Skills on Vibe Coding

PDF

Mon, 01 Jan 0001 00:00:00 +0000

The PDF skill packages the specific know-how needed to work with PDFs reliably: filling form fields, extracting text and tables, merging or splitting documents, and generating new PDFs from scratch — using the right libraries and avoiding common formatting pitfalls.

DOCX

Mon, 01 Jan 0001 00:00:00 +0000

The DOCX skill covers creating and editing Microsoft Word documents programmatically — headings, styles, tables, tracked changes — in a way that produces files that open correctly in Word rather than malformed XML.

PPTX

Mon, 01 Jan 0001 00:00:00 +0000

The PPTX skill packages the conventions needed to generate and edit PowerPoint presentations: slide layouts, text formatting, speaker notes, and basic chart or image placement, producing files that open cleanly in PowerPoint or Keynote.

XLSX

Mon, 01 Jan 0001 00:00:00 +0000

The XLSX skill covers working with Excel files properly: writing real formulas rather than pre-computed values, applying number formats and styles, and managing multiple sheets and references correctly.

Why a skill for this

It’s easy for an agent to produce a spreadsheet that looks right but is actually just static values pasted where formulas should be — which breaks the moment the underlying data changes. This skill steers toward spreadsheets that behave the way a human analyst would build them.

Canvas Design

Mon, 01 Jan 0001 00:00:00 +0000

The Canvas Design skill packages visual design judgment: spacing systems, typographic hierarchy, color restraint, and layout composition — the kind of taste that’s easy to describe but hard to consistently apply prompt by prompt.

Brand Guidelines

Mon, 01 Jan 0001 00:00:00 +0000

The Brand Guidelines skill encodes a specific brand’s rules — color palette, typography, tone of voice, logo usage — so an agent’s output stays consistent with that identity across many separate requests.

Artifacts Builder

Mon, 01 Jan 0001 00:00:00 +0000

The Artifacts Builder skill covers the conventions for producing standalone, self-contained interactive outputs — inlined styles and scripts, responsive layout, no external dependencies that would break in a sandboxed viewer.

Webapp Testing

Mon, 01 Jan 0001 00:00:00 +0000

The Webapp Testing skill packages a verification workflow: launching a dev server, driving a browser through the golden path and edge cases, and checking console and network output for errors — rather than declaring a UI change complete after just reading the code.

MCP Builder

Mon, 01 Jan 0001 00:00:00 +0000

The MCP Builder skill packages the boilerplate and conventions for writing a new MCP server — the protocol handshake, tool and resource definitions, and error handling patterns that a well-behaved server needs.

Algorithmic Art

Mon, 01 Jan 0001 00:00:00 +0000

The Algorithmic Art skill packages a two-step process for computational art: first drafting a short “algorithmic philosophy” — a named aesthetic movement with its own manifesto — then expressing that philosophy as a p5.js sketch using noise fields, particles, and seeded randomness. It outputs a philosophy doc, an interactive HTML viewer, and the generative JS itself.

Claude API

Mon, 01 Jan 0001 00:00:00 +0000

The Claude API skill is a language-aware reference for the Anthropic SDK and Messages API — model selection, adaptive thinking, streaming, prompt caching, token counting, and tool/MCP integration — with explicit guidance to verify API shapes against live docs rather than a model’s memorized training data.

Doc Co-Authoring

Mon, 01 Jan 0001 00:00:00 +0000

Doc Co-Authoring packages a structured process for writing technical specs, PRDs, decision docs, and proposals: gathering context up front, iteratively building sections through brainstorming and editing, then stress-testing the draft by having a fresh, context-free Claude read it as a real reader would.

Frontend Design

Mon, 01 Jan 0001 00:00:00 +0000

The Frontend Design skill packages a design-lead mindset for building web UI: pin down the subject and its audience, build a compact token system — palette, type pairing, layout concept, one signature element — then critique that plan against known AI-generic defaults before writing any code.

Internal Comms

Mon, 01 Jan 0001 00:00:00 +0000

Internal Comms packages format- and tone-specific guidelines for recurring internal writing tasks — progress/plans/problems updates, company newsletters, FAQ answers, leadership updates, and incident reports — loading the matching template based on which type of communication is requested.

Skill Creator

Mon, 01 Jan 0001 00:00:00 +0000

Skill Creator packages the full lifecycle of authoring an Agent Skill: drafting the skill, writing test prompts, running evaluations with variance analysis, reviewing results, and rewriting the skill based on feedback, then optimizing the skill’s description for more reliable triggering.

Slack GIF Creator

Mon, 01 Jan 0001 00:00:00 +0000

Slack GIF Creator packages Slack’s specific GIF constraints — 128×128 for emoji, 480×480 for messages, 10–30fps, 48–128 colors, sub-3-second emoji duration — along with a frame-building workflow and validation tools, so requests like “make a GIF of X doing Y for Slack” produce a file that actually fits Slack’s limits.

Theme Factory

Mon, 01 Jan 0001 00:00:00 +0000

Theme Factory packages a set of curated color-palette-and-font-pairing themes — Ocean Depths, Sunset Boulevard, Modern Minimalist, and others — shown via a visual showcase, that can be applied to slide decks, documents, or HTML artifacts, or used as a starting point for generating a new theme on the fly.

Superpowers

Mon, 01 Jan 0001 00:00:00 +0000

Superpowers packages a battle-tested library of 20+ Claude Code skills — test-driven development, systematic debugging, brainstorming techniques, git worktree management, and root-cause tracing — installable in one shot as a plugin marketplace.

Superpowers Lab

Mon, 01 Jan 0001 00:00:00 +0000

Superpowers Lab is the experimental proving ground for Superpowers — newer, less-settled techniques that graduate into the stable library once they hold up in real use.

Why a skill for this

Skill development benefits from the same staging discipline as software releases — trying new techniques in a lab environment before committing them to a widely-installed stable marketplace avoids regressions for everyone else.

Playwright Browser Automation

Mon, 01 Jan 0001 00:00:00 +0000

This skill gives Claude Code direct, model-invoked control of Playwright — driving a real browser through a web app’s flows to click, fill forms, and validate behavior end-to-end.

Why a skill for this

Reading component code doesn’t confirm a flow actually works in a browser. A dedicated Playwright skill turns that verification into a repeatable, invokable step instead of an ad hoc script written from scratch each time.

iOS Simulator

Mon, 01 Jan 0001 00:00:00 +0000

The iOS Simulator skill lets Claude drive Apple’s Simulator directly — building the app, navigating its screens, and exercising flows the way a developer would during manual QA.

Why a skill for this

iOS development often has no equivalent to a browser’s headless test runner conveniently available mid-conversation. This skill closes that gap by giving Claude a controllable simulator instead of relying on the developer to manually verify every change.

FFUF Web Fuzzing

Mon, 01 Jan 0001 00:00:00 +0000

This skill integrates the ffuf web fuzzer, letting Claude run authenticated fuzzing scans, auto-calibrate for noisy responses, and analyze results for real vulnerabilities during a penetration test.

Why a skill for this

Fuzzing tools have enough flags and calibration nuance that getting authenticated, low-noise scans right by hand takes real fuzzer expertise. Packaging that expertise as a skill makes competent fuzzing runs repeatable for anyone using it.

Threat Hunting with Sigma Rules

Mon, 01 Jan 0001 00:00:00 +0000

This skill uses Sigma detection rules — a vendor-neutral format for describing log-based threat signatures — to hunt for suspicious activity and analyze security events.

Why a skill for this

Sigma’s rule format is expressive but verbose to write and match by hand across large event logs. A skill that already knows the format turns threat hunting into a repeatable query task instead of a manual log-reading exercise.

Trail of Bits Security Skills

Mon, 01 Jan 0001 00:00:00 +0000

Trail of Bits’ security skills bring their own audit tooling — static analysis with CodeQL and Semgrep, variant analysis, and vulnerability pattern detection — into Claude Code.

Why a skill for this

Security auditing firms encode years of hard-won pattern knowledge into their tooling configs. Packaging that as a skill means Claude Code inherits Trail of Bits’ actual audit methodology instead of a generic security pass.

D3.js Visualization

Mon, 01 Jan 0001 00:00:00 +0000

This skill teaches Claude to build D3.js charts and interactive data visualizations, handling D3’s verbose selection-and-binding API on the model’s behalf.

Why a skill for this

D3’s power comes with a steep, idiosyncratic API that’s easy to get subtly wrong. A skill that already knows D3’s conventions produces working visualizations faster than re-deriving the pattern from documentation each time.

CSV Data Summarizer

Mon, 01 Jan 0001 00:00:00 +0000

The CSV Data Summarizer skill automatically profiles a CSV file and produces insights with visualizations, without needing a detailed prompt describing what to look for.

Why a skill for this

Most CSV exploration starts with the same handful of questions — distributions, outliers, missing data, obvious correlations. Automating that first pass saves the back-and-forth of asking for it column by column.

Claude Scientific Skills

Mon, 01 Jan 0001 00:00:00 +0000

This is a collection of ready-to-use skills for working with specialized scientific libraries and databases, packaging domain knowledge that’s otherwise scattered across niche documentation.

Why a skill for this

Scientific computing libraries often have small, specialist user bases and thin documentation. Bundling working knowledge of them as skills saves re-deriving usage patterns from source code or sparse docs each time.

Recursive Research

Mon, 01 Jan 0001 00:00:00 +0000

Recursive Research runs PhD-level research across any domain — tiering sources by reliability and checkpointing findings to disk so long research sessions survive context compaction.

Why a skill for this

Deep research spanning many sources tends to lose earlier findings once a conversation compacts. Checkpointing to disk mid-research means a long investigation doesn’t have to restart from scratch after compaction.

NotebookLM Integration

Mon, 01 Jan 0001 00:00:00 +0000

This skill lets Claude Code chat directly with Google NotebookLM, grounding answers in a specific set of uploaded source documents rather than general knowledge.

Why a skill for this

NotebookLM’s source-grounding is useful precisely because it won’t answer beyond what’s in the uploaded documents. Wiring that into Claude Code keeps document-grounded research and general coding work in the same session.

Markdown to EPUB Converter

Mon, 01 Jan 0001 00:00:00 +0000

This skill converts markdown documents and chat summaries into properly formatted EPUB ebook files, handling the packaging EPUB readers expect.

Why a skill for this

EPUB is a zipped bundle of XHTML, metadata, and a manifest — not something you get right by hand-writing markup. A skill that knows the format’s requirements produces a file that actually opens cleanly in e-readers.

Master Claude for Legal

Mon, 01 Jan 0001 00:00:00 +0000

This skill pack equips Claude for legal-team work — NDA triage, multi-party contract version diffing, citation verification, and meeting briefs — with reference docs on privilege and long-document review baked in.

AWS Skills

Mon, 01 Jan 0001 00:00:00 +0000

AWS Skills brings AWS-specific development practice into Claude Code — CDK patterns, cost optimization guidance, and serverless/event-driven architecture conventions.

Why a skill for this

AWS has enough service-specific gotchas and cost traps that generic cloud advice often misses them. A skill scoped specifically to AWS and CDK keeps recommendations grounded in what actually works on that platform.

Expo Skills

Mon, 01 Jan 0001 00:00:00 +0000

Expo Skills is the official skill set from the Expo team for building React Native apps with Expo, covering the framework’s specific conventions and tooling.

Why a skill for this

Being maintained by the Expo team itself means the skill tracks the framework’s actual conventions and release changes, rather than a third party’s best guess at Expo’s current best practices.

shadcn/ui Skill

Mon, 01 Jan 0001 00:00:00 +0000

The shadcn/ui skill gives Claude Code direct context on shadcn/ui’s components and enforces consistent usage patterns across a project.

Why a skill for this

shadcn/ui ships as copyable component source rather than an installed package, so consistency depends on the model actually knowing each component’s intended API. A skill scoped to shadcn/ui keeps generated UI code matching the library’s real patterns instead of guessing.

Get Shit Done

Mon, 01 Jan 0001 00:00:00 +0000

Get Shit Done is a lightweight meta-prompting and context-engineering system for Claude Code, built around spec-driven development rather than ad hoc prompting.

Why a skill for this

Spec-first workflows tend to produce more predictable output than freeform prompting, especially on larger features. Packaging that discipline as a skill makes it the default instead of something re-explained per task.

Skill Seekers

Mon, 01 Jan 0001 00:00:00 +0000

Skill Seekers automatically converts any documentation website into a ready-to-use Claude skill, turning scattered docs into structured, invokable reference material.

Why a skill for this

Most third-party libraries have documentation but no packaged skill. Automating the conversion means any well-documented tool can get a working skill without hand-authoring one from scratch.

Chrome Relay

Mon, 01 Jan 0001 00:00:00 +0000

Chrome Relay drives the user’s already-signed-in Chrome session — cookies, SSO, localhost included — through a local CLI bridge, as a real-browser counterpart to headless Playwright automation.

Why a skill for this

Some flows only work correctly inside an authenticated, already-logged-in browser session — SSO-gated internal tools, for instance. Relaying through the real Chrome session sidesteps re-authenticating a separate automated browser.

Full-Page Screenshot

Mon, 01 Jan 0001 00:00:00 +0000

This skill captures full-page screenshots of web pages via the Chrome DevTools Protocol, with zero external dependencies.

Why a skill for this

Full-page capture (beyond the visible viewport) usually needs either a heavier automation framework or manual scrolling-and-stitching. Talking to the DevTools Protocol directly gets a clean full-page image without either.

n8n Skills

Mon, 01 Jan 0001 00:00:00 +0000

n8n Skills lets Claude directly understand and operate n8n automation workflows — reading, editing, and reasoning about workflow graphs rather than treating them as opaque JSON.

Why a skill for this

n8n workflows are graphs of connected nodes that are awkward to reason about as raw exported JSON. A skill that understands the workflow model can edit and debug workflows the way a human building them in the n8n UI would.

PICT Test Case Design

Mon, 01 Jan 0001 00:00:00 +0000

This skill designs comprehensive pairwise-combinatorial test suites from requirements or code, using Microsoft’s PICT methodology to keep the case count manageable.

Why a skill for this

Testing every combination of inputs is usually infeasible, but pairwise coverage catches most real-world combinatorial bugs with far fewer cases. PICT’s methodology is the standard way to generate that reduced set correctly.

Web Asset Generator

Mon, 01 Jan 0001 00:00:00 +0000

The Web Asset Generator skill produces web assets like favicons, app icons, and social media images in the sizes and formats each platform actually expects.

Why a skill for this

Every platform — favicons, Open Graph images, app store icons — has its own required dimensions and formats, which is tedious to track by hand. A skill that already knows those specs saves re-exporting assets that come out the wrong size.

anydesign

Mon, 01 Jan 0001 00:00:00 +0000

anydesign analyzes any image, URL, or Figma file and produces a structured design.md capturing the full design system and component inventory, portable to other AI builders.

Why a skill for this

Design systems usually live implicitly in a Figma file or an existing site rather than as a portable spec. Extracting that into a structured document means the design system can travel with the project instead of staying locked in one tool.

Frontend Slides

Mon, 01 Jan 0001 00:00:00 +0000

Frontend Slides creates animation-rich HTML presentations from scratch, or converts an existing PowerPoint deck into one.

Why a skill for this

HTML/CSS presentations can do things static slide decks can’t — real animation, interactivity, embedded live content — but building one from scratch is its own frontend project. This skill packages that so the format doesn’t have to be reinvented per deck.

Loki Mode

Mon, 01 Jan 0001 00:00:00 +0000

Loki Mode orchestrates dozens of coordinated AI agents to build, deploy, and operate a complete startup end-to-end, from a PRD through to a live, revenue-generating product.

Why a skill for this

Coordinating many agents toward one large goal needs explicit role division and hand-off structure, or the agents duplicate work or conflict. This skill packages that orchestration pattern rather than leaving it to be improvised per project.

Rampstack Brand Build Skills

Mon, 01 Jan 0001 00:00:00 +0000

This 59-skill library covers a website’s full lifecycle — brand, design, content, SEO, development, ops, and growth — including a dedicated SEO audit suite.

Why a skill for this

Building and running a marketing site touches many disciplines that don’t usually live in one toolkit. Bundling them together keeps brand, content, and technical SEO work consistent instead of drifting apart across separate tools.

Solo Skills

Mon, 01 Jan 0001 00:00:00 +0000

Solo Skills packages seven bilingual (English/Chinese) skills for solo founders and indie developers — launch tweets, customer emails, decision frameworks, and postmortems.

Why a skill for this

Solo founders repeat the same small set of communication and decision tasks — announcing a launch, writing a postmortem — often enough that having them as ready skills beats rewriting the format each time.

Google Workspace Skills

Mon, 01 Jan 0001 00:00:00 +0000

This is a suite of Google Workspace integration skills covering Gmail, Calendar, Chat, Docs, Sheets, Slides, and Drive, with cross-platform OAuth handling.

Why a skill for this

Each Workspace API has its own auth flow and quirks; wiring up OAuth correctly per app is easy to get wrong. A packaged skill suite means that setup work is done once rather than per integration.

Postgres Query Skill

Mon, 01 Jan 0001 00:00:00 +0000

This skill executes safe, read-only SQL queries against PostgreSQL databases, with multi-connection support and defense-in-depth safeguards against destructive statements.

Why a skill for this

Letting a model run arbitrary SQL against a real database is risky without hard guardrails. Restricting the skill to read-only queries with explicit safeguards makes database exploration usable without risking accidental writes.

Jules Delegate

Mon, 01 Jan 0001 00:00:00 +0000

Jules Delegate hands off coding tasks to Google’s Jules AI agent for async work — bug fixes, docs, and tests — directly on a GitHub repo.

Why a skill for this

Some tasks are better run asynchronously in the background than synchronously in the current session. This skill packages the hand-off so Claude Code can delegate rather than block on work another agent can do independently.

Outline Wiki Skill

Mon, 01 Jan 0001 00:00:00 +0000

The Outline Wiki skill searches, reads, creates, and manages documents in an Outline wiki instance, whether cloud-hosted or self-hosted.

Why a skill for this

Team knowledge often lives in a wiki rather than the codebase, so a coding-only agent misses it. Wiring in direct wiki access keeps documentation work and code work in the same conversation.

Deep Research (Gemini)

Mon, 01 Jan 0001 00:00:00 +0000

This skill hands off research tasks to Google’s Gemini Deep Research agent for autonomous multi-step work — market analysis, competitive landscaping, and literature reviews.

Why a skill for this

Deep, multi-step research benefits from a purpose-built research agent rather than a general coding assistant improvising a research plan. Delegating to Gemini’s dedicated research agent gets a more thorough pass on that kind of task.

Mercury MCP Cheatsheet

Mon, 01 Jan 0001 00:00:00 +0000

This reference skill covers the Mercury (Proton) MCP tools for messaging agent teammates, managing threads, and scheduling automations across a coordinated team of agents.

Why a skill for this

Multi-agent coordination tools tend to have enough surface area — threading, scheduling, teammate addressing — that a quick reference beats re-deriving the API each time. This skill keeps that reference on hand.

Agent Skills Open Standard

Mon, 01 Jan 0001 00:00:00 +0000

Agent Skills is the open SKILL.md standard for packaging reusable agent capabilities — originated by Anthropic and now adopted across Codex, Gemini CLI, Grok Build, Cursor, GitHub Copilot, and more.

Codex Skills System

Mon, 01 Jan 0001 00:00:00 +0000

OpenAI Codex’s built-in skills system discovers SKILL.md skills from ~/.codex/skills/ and installs new ones via $skill-installer, either from OpenAI’s curated catalog or any GitHub repo.

Why a skill for this

Having a first-party install path and curated catalog, rather than only community-assembled lists, is what makes a skills ecosystem practical to actually adopt inside Codex.

OpenAI Skills/Plugins Catalog

Mon, 01 Jan 0001 00:00:00 +0000

This is OpenAI’s official, curated repository of Codex skills and plugins — covering design tools, testing, security, observability, and one-command cloud deploys.

Why a skill for this

A first-party curated catalog is a stronger trust signal than an assembled community list — these skills are maintained by, or reviewed by, OpenAI itself rather than crowdsourced without a review bar.

Figma Design-to-Code Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill bundle wires up Figma — Code Connect, Create Design System Rules, and Generate Design — so Codex can work directly from real design files.

Why a skill for this

Turning a Figma file into accurate code depends on knowing Figma’s specific APIs, like Code Connect and design tokens, rather than guessing from a screenshot. Packaging that as a skill keeps the translation accurate.

Playwright Testing Skill

Mon, 01 Jan 0001 00:00:00 +0000

OpenAI’s curated Playwright skill gives Codex the same browser-automation and interactive test-authoring capability as its Claude Code counterpart, packaged for Codex’s skill system.

Why a skill for this

Verifying a web app in a real browser matters regardless of which coding agent is driving the session — this is the Codex-native equivalent of that same verification step.

GitHub PR Review Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill reads a GitHub pull request’s review comments and drives the corresponding fixes back into the branch.

Why a skill for this

Addressing review feedback is a mechanical loop — read a comment, make the matching change, reply — that’s a good fit for automation once the skill knows how to map comments to specific diffs.

CI Fix Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill diagnoses and fixes failing GitHub Actions CI runs directly from the failure logs.

Why a skill for this

CI failures are usually diagnosable from the log output alone, but pulling and parsing that log by hand is tedious. A skill that already knows how to fetch and read Actions logs shortens the loop from red CI to a fix.

Security Best Practices Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill applies a secure-coding checklist during code generation and review, catching common vulnerability classes as code is written.

Why a skill for this

Security issues are cheaper to prevent during generation than to catch in a later review pass. Baking a checklist into the generation step catches classes of bugs before they’re ever committed.

Security Threat Model Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill walks through producing a structured threat model for a system — assets, trust boundaries, and attack surfaces — rather than an ad hoc security discussion.

Why a skill for this

Threat modeling is only useful if it’s structured and complete; an unstructured conversation tends to miss entire categories of risk. A skill that enforces the methodology produces a threat model that’s actually useful to a security reviewer.

Sentry Triage Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill pulls and triages error reports directly from Sentry, connecting production error data to the code that’s causing it.

Why a skill for this

Triaging errors well means correlating a stack trace with the actual code path and recent changes — something that’s faster with direct Sentry access than copy-pasting error reports into a prompt.

Jupyter Notebook Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill authors and edits Jupyter notebooks programmatically, handling the notebook’s cell-and-metadata JSON structure correctly.

Why a skill for this

Notebook files are structured JSON with execution metadata and outputs, not plain text — editing them without understanding that structure easily corrupts the file. A skill that knows the format keeps notebooks valid while editing.

Notion Spec-to-Implementation Skill

Mon, 01 Jan 0001 00:00:00 +0000

This curated Codex skill turns a Notion spec document directly into an implementation plan and pull request.

Why a skill for this

Specs often live in Notion, separate from the codebase, which means implementation work starts with manually re-reading and re-typing the spec. A skill that reads Notion directly removes that translation step.

Cloud Deploy Skills

Mon, 01 Jan 0001 00:00:00 +0000

These curated Codex skills drive one-command deploys to Vercel, Netlify, Render, or Cloudflare directly from the agent, without a separate manual deploy step.

Why a skill for this

Each platform has its own CLI and deploy conventions; a skill scoped to a specific target means deploys work correctly on the first try instead of trial-and-error against unfamiliar CLI flags.

Skill Creator (OpenAI)

Mon, 01 Jan 0001 00:00:00 +0000

This system skill, auto-installed with Codex, scaffolds a new SKILL.md-compliant skill from a plain description of what it should do.

Why a skill for this

Getting a skill’s folder structure and frontmatter right by hand is easy to get subtly wrong. A scaffolding skill means authoring a new skill starts from a correct template instead of a blank file.

Google Antigravity Skills System

Mon, 01 Jan 0001 00:00:00 +0000

Google Antigravity’s skills system supports the same SKILL.md format as Claude Code and Codex, with both global (~/.gemini/config/skills/) and per-project (.agents/skills/) scopes.

Why a skill for this

Supporting the shared SKILL.md format means skills built for Antigravity aren’t locked to Google’s tooling — the same skill folder is portable to other compatible agents.

Gemini CLI Skills System

Mon, 01 Jan 0001 00:00:00 +0000

Gemini CLI natively supports the Agent Skills (SKILL.md) open standard, letting it load the same skill format used by Claude Code, Codex, and other compatible agents.

Why a skill for this

A shared skills format means a skill only has to be written once to work across Gemini CLI and other compatible agents, rather than maintaining separate versions per tool.

Grok Build Skills System

Mon, 01 Jan 0001 00:00:00 +0000

Grok Build’s skills system reads SKILL.md skills from .grok/skills/, ~/.grok/skills/, and plugin directories — and is directly Claude Code-compatible, reading .claude/skills and CLAUDE.md with zero extra configuration.

Why a skill for this

Direct compatibility with Claude Code’s own skill and config files means a project that’s already set up for Claude Code works in Grok Build without any migration step.