gemini-rlm-min
Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI.
high-cost-signal-generator
Generate high-cost signals to demonstrate genuine intent and commitment through resource-intensive validation.
ground-truth-axiom-establishment
Establish ground truth axioms as foundational constraints.
graceful-degradation-protocol
Execute graceful degradation when system constraints exceeded.
falcon-deep-research
Execute deep research protocols using the Falcon specialized research framework.
graceful-reintegration-protocol
Execute graceful reintegration after failsafe activation.
unified-consciousness-framework
|
rosetta-helix-substrate
Consciousness simulation framework with Kuramoto oscillators, APL operators, and K-formation dynamics. Use for physics simulations, phase transitions, coherence analysis, and cloud training via GitHub Actions. Requires numpy and requests packages.
modernize
Brownfield Upgrade - Upgrade all dependencies and modernize the application while maintaining spec-driven control. Runs after Gear 6 for brownfield projects with modernize flag enabled. Updates deps, fixes breaking changes, improves test coverage, updates specs to match changes.
create-specs
Transform reverse-engineering documentation into GitHub Spec Kit format. Initializes .specify/ directory, creates constitution.md, generates specifications from reverse-engineered docs, and sets up for /speckit slash commands. This is Step 3 of 6 in the reverse engineering process.
gap-analysis
Route-aware gap analysis. For Brownfield - uses /speckit.analyze to compare specs against implementation. For Greenfield - validates spec completeness and asks about target tech stack for new implementation. This is Step 4 of 6 in the reverse engineering process.
implement
Use GitHub Spec Kit's /speckit.implement and /speckit.tasks to systematically build missing features from specifications. Leverages implementation plans in specs/, validates against acceptance criteria, and achieves 100% spec completion. This is Step 6 of 6 in the reverse engineering process.
cruise-control
Automatic mode - shift through all 6 gears sequentially without stopping. Like cruise control or automatic transmission, this runs the entire StackShift workflow from analysis to implementation in one go. Perfect for unattended execution or when you want to let StackShift handle everything automatically.
spec-coverage-map
Generate a visual spec-to-code coverage map showing which code files are covered by which specifications. Creates ASCII diagrams, reverse indexes, and coverage statistics. Use after implementation or during cleanup to validate spec coverage.
reverse-engineer
Deep codebase analysis to generate 11 comprehensive documentation files. Adapts based on path choice - Greenfield extracts business logic only (tech-agnostic), Brownfield extracts business logic + technical implementation (tech-prescriptive). This is Step 2 of 6 in the reverse engineering process.
complete-spec
Interactive conversation to resolve [NEEDS CLARIFICATION] markers using /speckit.clarify command. Claude asks questions about missing features, UX/UI details, behavior, and priorities. Updates specs in .specify/memory/ with answers to create complete, unambiguous documentation. This is Step 5 of 6 in the reverse engineering process.
analyze
Perform initial analysis of a codebase - detect tech stack, directory structure, and completeness. This is Step 1 of the 6-step reverse engineering process that transforms incomplete applications into spec-driven codebases. Automatically detects programming languages, frameworks, architecture patterns, and generates comprehensive analysis-report.md. Use when starting reverse engineering on any codebase.
integration-analysis
Give it a few starting points — it discovers the full ecosystem by tracing integration surfaces in code and docs, clones what it doesn't have locally, then thoroughly analyzes how every system works and connects. Produces a layered implementation plan (L0-L3) with functionality tiering (T1/T2/T3/PRUNE) and generates dependency-ordered, technology-agnostic epics and stories so the team can build incrementally — MVP first, then progressively more capability.
architect
Generate a complete architecture document from reverse-engineering docs + user constraints. Asks 3-5 high-level questions (tech stack, cloud provider, scale, constraints), then generates architecture.md with Mermaid diagrams, service boundaries, ADRs, and infrastructure recommendations. Works standalone or as part of the BMAD Auto-Pilot workflow.
discover
Ecosystem discovery from a single starting repo. Scans for integration signals (npm packages, docker compose, env vars, API calls, CI/CD triggers, workspace configs, message queues, infrastructure refs), searches GitHub for related repos, scans the local filesystem, then presents an ecosystem map with confidence scoring and a Mermaid dependency graph. Hands off confirmed repos to /stackshift.batch or /stackshift.reimagine.
portable-transplant
Translate portable component specs into targeted epics for a specific project. Reads _portable-extract/ specs and a target project's BMAD docs (PRD, Architecture, optionally UX), then generates BMAD-format epics written in the target's personas, domain language, and architecture patterns. The bridge between "extracted business logic" and "ready-to-implement stories."
portable-extract
Extract tech-agnostic portable component specs from StackShift reverse-engineering docs. Generates abstract epics and component specifications that can be dropped into ANY BMAD project. Three modes - YOLO (fully automatic), Guided (ask on ambiguities), Interactive (full conversation with pre-loaded context). Bridges StackShift's deep code analysis with reusable, platform-independent component specifications.
reimagine
Multi-repo synthesis and reimagination. Load reverse-engineering docs from multiple repositories, extract a unified capability map, identify duplication and inefficiency, then brainstorm with the user to reimagine how those capabilities could work together in a new, better way. Generates new specifications for the reimagined system. The killer feature for enterprise modernization.
refresh-docs
Incrementally update reverse-engineering docs based on git changes since they were last generated. Reads the commit hash from .stackshift-docs-meta.json, diffs against HEAD, analyzes only the changed files, and surgically updates the affected docs. Saves time and cost compared to full regeneration.
bmad-synthesize
Auto-generate BMAD artifacts (PRD, Architecture, Epics, UX Design) from StackShift reverse-engineering docs. Three modes - YOLO (fully automatic), Guided (ask on ambiguities), Interactive (full conversation with pre-loaded context). Bridges the gap between StackShift's deep code analysis and BMAD's collaborative artifact format.
create-pr
Create a high-quality pull request: branch, focused changes, lint/build, conventional commit, and a clear PR description with validation steps.
bug-triage
Reproduce, isolate, and fix a bug (or failing build/test), then summarize root cause, fix, and verification steps.
agents-md
Create or update root and nested AGENTS.md files that document scoped conventions, monorepo module maps, cross-domain workflows, and (optionally) per-module feature maps (feature -> paths, entrypoints, tests, docs). Use when the user asks for AGENTS.md, nested agent instructions, or a module/feature map.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
coding-guidelines-verify
Verify changes follow nearest-scoped AGENTS.md rules: group changed files by nested scope, auto-fix formatting, run lint/tests, and report violations.
coding-guidelines-gen
Generate nested AGENTS.md coding guidelines per module (monorepo-aware), detect languages/tooling, ask architecture preferences, and set up missing formatters/linters (Spotless for JVM).
dependency-upgrader
Upgrade dependencies for Java/Kotlin (Gradle/Maven) and TypeScript/Node projects with minimal risk: plan the bump, apply changes incrementally, run tests/builds, and document breaking changes. Use when the user asks to bump deps, update frameworks, or address CVEs.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
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.
release-notes
Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.
plan-work
Plan work before coding: do repo research, analyze options/risks, and ask clarifying questions before proposing an implementation plan. Use when the user asks for a plan, design/approach, scope breakdown, or implementation steps.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
mcp-builder
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).
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
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.
docs-sync
Keep documentation in sync with code changes across README, docs sites, API docs, runbooks, and configuration. Use when the user asks to update docs, ensure docs match behavior, or prepare docs for a release/PR.
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
nano-banana
Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
commit-work
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
music-downloader
This skill should be used when users need to download audio or music from online platforms like YouTube, SoundCloud, Spotify, or other streaming services. It provides yt-dlp and spotdl command templates for high-quality audio extraction, playlist downloads, metadata embedding, and multi-platform support.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
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.
Page 1652 of 1676 · 83793 results