{"skills":[{"name":"tanker/frontend-design","owner":"tanker","visibility":"public","currentVersion":"2","description":"Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.","updatedAt":"2026-07-13T16:38:51.441Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":1,"viewCount":20,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/frontend-design@main"},{"name":"skl/skl","owner":"skl","visibility":"public","currentVersion":"4","description":"Use the skl CLI to publish, install, and manage reusable Agent Skills across\nAI coding agents (Claude, Copilot, Cursor, Gemini, Junie, Kiro, plus the\ncross-agent .agents/skills standard used by Codex, Zed, Goose, Amp, OpenCode,\nRoo, pi, and Grok) — \"the Agent Skills manager.\" Trigger whenever the user\nwants to install/add/remove/publish/save/share or \"set up\" Agent Skills\n(packaged skills in folders like .claude/skills, .cursor/skills,\n.agents/skills), or check installed-skill health — even if they never type\n`skl`.\n\nTypical intents:\n- land/install the skills a skl.json manifest lists (e.g. after cloning a repo)\n- add/remove a named skill (often user/skill-name) + update the manifest and\n  each agent's skills folder\n- install a skill for the whole machine (user-level, `-g`) instead of one project\n- publish/push a local skill folder so others can grab it, or save it privately\n- install a skill straight from a GitHub repo URL\n- log in to useskl.com or a skl server to publish/fetch\n- scan a project for out-of-date or modified skills\n\nNot for writing a skill's content (use skill-creator) or unrelated package\nmanagers (npm/pip/etc.).","updatedAt":"2026-07-11T21:11:38.251Z","starCount":1,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":85,"viewCount":471,"license":"MIT","importedFrom":"github:loopdoop/skl-skill/skl@main"},{"name":"skl/canvas-design","owner":"skl","visibility":"public","currentVersion":"1","description":"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.","updatedAt":"2026-07-01T01:19:15.573Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":32,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/canvas-design@main"},{"name":"skl/brand-guidelines","owner":"skl","visibility":"public","currentVersion":"1","description":"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.","updatedAt":"2026-07-01T01:18:43.703Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":20,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/brand-guidelines@main"},{"name":"skl/karpathy-guidelines","owner":"skl","visibility":"public","currentVersion":"1","description":"Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.","updatedAt":"2026-07-01T01:15:08.429Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":7,"license":"MIT","importedFrom":"github:multica-ai/andrej-karpathy-skills/skills/karpathy-guidelines@main"},{"name":"skl/skill-creator","owner":"skl","visibility":"public","currentVersion":"1","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","updatedAt":"2026-07-01T01:13:37.562Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":10,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/skill-creator@main"},{"name":"skl/frontend-design","owner":"skl","visibility":"public","currentVersion":"1","description":"Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.","updatedAt":"2026-07-01T01:12:55.084Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":7,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/frontend-design@main"},{"name":"skl/claude-api","owner":"skl","visibility":"public","currentVersion":"2","description":"Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","updatedAt":"2026-07-01T01:09:39.143Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":2,"viewCount":85,"license":"Apache-2.0","importedFrom":"github:anthropics/skills/skills/claude-api@main"},{"name":"tanker327/team","owner":"tanker327","visibility":"public","currentVersion":"4","description":"Decide whether a task warrants a multi-agent team and, if so, design it (roles, per-agent models, file ownership, task waves) and get user approval before launching. Use when the user wants work split across several parallel Claude agents/teammates — e.g. \"agent team\", \"swarm\", \"throw a team of claudes at this\", \"split this across agents\", \"multi-agent workflow\" — or describes work that benefits from parallel agents even without naming them: a multi-layer feature (backend/frontend/data/tests) built concurrently; a large migration, audit, or refactor spanning many independent files/modules/services; a multi-perspective code or architecture review (e.g. security + performance + tests at once); or competing-hypotheses debugging where several theories are investigated in parallel and challenged. Treat these as a cue to plan a team, not to work solo. Do NOT use for single-file, small, or tightly sequential work, debugging one known error, building an AI \"agent\" product (Agent SDK), Docker/infra \"swarm\" clusters, bulk email to \"agents\", or human/game \"team composition\".","updatedAt":"2026-06-21T00:20:37.069Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":1,"viewCount":15,"license":null,"importedFrom":null},{"name":"tanker/skill-creator","owner":"tanker","visibility":"public","currentVersion":"0.1","description":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","updatedAt":"2026-06-16T03:09:23.374Z","starCount":0,"viewerHasStarred":false,"forkCount":0,"forkedFrom":null,"downloadCount":0,"viewCount":16,"license":"Apache-2.0","importedFrom":null}],"page":1,"pageSize":24,"hasMore":false}