Claude Devline

Update dependencies across one or many repositories. Default mode patches CVEs/security advisories: give CVE IDs (or a vulnerable package) and it researches affected/fixed versions, then launches dependency agents to update, verify, and commit. With --migrate it runs major-version migrations: give a package + target version (or an 'X to Y' library swap, or nothing for an EOL audit) and it researches the migration guide and tooling, gets your approval, then launches dependency agents (opus) to run codemods and refactor breaking changes. Use whenever the user mentions CVEs, security vulnerabilities in dependencies, patching/updating packages for security, OR migrating/upgrading a dependency across a major version, moving from one library to another, end-of-life/EOL, deprecations, or breaking-change upgrades.

Create a detailed TDD implementation plan with parallel tasks from a feature spec or description.

Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for "brand", "brand identity", "voice", "visual identity", "brand guidelines", "messaging framework", "brand consistency", branded content, tone of voice, marketing assets, brand compliance, style guides.

This skill should be used when the user asks to "debug this", "fix this bug", "find the root cause", "investigate an error", "troubleshoot", "why is this failing", "trace the issue", or mentions errors, exceptions, stack traces, or unexpected behavior that needs investigation. Launches the debugger agent for systematic root cause analysis.

Fast-lane a small change — branch, implement (TDD), one review, commit. Skips brainstorm, planning, design-system, deep review, and all approval gates. Use for bugfixes, typos, tweaks, or any change that touches ~1 file / ≲30 lines with no new component, schema, endpoint, or UI surface.

This skill should be used when the user runs "/setup", "setup my project", "initialize CLAUDE.md", "create CLAUDE.md", or wants to set up the devline clarification protocol for a project. Creates a CLAUDE.md with the clarification protocol and interactively generates a minimal devline.local.md with only non-default settings.

Standalone design skill for individual components, color themes, brand identity, or fitting within an existing project theme. Use when the user asks to "design a button", "create a color theme", "create a brand identity", "make this match our site", "show me 6 card styles", "add a modal to the brand", or any targeted UI design request. Also triggers on mood-based requests like "warm dark theme", "cool minimalist colors", "playful typography".

Perform an in-depth code review of recent changes. Checks correctness, security, performance, and code quality.

This is the default skill for all development work. It orchestrates the entire development lifecycle from idea to merge-ready code, coordinating multiple agents for brainstorming, planning, implementation, review, documentation, and final approval. Use this for any development task that is non-trivial and could benefit from structured planning, parallel execution, and rigorous review or require more than 3 lines of code changed.

Use whenever text is being produced or edited that could be public/published. Covers 4 purposes — communication (emails, LinkedIn), project content (READMEs, website copy, docs), scientific writing (papers, theses), and fiction (books, stories). Humanize AI-generated text by removing common AI writing patterns. Triggers on "humanize this", "make this sound human", "fix AI writing", "rewrite this naturally", "write a blog post", "draft an email", "write a README", "translate this", "translate to German", "auf Deutsch", "write a chapter", "scientific paper", or any request to produce, edit, or translate text meant for human readers.

Retrieves authoritative, up-to-date technical documentation, API references, configuration details, and code examples for any developer technology. Use this skill whenever answering technical questions or writing code that interacts with external technologies. This includes libraries, frameworks, programming languages, SDKs, APIs, CLI tools, cloud services, infrastructure tools, and developer platforms. Common scenarios: - looking up API endpoints, classes, functions, or method parameters - checking configuration options or CLI commands - answering "how do I" technical questions - generating code that uses a specific library or service - debugging issues related to frameworks, SDKs, or APIs - retrieving setup instructions, examples, or migration guides - verifying version-specific behavior or breaking changes Prefer this skill whenever documentation accuracy matters or when model knowledge may be outdated.

Implement tasks using TDD. Accepts a plan or specific task description. Runs implementer agents in parallel where possible.

Design intelligence for UI/UX — injected into the frontend-planner agent. Provides BM25-searchable database of 67 styles, 161 color palettes, 57 font pairings, 160 animated component patterns, 161 industry rules, plus framework-agnostic design guidelines. Not invoked directly.

This skill should be used when the user asks to "brainstorm", "refine an idea", "flesh out a feature", "define requirements". Guides interactive refinement of rough ideas into concise, actionable feature specifications. Focuses on the "what" and architecture — never the "how".

Final comprehensive pull request review — the last gate before merge. Checks security, credentials, code quality, tech debt, conventions, and plan compliance.

Graphic design skill: logo design (55 styles, 30 color palettes, 25 industry guides), corporate identity programs (50+ deliverables), icon design (15 styles, SVG), banner design (22 art direction styles, social/ads/web/print), HTML presentations (Chart.js, copywriting formulas), social photos (multi-platform). Trigger on: logo, logo design, corporate identity, CIP, banner, social media banner, presentation, slides, icon design, social photos, graphic design, visual assets.

Grep-based reverse dependency analysis — injected into the planner and reviewer agents. Computes which files are affected by changes to a set of seed files. Not invoked directly.

Domain logic for TDD methodology — injected into agents that implement code using test-driven development. Not invoked directly.

Domain logic for dependency management — injected into the dependency agent. Provides ecosystem detection, version update mechanics, build/test verification, and commit/push workflows across all major package managers. Not invoked directly.