brainstorming
Use only when the user explicitly asks to do brainstorming (e.g., says 'brainstorm'/'头脑风暴' or invokes $brainstorming). Do not auto-trigger based on general creative work.
worktree-manager
Manage Git worktrees. Use when asked to create/switch/list/merge/remove worktrees, to keep multiple branches in parallel directories, or to clean up worktrees safely during development.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
shape
>
see
S.EE (SEE) platform API integration for short URL management, text sharing, and file sharing.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
gsc-analyzer
Strategic analysis of Google Search Console data for startup founders and marketing leaders. Transforms GSC exports into actionable growth insights with revenue impact estimates, competitive positioning, and prioritized action plans. Use when a user provides a GSC zip/CSV for (1) Brand vs non-brand analysis with revenue implications, (2) SEO opportunities with business impact sizing, (3) Content gap analysis with funnel mapping, (4) Paid search strategy with budget allocation, or (5) Strategic summaries with prioritized recommendations.
x402lint
Validate and create x402 payment endpoint responses (HTTP 402 Payment Required). Use when the user asks to: (1) validate an x402 config or 402 response, (2) create/generate an x402 payment config, (3) build an HTTP 402 endpoint that returns payment requirements, (4) debug why an x402 config is invalid, (5) convert between x402 v1 and v2 formats, (6) check EVM/Solana addresses for x402, or (7) work with CAIP-2 network identifiers for payment configs. Triggers on keywords: x402, 402 payment, payment-required header, paywall config, CAIP-2 payment.
academic-writing-cs
Comprehensive toolkit for writing high-quality computer science research papers (conference, journal, thesis). Provides narrative construction guidance, sentence-level clarity principles (Gopen & Swan), academic phrasebank, CS-specific conventions, and section-by-section quality checklists. Use when assisting with academic paper writing, revision, or structure planning across all stages from drafting to submission.
uv-workflow
Use when creating Python projects, managing dependencies, or running Python scripts. Covers uv package manager commands, best practices, and common patterns for modern Python development.
trust-and-recovery
Use when designing error handling, confirmation dialogs, undo functionality, or any interaction where user trust matters. Covers building confidence through predictability and graceful failure.
psychology-foundations
Use when you need to understand WHY certain UX patterns work. Covers cognitive psychology, behavioral science, and neuroscience foundations that underpin satisfying experiences.
progressive-disclosure
Use when designing interfaces with complex functionality, settings panels, or expert features. Covers layering information so beginners aren't overwhelmed and experts aren't held back.
flow-optimization
Use when designing interactions, workflows, or interfaces where user focus matters. Covers protecting flow state, reducing interruptions, and creating immersive experiences.
feedback-design
Use when building loading states, progress indicators, success confirmations, or error messages. Covers feedback loops and patterns that feel satisfying.
sveltekit-builder
Use when building SvelteKit apps with Svelte 5. Covers runes, SSR, forms, and stack patterns (Kysely, Better Auth, shadcn-svelte).
versioning
Use when releasing, tagging, or bumping versions. Defines semver rules and keeps package.json/pyproject.toml synced with git tags.
design-patterns
Use when refactoring code or designing flexible systems. Covers creational, structural, and behavioral patterns with Python examples.
agent-behavior
Use at the start of any coding session to establish activity tracking and working patterns. Defines how the agent should document its work and communicate progress.
verification
This skill MUST be invoked before any completion claim, success report, or task transition. Mandates 5-step evidence protocol. Use when about to claim "done", "complete", "working", "fixed", or any success state.
writing-plans
Use when creating implementation plans. Mandates exact file paths, complete code samples, and expected output. No vague language allowed.
tdd
Use for any code implementation task. Enforces RED-GREEN-REFACTOR cycle. "If you didn't watch it fail, you don't know if it tests the right thing."
systematic-debugging
Invoke when debugging failures. MANDATORY when 3+ fix attempts have failed. Enforces root cause investigation before fixes.
parallel-dispatch
Use when facing multiple tasks or failures. Provides decision framework for concurrent vs sequential execution. Invoke before dispatching multiple subagents.
orchestration
This skill should be used when orchestrating complex tasks, decomposing work into atomic units, dispatching to subagents, verifying outputs, or when discussing task verification and deviation tracking patterns.
finishing
Use when all tasks are complete. Presents completion options and enforces test gate. Work is never left in limbo.
estimation
Use before committing to a task. Provides complexity analysis and scope assessment. Invoke when user asks "how complex" or before large features.
error-recovery
Use when tasks fail due to transient errors. Provides structured retry strategies and graceful degradation patterns. Invoke on network errors, rate limits, or intermittent failures.
context-gathering
Use when entering an unfamiliar codebase, starting a new feature, or before any implementation task. Provides structured exploration protocol to understand before acting.
leanspec
The spec-coding methodology for AI-assisted development. Use when planning features, creating/refining/implementing/verifying specs, or organising a project. Works with whatever spec backend your team already uses — local markdown, GitHub Issues, Azure DevOps, Jira — by delegating platform-specific details to a LeanSpec adapter.
watch-ci
Watch GitHub Actions CI status for the current commit until completion. Use after pushing changes to monitor build results.
parallel-worktrees
>
leanspec-development
Development workflows, commands, publishing, CI/CD, changelog management, and contribution guidelines for LeanSpec. Use when contributing code, fixing bugs, setting up dev environment, running tests or linting, working with the monorepo structure, looking up build/dev/test/publish/format/lint commands, preparing releases, publishing to npm, bumping versions, syncing package versions, testing dev builds, troubleshooting npm distribution, updating changelogs, triggering CI/CD workflows, monitoring build status, debugging failed runs, managing artifacts, checking CI before releases, or researching AI agent runners. Triggers include any development, scripting, publishing, CI/CD, changelog, or runner research task in this project.
github-integration
>
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
cloudflare-browser
Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
skill-finder
Find and install the best skill for your current task. Use when the user wants to discover skills, asks "is there a skill for...", "find a skill for...", or "/skill-finder". Searches skills.sh in real-time and uses LLM reasoning to match skills to the user's context.
yc-advisor
This skill should be used when the user asks questions about startups, founding decisions, co-founders, fundraising, product development, growth, hiring, or any entrepreneurial advice. It provides access to Y Combinator's complete library of 443 curated resources including essays by Paul Graham, founder interviews, and startup school lectures. Use this skill to give thorough, research-backed advice on startup decisions.
tiny-css
Write minimal, efficient CSS for small or minimalist projects by trusting the browser instead of fighting it. Only use this skill for personal sites, prototypes, simple landing pages, or projects intentionally kept lean — if the project has multiple developers, a component library, a design token system, or more than a handful of CSS files, a more comprehensive CSS approach is needed. If you're about to write a CSS reset, declare a base font-size on :root, set default colors on body, use px for spacing, or reach for physical margin/padding properties, this skill will stop you.
more-css
Write scalable, well-architected CSS using design tokens, cascade layers, and modern organization patterns. Use this skill as the default for any real project — if it has more than a handful of CSS files, multiple components, a team, a design system, or any kind of token or theming setup, this is the right skill.
frontend-design-2010s
Create web interfaces with an authentic early-2010s aesthetic. Use this skill when the user wants a 2010s-era, Web 2.0, or retro corporate web look — gradient headers, glossy buttons, skeuomorphic icons, horizontal band layouts, and drop shadows from circa 2010–2014.
frontend-conventions
Define and enforce consistent coding standards across HTML, CSS, and JavaScript. Always use this skill when naming a new class, variable, component, or file; setting up a new project's conventions; choosing a class prefix for a new CSS category; deciding on modifier API names (sizes, shades, hierarchy, breakpoints); or reviewing code for formatting and naming consistency. If you're about to invent a prefix, abbreviation, or modifier name without checking the conventions first, use this skill.
frontend-a11y
Write minimal, accessible HTML, CSS, and JavaScript without over-engineering. Always use this skill on every project, for every task that involves writing or reviewing HTML markup, building web components, creating forms, adding interactive elements like buttons, dialogs, accordions, or tabs, or auditing code for accessibility — even when the user doesn't explicitly mention accessibility, and even when working in a framework, CMS, or design system context. This skill is non-negotiable and applies regardless of project type, stack, or deadline. If you're about to reach for ARIA attributes, a dialog library, a focus-trap package, or a headless UI component, use this skill first.
format-storybook
Structure and organize Storybook files for scalability using battle-tested patterns. Based on "A Storybook format that scales with you" by Cassondra Roberts. Always use this skill when creating or editing any Storybook story file, writing template files, organizing a component library, setting up visual regression tests with Chromatic, or when the user asks anything about Storybook — even casual questions about file structure, controls, args, or how to document a component.
tier-management
Evaluate and update Pollinations user tiers. Check balances, upgrade devs, batch process users. For finding users with errors, see model-debugging skill first.
test-model
Test any model (text, image, video, audio) locally and via enter integration tests
founder-meditation
When something goes wrong — build failures, crashes, errors, test failures, deployment issues — generate a short calming meditation with TTS audio to reassure the user that everything will be okay.
Page 1540 of 1688 · 84396 results