile, test, and lint commands between implementation and quality review. Gates simplify-and-harden behind machine verification. If checks fail, routes back to implementation with diagnostics for a fix loop. If checks pass, signals ready for the quality pass. Use after any implementation work completes and before simplify-and-harden. Essential for the inner loop's verify step.
skill-pipeline
>
session-context
[Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corrections, failed approaches, and unresolved work. Use after the initial intent frame and before finalizing the approach, when asked to find related work, or when a concrete history gap could change the approach.
self-healing
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.
Page 1 of 1675 · 83712 results