planning-with-files
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
orchestrate
Workflow orchestrator. Builds task queue from input, dispatches subagents, manages completion.
spawn
How to spawn subagents correctly. Use this reference when you need to delegate work to a specialized agent.
agent-teams-workflow
Coordinate agent teams for multi-domain collaborative implementation from a design doc or plan
ctx
View and manage hierarchical context for the current directory
debug
Systematic debugging workflow with root cause verification before fixing
develop
PR-based development workflow with SE team simulation
distill
Distill session episodes into persistent memory patterns
implement
Auto-started default workflow. Overridden by iterate, debug, or orchestrate when invoked.
iterate
Autonomous TDD implementation workflow with phase gates.
parallel-orchestrate
Orchestrate N independent TDD subagents from a YAML task manifest with worktree isolation
pipeline
Full pipeline from design doc through plan, manifest, parallel orchestration, to branch completion
plan-to-manifest
Translate a superpowers implementation plan into a parallel orchestration YAML manifest
poll
Controlled polling for async operations at specified intervals
pr-comment
PR review comment workflow - understand the concern before fixing
remember
Save a learning to persistent memory with automatic scope inference
teams-develop
Full PR-based development lifecycle using native Claude Code teams — PM coordinates specialized agents through intake, research, design, implement, review, integrate, and complete phases
verify
Run code quality checks (ruff, black, mypy, pytest)
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 AI Agent's capabilities with specialized knowledge, workflows, or tool integrations.
context-daddy
Context management tools for Claude Code - provides intelligent codebase mapping with Python, Rust, and C++ parsing, duplicate detection, and MCP-powered symbol queries. Use this skill when working with large codebases that need automated indexing and context management.
ui-ux-design
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work.
context7
Documentation lookup via Context7 REST API. Use when the user needs current library APIs, framework patterns, migration guidance, or official code examples for React, Next.js, Prisma, Express, Vue, Angular, Svelte, or other npm/PyPI packages. Use when the user says 'how do I use X library', 'what's the API for Y', or asks for official documentation.
github-navigator
GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any `github.com` URL or GitHub repo path like `owner/repo`. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR', 'clone repo', or 'analyze this repo'.
maven-tools
JVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, JVM library versions, safe upgrades, CVEs, license risks, release history, or project dependency health. Use when reviewing `pom.xml`, `build.gradle`, `build.gradle.kts`, or Maven coordinates. Use when the user says 'check my dependencies', 'should I upgrade X', or 'is this version safe'.
skill-crafting
Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'build a skill', 'fix my skill', 'skill not working', 'analyze my skill', 'validate skill', 'audit my skills', 'check character budget', 'create a skill from this session', 'turn this into a skill', 'make this reusable', 'can this become a skill', 'should this be a skill', or asks for reusable patterns in the session.
git-operator
Rules and procedures for Git operations (add, branch, commit, push). Use when performing git add, git commit, git push, or creating branches.
github-issue-commenter
Posts work report comments to GitHub Issues or PRs using gh CLI. Use when reporting completed work, posting progress updates, summarizing changes made in a session, or adding structured comments to issues or PRs. Also use when the user says "issue にコメントして", "作業報告して", or "進捗を報告して".
github-issue-creator
Creates GitHub issues using gh CLI. Use when creating new issues.
github-pr-creator
GitHub CLI で Pull Request を作成する。実装完了後や変更 push 後に PR を提出したい時に使用する。
github-project-operator
Manages GitHub Projects v2 write operations using gh CLI. Use when adding issues or PRs to a project, creating tasks (issues) in a project, updating field values (Status, Priority, Size, Sprint, etc.), creating draft issues, creating fields, or archiving items. Also use at the start of a session when selecting a project to work with.
github-project-reporter
Reads and analyzes GitHub Projects v2 data using gh CLI. Use when listing items by status, extracting high-priority tasks, generating sprint progress summaries, detecting blockers or health issues (unassigned items, overdue items, WIP excess), or producing progress reports.
github-sub-issue-creator
Creates GitHub sub-issues and links them to parent issues using gh CLI and REST API. Use when creating child issues, breaking down large issues into smaller tasks, or establishing parent-child relationships between issues.
project-charter-creator
Use this skill whenever the user wants to create, draft, or improve a Project Charter. Triggers include: any mention of 'project charter', 'charter', 'プロジェクト憲章', 'プロジェクトチャーター', 'プロジェクト企画書', or requests to formally authorize a project, define project scope and objectives, align stakeholders, or establish project governance. Also use when the user says 'プロジェクトの立ち上げ', 'プロジェクトの認可', 'キックオフ文書', or mentions needing to get sponsor approval for a project. This skill covers project charters for any methodology (Waterfall, Agile, Lean Six Sigma) and any domain (IT, construction, marketing, organizational change, product development, etc.). Use this skill even if the user just says 'help me start a project' or 'I need to get alignment on my project'.
project-plan-creator
Creates project management plans in Markdown. Use when creating project plans, defining how to manage scope/schedule/risk/communication, or detailing project execution strategy. Primarily for internal projects that build systems, processes, or organizational capabilities.
rfi-creator
Use this skill whenever the user wants to create, draft, or improve a Request for Information (RFI) document. Triggers include: any mention of 'RFI', 'Request for Information', 'information request to vendors', '情報提供依頼書', 'ベンダー情報収集', or requests to explore what vendors or solutions exist in a market before issuing an RFP. Also use when the user wants to compare vendor capabilities at an exploratory stage, gather market intelligence, or create a shortlist of potential suppliers. This skill covers RFIs for any domain: IT systems, SaaS, consulting, construction procurement, marketing, and more. Do NOT use this skill for RFPs (detailed proposal requests with requirements and pricing) or RFQs (pricing-only requests) — use the rfp skill for RFPs instead. If the user is unsure whether they need an RFI or RFP, help them decide based on how well-defined their requirements are.
rfp-creator
Use this skill whenever the user wants to create, draft, or improve a Request for Proposal (RFP) document. Triggers include: any mention of 'RFP', 'Request for Proposal', 'proposal request', 'vendor selection document', 'procurement document', or requests to create documents for soliciting bids from vendors/suppliers. Also use when the user mentions '提案依頼書' (Japanese RFP), 'ベンダー選定', or similar procurement-related document creation in any language. This skill covers RFPs for any domain: IT systems, construction, marketing, consulting, software development, MDM, ERP, and more. Use this skill even if the user just says 'help me write an RFP' or 'I need to compare vendors for a project'. Do NOT use for RFP *responses* (vendor-side proposal writing) or general report/memo creation.
self-critique
Analyze your own previous response with rigorous self-critique
create-skill
Guide for authoring agent skills. Use when creating new skills, writing SKILL.md files, or improving existing skills.
dotnet-file-based-apps
Creates .NET file-based apps from single C# files. Use when building scripts, utilities, or small applications without project files.
address-review-comments
Addresses PR review comments systematically. Use when fixing review feedback, responding to code review threads, or processing PR comments.
azure-pipelines-tasks
Finds Azure Pipelines task implementation source code. Use when investigating task behavior, debugging pipeline issues, or understanding how built-in tasks work.
commit
Creates logical git commits from working tree changes. Use when finishing work, saving progress, or organizing changes into commits.
csharp-review
An agent designed to assist with software development tasks for C#/.NET projects.
ghostty-config
Edits Ghostty terminal configuration. Use when configuring fonts, colors, keybindings, or appearance in Ghostty.
github-actions-composite
Creates GitHub Actions composite actions. Use when building reusable action.yml files, integrating github-script, or setting up action inputs/outputs.
nuget-manager
Manage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updating NuGet package versions. It enforces using `dotnet` CLI for package management and provides strict procedures for direct file edits only when updating versions.
open-pull-request
Drafts and submits pull requests via gh CLI. Use when opening PRs, writing PR descriptions, or submitting code for review.
prompt-engineering
Techniques for writing effective LLM prompts. Use when crafting system prompts, optimizing agent instructions, or improving model outputs.
ansible-patterns
Ansible playbook patterns - simplicity, external files, system compatibility
nuxt-patterns
Nuxt development patterns - validation, error handling, code organization, state management
Page 1131 of 1445 · 72242 results