SkillFlux

    ↑ ↓ select↵ openSearch all of SkillFlux
    Browse directory
    Aspectanthropics/skillsScientific Agent Skills
    Main purposeOfficial Anthropic skill examplesAppraise scientific evidence and prioritize traceable research directions
    Source typeOpen-source repos · Open-source skill repositoryOpen-source repos · Scientific agent skill repository
    Use casesCoding & development, Find the right skillCoding & development, Content & writing, Planning & long tasks
    LanguageEnglishEnglish
    PricingFreeFree
    Best forDevelopers learning skill structure and requirements from original files. Teams seeking first-hand examples before writing or evaluating their own skills.Researchers who need to locate evidence behind a paper or scientific claim and distinguish risk of bias from certainty of evidence. Research teams choosing directions who need to preserve dissent, evaluation reasons and follow-up validation tasks.
    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.Core analytical guidance works offline. Optional brainstorming utilities need Python 3.11+ and check structure or scoring records, not scientific truth. Diagram support needs Python, requests, an OpenRouter key and network access, and sends content to an external service. It produces PNG drafts whose labels and relationships need human checking; idea scores do not replace validation or expert review.
    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 find65% clean · 0/20 fail at least one check · 7/20 do not say when to use the skill · 0/20 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 ↗

    Scientific Agent Skills: SkillFlux note

    The analysis covers the two main skills and the scientific-schematics support skill, based on their instructions, references, scripts and MIT licenses at a pinned snapshot, without behavioral testing. It is not a scientific finding or an execution test; Python packages and external APIs must be prepared separately.

    Visit Scientific Agent Skills ↗

    "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