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

    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.

    SkillFlux sample check

    On 2026-10-31, SkillFlux pinned this source at commit 23e2428, drew a seeded sample of 20 from the 204 entries it contains, and ran static health check 1.0.0 on each. 40% had no failing check, said when to use the skill and carried a license.

    • 20/20sampled entries had a SKILL.md we could check
    • 0/20fail at least one check
    • 12/20do not say when to use the skill
    • 0/20have no license we could find
    • 0/20bundle scripts the agent may run
    • 0/20include scripts that call the network
    • 0/20include destructive shell commands
    • 5/20exceed the 5,000-token body guideline
    See the 20 sampled entries
    EntryResultFlags
    NeoLabHQ/context-engineering-kit/antigravity/skills/test-coverage13 pass, 2 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/plugins/fpf/skills/reset13 pass, 2 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/resolve-fixed-pr-comments14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/implement-task12 pass, 3 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/git-worktrees13 pass, 2 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/propose-hypotheses14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/query14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/update-docs11 pass, 4 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/reflect12 pass, 3 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/plugins/git/skills/attach-review-to-pr12 pass, 3 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/plugins/review/skills/review-local-changes15 pass, 0 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/write-tests15 pass, 0 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/git-notes15 pass, 0 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/kaizen14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/plugins/mcp/skills/setup-arxiv-mcp14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/fix-tests14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/plugins/kaizen/skills/kaizen14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/judge14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/antigravity/skills/prompt-engineering14 pass, 1 warn, 0 fail—
    NeoLabHQ/context-engineering-kit/skills/setup-arxiv-mcp14 pass, 1 warn, 0 fail—

    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

    • Developers tuning agent reliability.

    Use cases

    SkillFlux notes

    Install individual plugins and compare results on a task you repeat often.

    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 Context Engineering Kit source

    Limitations

    • Claims of improved quality are the maintainers'.

    Alternatives

    Related entries4 sources

    A web-based directory of agent plugins from official and community providers, rebuilt daily, where you can assemble a stack and install it with one script. The site is published on GitHub Pages.

    Skills + PluginsOpen-source reposGitHubOpen sourceGlobal
    View

    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.

    SkillsOpen-source reposGitHubOpen sourceGlobal
    View

    Seth Hobson's catalog shares one Markdown source of plugins, agents, skills and commands across Claude Code, Codex CLI, Cursor, OpenCode, Antigravity, Copilot and Pi, covering languages, review, testing, infrastructure and security.

    Skills + PluginsOpen-source reposGitHubOpen sourceGlobal
    View

    AWS Labs plugins and skills for Lambda, Step Functions, API Gateway, Amplify, serverless deployment, architecture diagrams and dataset work. The README points to the newer Agent Toolkit for AWS as the successor.

    Skills + PluginsOfficial vendorsGitHubOpen sourceGlobal
    View