SkillFlux

    ↑ ↓ select↵ openSearch all of SkillFlux
    Browse directory

    This page provides source information and editorial guidance. Recommendations and trust labels do not mean every skill here was tested. Results for individual skills are on the skill data pages. See skill data · Listing policy

    Overview

    Murat Can Koylan's open collection teaches context engineering and harness engineering: context fundamentals, compression, degradation, memory systems, evaluation and long-horizon prompting for production agent systems.

    SkillFlux sample check

    On 2026-10-31, SkillFlux pinned this source at commit 9ff0c99, drew a seeded sample of 19 from the 19 entries it contains, and ran static health check 1.0.0 on each. 74% had no failing check, said when to use the skill and carried a license.

    • 19/19sampled entries had a SKILL.md we could check
    • 1/19fail at least one check
    • 4/19do not say when to use the skill
    • 0/19have no license we could find
    • 13/19bundle scripts the agent may run
    • 1/19include scripts that call the network
    • 1/19include destructive shell commands
    • 3/19exceed the 5,000-token body guideline
    See the 19 sampled entries
    EntryResultFlags
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/context-fundamentals15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/context-degradation14 pass, 1 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/multi-agent-patterns15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/harness-engineering15 pass, 0 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/filesystem-context15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/latent-briefing15 pass, 0 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/hosted-agents15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/memory-systems14 pass, 1 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering11 pass, 3 warn, 1 failScripts contain rm -rf, sudo or similar, Bundles scripts the agent may run, Scripts call the network, Possible credential in files, Instructions match a risk pattern
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/long-horizon-prompting14 pass, 1 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/evaluation15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/self-managed-context14 pass, 1 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/advanced-evaluation14 pass, 1 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/context-optimization14 pass, 1 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/bdi-mental-states15 pass, 0 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/self-improvement-loops14 pass, 1 warn, 0 fail—
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/context-compression15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/tool-design15 pass, 0 warn, 0 failBundles scripts the agent may run
    muratcankoylan/Agent-Skills-for-Context-Engineering/skills/project-development15 pass, 0 warn, 0 failBundles scripts the agent may run

    The sample reads files only; it does not run any skill and does not describe entries outside the sample. Flags describe what a skill contains; they are not verdicts. Raw data · Method

    Best for

    • People designing agent systems rather than using one.

    Use cases

    SkillFlux notes

    Reads more like a course than a toolset; use it to inform your own skills.

    Installation and use

    Open the original repository and read its README, the selected skill instructions and any linked scripts. Check installation paths, host requirements, dependencies and licenses, then follow the project documentation to verify a small task in a workspace you can restore.

    Read the original Agent Skills for Context Engineering source

    Limitations

    • Conceptual; few skills perform a concrete task.

    Alternatives

    Related entries4 sources

    NeoLab's marketplace of context engineering techniques for Claude Code, OpenCode, Cursor and Antigravity, built from prompts its developers use daily and from benchmarked papers, with a small token footprint as a design goal.

    Skills + PluginsOpen-source reposGitHubOpen sourceGlobal
    View

    Android Skills is a skill repository published by the Android developer team on GitHub, focused on native Android development. Developers can inspect its files and instructions directly and compare them with their project’s Android stack before adopting relevant content.

    SkillsOpen-source reposOpen sourceGitHubGlobal
    View

    anthropics/skills is Anthropic’s public skill repository on GitHub, where readers can inspect capability files and implementations directly. It provides a first-hand reference for how skills are organized and a useful baseline when evaluating community resources.

    SkillsOpen-source reposOpen sourceGitHubGlobal
    View

    VoltAgent’s awesome-agent-skills brings vendor-team and community skill sources together in a curated GitHub list. Its scope is broader than a single agent, making it useful for comparing source types before checking each project’s host requirements, installation method and capability scope.

    SkillsOpen-source reposOpen sourceGitHubGlobal
    View