Cline Skills

Cline, the open-source coding agent for VS Code, reads Agent Skills from its skills directory. SkillMD lists 1,081,265 safety-reviewed skills (SKILL.md files) you can use in Cline free: search by task, install with one command, or copy the file into ./.agents/skills.

Install a skill in Cline

  1. CLI (recommended). Install the CLI once, then add any skill to Cline by slug:
    npm i -g skillmds@latest
    skillmd add <owner>/<name> -a cline      # project scope → ./.agents/skills
    skillmd add <owner>/<name> -a cline -g   # global scope  → ~/.agents/skills
  2. Manual copy. Open any skill on SkillMD, download its SKILL.md, and save it as ./.agents/skills/<skill-name>/SKILL.md (or ~/.agents/skills/… for every project).
  3. MCP server. If Cline supports MCP servers, connect the SkillMD server and ask the agent to search and install skills for you. Setup details: MCP docs.

Machine-readable version of this guide: /agents/cline.txt

Top skills for Cline

emilkowalski
Apple Design
Translates Apple's fluid interface design principles—spring animations, direct manipulation, interruptibility, and velocity handoff—into web implementations using CSS, Pointer Events, and spring libraries like Motion/Framer Motion.
Audited 43.2k
emilkowalski
Improve Animations
Audits a codebase's animation and motion code, then produces a prioritized list of findings and self-contained implementation plans for other agents to execute.
Audited 43.2k
emilkowalski
Review Animations 2
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy, flagging issues with easing, duration, performance, and accessibility.
Audited 43.2k bundle
emilkowalski
Find Animation Opportunities
Sweeps a codebase or UI for places that would genuinely benefit from motion, applying a strict gate to reject over-animation, and proposes precise animation recipes without implementing them.
Audited 43.2k
heather
Robots Sitemap Validator
Check local robots.txt and sitemap.xml files for crawl-blocking mistakes. Use when someone asks to validate a sitemap, inspect robots.txt, or confirm whether local crawl files are safe to publish.
Audited
epistemedeus
Samedaydesk Machine Commerce
Discover SameDayDesk's twenty-two account-free machine services and produce a verified, non-spending purchase intent from the live OpenAPI contract and unpaid HTTP 402 challenge. Use to select and preflight public web extraction, company or wallet enrichment, repository security scans, JSON-LD generation, AI-search audits, Morpho risk analysis, work opportunities, agent-service discoverability, agent-surface context budgets, contract-qualified service search, seller integrity, x402 or MPP payment offers, Base or Solana transaction evidence, or delegated-wallet policy conformance before a separately authorized payment executor is involved.
younis-k
Skill Test
Provides a comprehensive set of design rules and anti-patterns to avoid AI-generated slop when building any interface.
Audited
user-2-3-4-5-6
Topic Intelligence
Find current creator or editorial topics from AI Workstation Global Topic Radar and turn one into an evidence-backed content brief with research questions, must_verify, avoid_claims, and visual requirements.
bundle
emilkowalski
Emil Design Eng 2
Provides design engineering guidance focused on animation principles, UI review, and interface craftsmanship.
43.2k
user-2-3-4-5-6
AI Open Source Intelligence
Use live AI Open Source Radar evidence to browse, discover, verify, compare, and select open-source AI projects or plan candidate stacks. Use for Radar rankings, project and license checks, alternatives, technology selection, stack planning, and Radar Skills browsing; not for general AI news or closed-source product research.
bundle
86606675
Orchestrate Research Evidence
Orchestrates evidence-based research across local PDFs, scholarly search, citation-context tools, web sources, and code repositories to produce traceable syntheses with counterevidence audits.
Audited
ruslan-strazhnyk
Agentic App Risk Review
Defensive review of an LLM/agent application for OWASP-LLM-style risks — prompt injection, unsafe tool calls, excessive agency, and PII/secret leakage. Reads your code, flags issues with file:line. Pure Claude Code, no signup.
1102tools
Igce Builder Ffp
Builds auditable firm-fixed-price IGCEs using BLS wages, layered fringe, overhead, G&A and profit, GSA CALC+ positioning, and GSA Per Diem travel data.
ruslan-strazhnyk
Form Validation Scan
Probe the forms on a page for validation gaps — missing required-field enforcement, no client-side validation, accepts malformed input, and absent error messaging. Reports per-field findings. Playwright MCP only, no signup.
1102tools
Market Research Workflow
Conducts evidence-supported federal acquisition market research and develops FAR Part 10 reports covering commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, and market conditions.
justhandledlabs
Ubrowser Setup Validator
Install, validate, or diagnose the upstream uBrowser MCP runtime and its local Playwright dependencies. Use for missing server files, MCP startup failures, tool-surface checks, or a clean uBrowser setup; do not use for ordinary browser automation.
info
Stop Senior Care Referral Cascade
Map and organize unwanted calls, texts, or emails after a U.S. senior-care referral inquiry by using GeezerKeeper's live public MCP for current network exit routes, separate provider jobs, unfilled request templates, duplicate-referral deadline facts, and current free or paid workflow fit. Use when a person asks why a senior-care marketplace or several providers are contacting them, how to opt out, how to prepare a stop-contact request, how to compare inquiry consequences before submitting a form, or how a senior-living professional should track direct-versus-network referrals. Do not use for emergencies, care placement, legal or medical advice, automatic sending, unknown-caller identity claims, or transmitting personal information.
1102tools
Acquisition Policy Workflow
Explains current FAR, DFARS, and agency-supplement policy; compares codified text, RFO model text, and agency deviations; traces rulemaking and public comments; and produces evidence-supported Acquisition Policy Impact Briefs.

Browse all skills →

Frequently asked questions

Where does Cline look for skills?

Cline loads Agent Skills from ./.agents/skills inside a project and from ~/.agents/skills globally. Each skill lives in its own folder as <skill-name>/SKILL.md; the agent reads the skill's description and applies it when a request matches.

How do I install a skill in Cline?

Run npm i -g skillmds@latest once, then skillmd add <owner>/<name> -a cline in your project (add -g for global scope). The CLI writes the SKILL.md into .agents/skills for you. You can also copy the file by hand from any skill page on skillmd.com.

Do skills made for Claude Code work in Cline?

Yes. SKILL.md is an open, agent-neutral format: the same file works across Claude Code, Cline, Cursor, Codex, and 60+ other agents. Only the directory it lives in changes, and skillmd add -a cline handles that for you.

Skills for other agents

Claude CodeCursorOpenAI CodexGemini CLIGitHub CopilotWindsurfRoo CodeAntigravityOpenCodeGooseAmpWarpKiro All agents →