SkillFlux

    ↑ ↓ select↵ openSearch all of SkillFlux
    Browse directory
    Aspectanthropics/skillsawesome-claude-skills (travisvn)
    Main purposeOfficial Anthropic skill examplesClaude skill list and architecture reference
    Source typeOpen-source repos · Open-source skill repositoryOpen-source repos · Open-source skill repository
    Use casesCoding & development, Find the right skillFind the right skill, Coding & development
    LanguageEnglishEnglish
    PricingFreeFree
    Best forDevelopers learning skill structure and requirements from original files. Teams seeking first-hand examples before writing or evaluating their own skills.Developers learning skill structure before exploring Claude-oriented candidates.
    LimitationsAn official source does not replace validation against your agent, project and permission configuration. Read each item’s license and dependency notes rather than assuming identical conditions throughout the repository.The list and architecture explanation do not replace host documentation or establish identical structure across linked projects.
    SkillFlux sample84% clean · 1/19 fail at least one check · 1/19 do not say when to use the skill · 1/19 have no license we could find95% clean · 0/20 fail at least one check · 0/20 do not say when to use the skill · 1/20 have no license we could find

    anthropics/skills: SkillFlux note

    Start with one directory relevant to your task. Read its main instructions, then inspect linked scripts and reference files. Recording triggers, inputs, outputs and dependencies makes it easier to judge whether that example belongs in your workflow.

    Visit anthropics/skills ↗

    awesome-claude-skills (travisvn): SkillFlux note

    Read the architecture explanation and compare it with the file layout of one linked project. Conceptual material can guide your reading, while the format and loading behavior of a specific version should be checked against the host and project documentation.

    Visit awesome-claude-skills (travisvn) ↗

    "Clean" is the share of sampled entries with no failing check, a "when to use" description and a license. Sampling reads files only and does not show whether a skill works. Method