tasks-generator
Generate structured task roadmaps from project specifications. Use when the user asks to create tasks, sprint plans, roadmaps, or work breakdowns based on PRD (Product Requirements Document), Tech Specs, or UI/UX specs. Triggers include requests like "generate tasks from PRD", "create sprint plan", "break down this spec into tasks", "create a roadmap", or "plan the implementation".
agile-planning
Generate agile release plans with sprints and roadmaps using unique sprint codes. Use when creating sprint schedules, product roadmaps, release planning, or when user mentions agile planning, sprints, roadmap, or release plans.
writing-data
Use this skill when you need to structure data in `srs/data` for the Next.js app
writing-lib-functions
Use this skill when you need to write lib functions in `srs/lib` for the Next.js app
writing-page-layout
Use this skill when you need to write code for a page layout in the Next.js
writing-types
Use this skill when you need to write types and interfaces in `srs/types` for the Next.js app
writing-utils
Use this skill when you need to write utility functions for the Next.js app
reporting-sprints
Use this skill when you need to report on a sprint
coding-with-tailiwnd
Use this skill when you need to code with tailwind css
reporting-issues
Use this skill when you need to report on a troubleshooting session
setup
Setup instructions for this project
tdd-vitest-typescript
Test-Driven Development (TDD) using Vitest and TypeScript. Use when the user requests help with TDD, writing tests before code, test-first development, Vitest test setup, TypeScript testing patterns, unit testing, integration testing, or following the Red-Green-Refactor cycle with Vitest.
designing-components
Use this skill when you need to design a component
architecture-analysis
Comprehensive frontend architecture analyzer that identifies technology stacks, build tools, and architectural patterns. Use when you need to quickly understand a project's structure, dependencies, and technical configuration. Provides analysis for Vue/React/Angular frameworks, Node.js environments, package managers, TypeScript usage, linters, and architecture patterns with multiple output formats including executive summaries and visualizations.
unit-test-generator
Intelligent unit test generator for frontend projects that detects existing test frameworks and generates comprehensive tests for functions, components, and modules. Use when you need to: (1) Add unit tests to existing codebases, (2) Set up testing infrastructure for new projects, (3) Generate test cases for specific functions or components, (4) Ensure architectural consistency in testing approach across projects. Supports Jest, Vitest, Mocha with React, Vue, Angular frameworks.
dependency-analysis
Enhanced dependency analyzer with comprehensive markdown reporting and actionable recommendations. Use when you need to optimize frontend project dependencies, detect security vulnerabilities, identify unused packages, find duplicate functionality, analyze dependency impact, generate cleanup scripts, or produce detailed Markdown reports. Supports JavaScript, TypeScript, Vue, React, Angular, and modern build tools with parallel processing and incremental analysis capabilities.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
test-executor
Runs tests for Go and Node/Bun projects, interprets failures, and reports coverage against this user's targets. Use when asked to run or fix tests, or when a change needs verification before being called done. Do not use to read or write test files.
journal-manager
Writes and maintains work journals under WORK/ in the Obsidian vault. Use after an experiment or analysis produces a reading that has no permanent home yet, and when consolidating or promoting existing journals. Do not use for ordinary implementation work, progress logs, or findings that already have a destination.
handoff
Session migration for context corruption recovery. Writes a fact-based handoff file so work can continue in a fresh session, or resumes from one. Manual trigger only (`/handoff`). Use when a session shows confabulation (phantom instructions, derailed context) and the user wants to move to a clean session instead of rewinding.
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
code-reviewer
Reviews a diff against this user's standards, above all whether a fix addresses the violated invariant or only silences its symptom. Use when the user asks for a review, before creating a PR, or when re-checking a diff that answers earlier review findings. Do not use after ordinary edits, and do not use for routine branch review — the built-in /code-review covers that.
context-compactor
Analyzes and compacts context-affecting documents (project memory, CLAUDE.md, skill files) to reduce token usage and compaction frequency. Manual trigger only. Always requires user approval before making changes.
doc-rules
Documentation rules — what earns a place on the page, plus structure, length, style, and how-to writing. Use when writing or revising a README, CLAUDE.md, INSTALL, how-to, design note, knowledge entry or release note, or when asked to review prose for AI-tone or trim it down. Do not use for code comments or commit messages in ordinary edits.
git-commit-assistant
Stages and commits changes safely in any repository. Use when the user asks to commit, or when a commit would include untracked or sensitive files (credentials, MCP configs, personal settings). Writes Conventional Commits messages with a Japanese explanation. Do not use to merely inspect git status or a diff.
release-assistant
Runs the release workflow for Node/Bun and Go projects — version bump from commit history, mandatory lint/build/test, then tag creation and push. Use when the user asks to release, cut a version, or publish a tag. Do not use for ordinary commits or for merging to main.
knowledge-manager
Records and retrieves the AI_KNOWLEDGE base in the Obsidian vault (patterns, troubleshooting, best practices). Use when a non-obvious finding is worth reusing across projects, when entering an unfamiliar technical area, or when the user asks to record knowledge. Do not use for findings that belong in the repository itself or in project memory.
beads-issue-tracking
Track complex, multi-session work with dependency graphs using beads (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
obsidian-vault-manager
Manage Obsidian knowledge base - capture ideas, YouTube videos, articles, repositories, create study guides, publish to GitHub Pages, and share notes via URL (no server storage). Use smart AI tagging for automatic organization.
brainstorming
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
shadcn-ui-designer
Design and build modern UI components and pages using shadcn/ui. Creates clean, accessible interfaces with Tailwind CSS following shadcn principles. Use when building UI components, pages, forms, dashboards, or any interface work.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
expo-ios-designing
Designs modern, clean iOS screens and components for Expo React Native apps following Apple HIG with safe areas, Dynamic Type, dark mode, accessibility, Liquid Glass materials, and App Store readiness.
article-extractor
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
stock-ui
Stock analysis UI frontend. React + TypeScript with Tailwind CSS, shadcn/ui, Recharts. Use for React components, API integration, routing, state management, styling, charts visualization.
data-skill
본 스킬은 대한민국 공공데이터포털(https://www.data.go.kr/)에서 제공하는 각종 공공데이터 API 를 사용하기 위한 설명입니다. 본 스킬은 공공데이터 개발 또는 공공 API 개발을 할 때 사용하면 됩니다.
odr-index
Build or rebuild the ODR index and dependency graph in AgentDB (strict mode — unified MADR DCAP: 6 required + 3 optional frontmatter keys, MADR body spine, matching odr-create / odr-review)
diagramming
Create professional diagrams using Mermaid or DOT/Graphviz. Mermaid for flowcharts, sequences, classes, ER, Gantt, architecture with semantic coloring and WCAG AA accessibility. DOT/Graphviz for pure network graphs, semantic webs, and maximum layout control.
odr-review
Lint ODR frontmatter, section structure, and references against the DCAP profile
owl
Design and implement OWL 2 ontologies for knowledge representation. Covers RDFS foundations, OWL profiles (EL, QL, RL), class expressions, property characteristics, reasoning patterns, SKOS taxonomies, and the evolving shift toward SHACL. Informed by Kurt Cagle's ontologist perspective.
dot-export
Export DOT/Graphviz diagrams from documents to PNG images (default) or SVG. Use after creating documents with DOT code blocks when you need to render them as static images for distribution, GitHub, wikis, or static sites. Supports multiple layout engines (dot, neato, circo, fdp, twopi, osage, patchwork). Processes .md, .html, .mdx, .rst, .adoc files.
adr-index
Build or rebuild the ADR index and dependency graph in AgentDB (strict mode — Phase 3 corpus, ADR- prefix filenames, no legacy fallbacks)
odr-create
Create a new Ontology Decision Record (ODR) with sequential numbering and AgentDB registration
shacl
Design, implement, and validate RDF data with SHACL (Shapes Constraint Language). Covers node shapes, property shapes, constraint components, validation reports, SHACL-SPARQL integration, AI/LLM patterns, UI generation, and taxonomy integration. Informed by Kurt Cagle's ontologist perspective and W3C specifications.
ruflo-source-patch
Fixes ruflo/@claude-flow's .claude-flow/.swarm folder + daemon proliferation (ruvnet/ruflo#2633) by patching the cwd-anchoring defect at its SOURCE in the installed npm library, and keeping it patched every session. Use when asked to "fix ruflo daemon sprawl", "stop .claude-flow proliferation", "patch ruflo cwd", "install ruflo source patch", or "uninstall ruflo source patch". Explicit triggers: /ruflo-source-patch-install, /ruflo-source-patch-uninstall.
mermaid-export
Export Mermaid diagrams from documents to PNG images. MUST be run immediately after creating or editing any Mermaid diagram, BEFORE committing. Processes .md, .html, .mdx, .rst, .adoc files.
qlever
Query, configure, and optimize QLever—the high-performance open-source RDF triplestore. Covers SPARQL queries, GeoSPARQL, text search, CLI operations, and public endpoints. Informed by Kurt Cagle's semantic web expertise.
notebook
Create professional Jupyter notebooks with zero-execution styling using markdown-based CSS and HTML components following Airbnb DLS principles.
adr-create
Create a new Architecture Decision Record with sequential numbering (ADR- prefixed filename) and AgentDB registration
council
Convene a dialectic expert-panel review (the Linked Data Council Hive) on an ontology/ADR/ODR proposition or a set of outstanding questions, then produce a session record. Use when a modelling decision has a credible split, a contested mapping or identity-criterion question needs adjudicating, or a precedent needs recording. Spawns a SCOPED panel via the Agent tool (Queen + Devil's Advocate + only the relevant experts), collects per-question verdicts, writes the synthesis, and routes dispositions to the ODRs/ADRs.
Page 1390 of 1713 · 85633 results
