feature-builder
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →feature-builder
Framework for making feature prioritization decisions
Complete feature development lifecycle from research to deployment. Uses Gemini Search for best practices, architecture design, Codex prototyping, comprehensive testing, and documentation generation. Full 12-stage workflow.
Эксперт feature documentation. Используй для документации функций, release notes, user guides и product documentation.
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.
Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs.
Implement feature steps using git worktrees, build and test adaptively, update implementation plan, and generate test plans. This skill should be used when ready to implement one or more steps from an implementation plan, automatically adapting to any framework, language, or project structure.
Develop features in isolated git worktrees with autonomous testing and iteration. Use when the user asks to develop a feature in a separate worktree, wants isolated feature development, or mentions working without affecting the current directory.
Merge feature branches into main using squash commits with comprehensive commit messages. Use this skill when the user requests to merge, ship, or integrate a feature branch into the main branch. The skill analyzes all commits in the feature branch to understand the full scope of changes, then creates a single squashed commit with a proper conventional commit message that summarizes the entire feature.
Implements a single task following the next → implement → check → done workflow with TDD support. Use when working on one specific task, implementing a single feature from the backlog, or following TDD red-green-refactor cycle. Triggers on 'next task', 'next feature', 'implement feature', 'work on feature', 'single task mode', 'what should I work on'.
Story orchestration with progress tracking, standardized directory structure, and validation
Plan feature implementation with technical specifications and actionable steps for solo developers
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
RICE scoring framework for ruthless feature prioritization. Evaluates features against strategic objectives, customer value, and resource constraints. Produces prioritized product roadmap with clear rationale for what to build first, defer, or kill.
Executes unattended batch processing of all pending tasks with autonomous decision-making. Use when running all tasks automatically, batch processing without supervision, completing entire feature backlog, or working on a specific task by ID. Triggers on 'run all tasks', 'complete all features', 'batch processing', 'unattended mode', 'auto-complete tasks', 'run feature'.
Creates focused feature specifications with user stories, acceptance criteria, and edge cases. Lighter than PRD, focuses on single feature implementation. Use when specifying individual features after PRD approval or for standalone feature work.
Guide iterative specification and CDC (Cahier Des Charges) creation through deep questioning, context analysis, and proactive proposals. Use this skill BEFORE feature-research to clarify requirements, identify prerequisites, define scope, and document complete specifications. Triggers when starting a new feature, task, bug fix, or refactoring and requirements need clarification.
Aggregate and analyze customer feedback from multiple sources for product insights
Process viewer comments and feedback to improve content
Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.
Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch of issues to investigate. Investigates each item BEFORE creating issues, classifies by type and priority, creates well-formed GitHub issues with proper project board integration.
Marketing and communications expertise from Elena covering last-minute requests, emergency protocols, channel selection, and timeline management for festival communications
Fetch GitHub issue details with AI analysis comment from github-actions bot, extracting structured data for architecture planning in WescoBar workflows
Fetch Linear issue and create branch
Use when user mentions a Jira issue key (e.g., PLAT-123) or needs context from Jira. Retrieves and formats issue details for PRISM agent workflows.
Fetch store leads from Google Maps using Dumpling AI API. Use this skill when the user wants to search for businesses, stores, restaurants, or any places on Google Maps.
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
Complete CI/CD video processing system. PROACTIVELY activate for: (1) GitHub Actions FFmpeg setup, (2) GitLab CI video pipelines, (3) Jenkins declarative pipelines, (4) FFmpeg caching strategies, (5) Windows runner workarounds, (6) GPU-enabled self-hosted runners, (7) Matrix builds for multi-format, (8) Artifact upload/download, (9) Video validation workflows, (10) BtbN/FFmpeg-Builds integration. Provides: YAML workflow examples, Docker container patterns, caching configuration, platform-specific solutions, debugging guides. Ensures: Fast, reliable video processing in CI/CD pipelines.
Testing toolkit for the FHIR Writing Clinical Notes specification at connectathons. Use when the user needs to test FHIR DocumentReference write operations, validate conformance with the Writing Clinical Notes spec, or participate in a FHIR connectathon for clinical notes. Includes templates, OAuth helpers, and automated test scenarios for both provider-authored and patient-asserted notes.
Use when writing or editing novels, short stories, or any fiction manuscript. Trigger on: 'write fiction', 'edit my novel', 'developmental edit', 'line edit', 'character voice', 'plot hole', 'brainstorm', or fiction writing tasks.
Validate field completeness, format correctness, and data quality for vehicle insurance CSV/Excel files.
This skill processes files containing figlet tags and replaces them with ASCII art representations. It detects and preserves comment styles (forward slash forward slash, hash, double-dash, forward slash asterisk), automatically manages Node.js dependencies, and supports 400+ fonts (defaulting to the standard font). The skill should be used when a user requests converting marked text in a file to ASCII art using figlet tag syntax, or when they want to list available fonts.
Generate ASCII art typography using pyfiglet. Use when user asks for ASCII art text, banners, headers, logo text, terminal art, or decorative typography. Curated whitelist of 24 display fonts available, agent can also use any of 500+ pyfiglet fonts.
Generate Figma mockups from wrangler specifications with hierarchical file structure and approval tracking
Extract design specifications from Figma designs using the Figma MCP server. Used during planning workflows to gather detailed design context for implementation.
Analyzes Figma designs and generates implementation-ready PRDs with detailed visual specifications. Use when user provides Figma link or uploads design screenshots. Requires Figma MCP server connection.
Extract design specifications from Figma files using MCP integration.
Pull frames/components via Figma MCP, normalize messy or non-autolayout designs, and generate faithful HTML/CSS (or Shopify Liquid) layouts with inferred spacing and responsiveness.
Generate Android Jetpack Compose UI from Figma using Figma Desktop MCP (get_metadata, get_variable_defs, create_design_system_rules, get_design_context, get_screenshot). Automatically detect icon/vector nodes in Figma, obtain SVG/path data when available, and convert icons to Android VectorDrawable XML using Android MCP Toolkit (convert-svg-to-android-drawable). Use when the user shares a Figma link/node-id and asks to implement UI in Compose from Figma.
Convert Figma designs into Flutter code through an automated workflow that extracts design metadata, generates reference code, exports assets, implements the UI, and iteratively tests until the implem
Figma MCPで取得したデザイン変数をTailwind CSS標準クラスに変換する。Figma MCPのコード生成後やデザイン実装時に自動起動。
Create FilamentPHP v4 actions with modals, confirmation, forms, and bulk operations
Create FilamentPHP v4 forms with fields, validation, sections, tabs, and relationships
Create FilamentPHP v4 infolists with entries, sections, and layouts for view pages
Create FilamentPHP v4 tables with columns, filters, sorting, search, and bulk actions
file-restructurer
Search for files and content in a codebase. Use when investigating a codebase, finding patterns, or locating specific files. Not for reading file content or simple directory listing.
Manage filesystem context for offloading large context to files, persisting state between sessions, and reducing token usage. Use when managing cross-session state or context persistence. Not for small temporary data or in-memory variables.
>
Completes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project)