skills

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

Build high-quality, animated, professional web pages that VISUALIZE software architecture, system design, data models, or a product idea — using Three.js (3D) + GSAP (scroll/animation) + SVG diagrams. Produces two things, usually together: (1) a cinematic scroll-story landing page where a 3D low-poly world narrates how a system works, and (2) an interactive architecture map with switchable overlay "lenses", clickable drill-down component diagrams, and crow's-foot ERDs. Every output ships with a built-in EDIT MODE so the human can click components / snip areas / pick 3D objects and batch visual feedback straight to you. Use this skill WHENEVER the user wants to visualize, present, "show", animate, or build an interactive page for an architecture, system design, technical concept, data model, pipeline, or product story — including phrases like "intro page", "architecture visualization", "interactive diagram", "scrollytelling", "3D system map", "ERD page", "design walkthrough", "make our architecture look impressive", or "present this design to stakeholders". Prefer this skill over hand- rolling Three.js/GSAP from scratch — it bundles battle-tested templates, a styling/anti-slop guide, a diagram-layout catalog, and an AI-tweakable code convention learned from a long real build.

Interact with Atlassian Jira and Confluence using REST APIs — no MCP server needed. Use this skill whenever the user mentions Jira, Confluence, Atlassian, tickets, issues, sprints, backlogs, epics, stories, or any project management task that involves creating/editing/searching/transitioning Jira issues, writing or reading Confluence pages, generating status reports, triaging bugs, converting specs to backlogs, capturing tasks from meeting notes, searching company knowledge, syncing local BMAD documents with Jira or Confluence, pushing docs to Jira, pulling from Jira, linking documents to tickets, downloading Confluence spaces to local markdown, or converting between Confluence storage format and markdown. Also trigger when the user says things like "move that ticket to done", "what's the status of PROJ-123", "create a bug for X", "search our wiki for Y", "file a ticket", "check for duplicates", "write a status update", "break this spec into stories", "sync this doc", "push to jira", "pull from jira", "sync to confluence", "link this to jira", "sync my epics", "download confluence pages", "sync confluence space", "convert confluence to markdown", or "pull docs from confluence". If there is even a chance the user wants to interact with Jira or Confluence, use this skill.

Orchestrates BMAD implementation workflows automatically — both the full Phase 4 epic/story pipeline and the Quick Flow for small, well-understood changes. Use this skill whenever the user wants to: (1) automate Phase 4 implementation ("auto implement", "start implementation", "begin phase 4", "automatic working on phase 4", "implement all stories", "process the epics"), (2) check implementation progress or status ("what's the status?", "how many stories are done?"), (3) resume a previously interrupted session ("continue from where we left off", "resume"), (4) implement a small self-contained change without going through full BMAD planning ("quick dev", "quick flow", "implement this change", a described bug fix, refactor, or small feature, patch). When the user describes a small change or asks to quickly implement something, route to Quick Flow — `bmad-quick-dev` handles intent-to-code directly without a separate spec step. If a multi-story project is already in flight (`sprint-status.yaml` exists) AND the user's current request is a substantive epic/story task, route to Phase 4; if the request is a small one-off, route to Quick Flow regardless. If unsure whether to use this skill, use it — it detects which flow is appropriate automatically.

Convert EPUB books to high-quality formatted Markdown using pandoc and AI-assisted formatting. Use when the user provides an EPUB file path and wants to convert it to professionally formatted Markdown, similar to the Clean Code Collection formatting. This skill handles the complete workflow from EPUB extraction through AI-driven content formatting, including fixing PDF conversion artifacts, joining split paragraphs, correcting code blocks, standardizing headers, and creating proper Table of Contents.

Bidirectional sync between BMAD planning artifacts and GitHub Projects v2. Use this skill whenever the user says "sync to github", "push stories", "pull status from github", "set up github project", "github sync", "onboard github project", "create github issues from stories", "update stories from github", "sync status", or wants to manage BMAD artifacts in GitHub Projects. Also trigger when user mentions "gh project", "github board", "sprint board", "project roadmap", "relationship field", "blocked by", or "parent issue" in the context of BMAD artifacts. Trigger on implicit cues like "I want to track stories in github", "let's set up a project board", "what's out of sync", "push the sprint to github".

Use when the user wants Jira issues pulled onto disk as local files — "pull PROJ-123", "fetch this story", "get that ticket locally", "download the bug", "save this issue and its comments", "grab the NFR", "read this ticket offline", or a pasted Jira browse URL with nothing else asked of it. Also for many at once — "sync all tickets in sprint 62", "pull every bug in the sprint", "fetch the whole backlog locally", "download all of team X's issues". Covers any issue type — story, bug, epic, subtask, or whatever types the project has invented for itself. Also when the issue links a Confluence page that should come down with it. This skill only reads: for creating, editing, transitioning, commenting, searching, or pushing anything back to Jira, use atlassian-rest instead.

Loads documents fully into the main agent's context so the agent can answer questions, summarize, or work with that content in subsequent turns. Use whenever the user wants to ingest, read, study, review, absorb, or pull in documents — especially when they say things like "load these docs", "read all of these", "ingest this folder", "pull in these PDFs", "load all docs in X", or paste a list of file paths/URLs and ask you to read them. Handles local files (text, code, markdown, PDFs, notebooks, images), entire folders (recursively), and remote URLs. The skill is single-turn — once the agent reports "DONE", it deactivates until the user invokes it again.

Use when writing, reviewing, executing, or updating manual test cases or a test plan; when asked 'how should I test this'; when restructuring an existing test suite or its layout; or after implementing a feature that changes system behavior — per CLAUDE.md, updating the manual test plan is mandatory. Covers API/backend, frontend, pipeline/workflow, AI/LLM, GUI, and infrastructure testing.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Manages git operations (branching, committing, pushing) across multi-repo systems with git submodules. Use this skill whenever the user wants to create a feature branch, commit changes, push code, sync submodules, or manage branches across the parent repo and service repos. Also use when implementing BMAD stories that touch one or more services, or when the user asks about git workflow in a multi-repo project. Triggers on phrases like "create branch", "commit changes", "push to remote", "sync submodules", "start working on story", "update service branch", or any git operation that spans parent and submodule repos.

Use when investigating and documenting a production incident, outage, data corruption event, or post-mortem — guides evidence collection during the investigation AND produces a rich, reproducible Root Cause Analysis report. Trigger on phrases like "write an RCA", "post-mortem for X", "document this incident", "what went wrong with...", "the pipeline broke yesterday, help me investigate", or any time the user is debugging a recently-resolved incident and wants a writeup. Also use proactively when the user finishes resolving an incident in-session and the resolution context is fresh — offer to capture it as an RCA before details fade.

Set up and configure Google's release-please for automated versioning, changelog generation, and publishing via GitHub Actions. Covers pipeline creation, Conventional Commits formatting, pre-release workflows, monorepo configuration, and troubleshooting release pipelines. Use this skill whenever the user wants to automate releases, set up CI/CD for publishing, configure version bumping, write release-please-compatible commit messages, tag versions automatically, publish to npm/PyPI/crates.io/Maven/Docker, or troubleshoot why a release PR wasn't created. Activate even if the user doesn't mention "release-please" by name — phrases like "automate my npm releases", "set up GitHub Actions for publishing", "how do I tag versions automatically", "changelog generation", "semver automation", or "pre-release workflow" all indicate this skill. For commit message guidance specifically, this skill focuses on release-please-compatible conventions; for broader multi-repo git operations with submodules, defer to multi-repo-git-ops instead.

Create Claude skills from book content (markdown files). Transforms long-form book knowledge into structured, context-efficient skill packages with granular reference files, workflows, and use-case guidelines. Use this skill when: - Converting a book (markdown) into a reusable Claude skill - Creating knowledge bases from technical books, guides, or documentation - Building skills that need progressive disclosure of large content - Structuring book knowledge for efficient context loading

Make impressive, on-brand presentation slides and decks end-to-end, for ANY design system. Use this skill whenever the user wants to brainstorm, build, design, generate, review, or export a slide, deck, presentation, pitch, or company/product/sales deck. It runs as job-specific WORKFLOWS: brainstorm a deck's structure, generate the HTML deck with a review loop, and export to editable PPTX, image PPTX, standalone HTML, or PDF. It is design-system-agnostic — it uses the user's own design system if they have one, a `nextlevelbuilder/ui-ux-pro-max-skill` suggestion if that's installed, or a bundled neutral default theme — and drives everything from design tokens (never hardcoded colors or fonts). It ships a token-driven brand kit (tokens, fonts, logos, 34 premade layouts), a "wow" craft guide, an anti-slop validator, a ready-made React deck template, point-and-comment edit mode, and a validated editable-PPTX pipeline. It can also supply just the design layer (tokens, components, patterns) to another slide generator so its output uses a real design system instead of a generic theme.

Generate interactive presentation slides using React + Tailwind, and export to standalone single-file HTML. Triggers on keywords like "slides", "presentation", "PPT", "demo", "benchmark", or when user requests export. Uses agent-browser skill for browser verification before export (install with `npx skills add vercel-labs/agent-browser` if not available).

Use when someone asks to research a software-engineering question through a verified, multi-perspective lens — "should we use X vs Y", "evaluate library/framework/database Z", "research whether we should adopt …", "write an ADR for …", "spike on …", or "migrate from X to Y / upgrade path". Runs a STORM-style pipeline specialized for software: auto-detects one of five research modes (library-eval, deep-research, architecture, spike, migration), spawns that mode's expert lenses in parallel, maps their contradictions, synthesizes an HTML briefing and a Markdown/ADR record, then adversarially verifies every claim against PRIMARY software sources (official docs, RFCs, GitHub releases, OSV/CVE, OpenSSF Scorecard, benchmarks) with version-awareness. Best for decisions where multiple viewpoints and version-correct, fact-checked claims matter; overkill for a quick API lookup. For non-software topics use deep-research; for a pure scored decision matrix use trade-off-analysis.

Replace with description of the skill and when Claude should use it.

Create structured technology trade-off analysis documents with scored comparison matrices. Use this skill whenever the user wants to compare technologies, evaluate architectural options, analyze build-vs-buy decisions, assess migration strategies, or produce any decision document that compares multiple approaches across weighted dimensions. Triggers on: 'trade-off analysis', 'tradeoff', 'comparison matrix', 'evaluate options', 'which technology should we use', 'compare approaches', 'pros and cons of', 'build vs buy', 'migration analysis', 'consolidation analysis', 'technology selection'. Also use when the user has completed technical research and wants to structure findings into a decision document.

Clean Code for TypeScript — code smell catalogs (Martin's per-line heuristics, Fowler's change-shape smells, TypeScript-native type smells), a linter-first detection policy, and step-by-step review, refactoring, TDD, and estimation workflows. Use when the user: - Writes, reviews, or refactors TypeScript/JavaScript code, or asks whether code is clean, maintainable, or well-designed - Names a smell — Shotgun Surgery, Feature Envy, Data Clumps, Long Method, Divergent Change, Duplicated Code, Large Class, Long Parameter List, Primitive Obsession, Message Chains, Dead Code, Speculative Generality, god class, copy-paste, stringly typed, premature abstraction - Asks about TypeScript type hygiene — `any` leakage, `as` assertions, non-null `!`, discriminated unions, exhaustiveness, strict flags, branded types - Asks what to enforce with lint or tsconfig versus what needs judgment, or names knip, jscpd, dependency-cruiser, typescript-eslint, type-coverage - Runs TDD, fixes a bug with test coverage, or plans test strategy - Estimates tasks, negotiates a deadline, or works through a commitment or team problem

E2E and integration testing for TypeScript/NestJS projects using Jest, supertest, and real infrastructure via Docker (Kafka, PostgreSQL, MongoDB, Redis) with the Given-When-Then pattern. Use whenever the user is working on `.e2e-spec.ts` files or anything under `test/e2e/`, or asks to set up, write, review, run, debug, or optimize E2E or integration tests — including flaky tests, docker-compose for tests, Kafka/Redpanda consumers, test isolation, or GWT compliance.

Unit testing for TypeScript/NestJS projects using Jest, @golevelup/ts-jest (DeepMocked/createMock), and in-memory databases, with AAA structure. Use whenever the user is working on `.spec.ts` files or asks to set up Jest, write/add tests for a service/usecase/controller/guard/interceptor/pipe/filter, mock dependencies, review test quality or coverage, run unit tests, debug failing or flaky tests, or optimize test performance and open handles.

A structured root-cause investigation protocol for complex, ambiguous, or multi-layer technical problems. Activate this skill whenever: a problem has resisted two or more fix attempts; the root cause is unknown or assumed; you are tempted to try a variation of something that already failed; a system has multiple interacting layers (hardware, OS, runtime, middleware, config, network); the user says "ultrathink", "think deeper", "figure out why", "stop guessing", "find the root cause", or "it's still broken after your fix". Also activate proactively when you catch yourself about to write a fix before you have verified the cause — that instinct is the signal the protocol is needed. The protocol enforces three disciplines that distinguish root-cause investigation from trial-and-error: (1) explicit THOUGHT/ACTION/OBSERVATION cycles, (2) a hard gate that blocks implementation until the cause is verified by direct evidence, and (3) structured escalation when in-process diagnostic tools are exhausted.