agentleFS
Sign inStart free
AresWeiAresWei/all-in-one-skill/skills/ALL-IN-ONE/SKILL.md

ALL-IN-ONE

Skill0 starsChanged 5 months agoMITView on GitHub

Use when starting any task that may need skills, plugins, connectors, MCP tools, or automatic capability routing

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. omdenkar2-ui/all-in-one★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when a task may need more than one capability, an explicit skill/plugin/app is mentioned, or the correct tool path is not obvious.

    line 16
  2. Distinctive:

    Do not use for trivial single-step answers, simple shell lookups, or tasks where a higher-priority instruction already names the exact …

    line 18
  3. Distinctive:

    Do not load all skills or plugin docs into context.

    line 48
  4. Distinctive:

    Do not install, enable, or invoke unavailable plugins by assertion.

    line 49
  5. Distinctive:

    Do not bypass user instructions, AGENTS.md, system/developer rules, permissions, sandboxing, Plan Mode, safety policy, or tool schemas.

    line 50
  6. Distinctive:

    Do not use file reads instead of proper skill/tool activation.

    line 51
  7. Distinctive:

    Do not keep searching once the relevant capability set is clear.

    line 52
  8. Distinctive:

    When using this skill, start with one concise status line:

    line 56
  9. Very specific:

    Keep it short. Use none for empty slots.

    line 62
  10. Distinctive:

    Use these checks when editing this skill:

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ALL-IN-ONE

Overview

Capability router for the current task. Select the smallest relevant set of skills, plugin tools, connectors, and MCP capabilities.

Core rule: route first, then act. Never claim a skill, plugin, connector, or tool is available until the runtime exposes it.

When to Use

Use when a task may need more than one capability, an explicit skill/plugin/app is mentioned, or the correct tool path is not obvious.

Do not use for trivial single-step answers, simple shell lookups, or tasks where a higher-priority instruction already names the exact skill or tool.

Routing Contract

  1. Identify the goal, explicit mentions, files, apps, plugins, current mode, repo context, and higher-priority constraints.
  2. Select process skills before domain skills:
    • Planning/spec: planning, brainstorming, writing-plans, project-planner.
    • Debugging/fixing: systematic-debugging, test-driven-development, verification-before-completion.
    • Skills: writing-skills plus test-driven-development.
    • Frontend/product UI: frontend-design, interaction-design, web framework skills.
  3. Select domain skills and tools only when the task calls for them:
    • GitHub/PR/CI/review: GitHub skills/tools.
    • Drive/Docs/Sheets/Slides: Google Drive skills/connectors.
    • OpenAI API/key/platform: OpenAI developer/platform skills/tools.
    • Reports/dashboards/charts: data analytics and artifact tools.
    • Images/video/design: image, Canva, Figma, creative production, HeyGen, invideo, HyperFrames.
    • Web apps/deployments: frontend, Next.js, Vercel, Supabase, Stripe.
  4. Discover plugins, connectors, and MCP tools before use. Request plugin installation only for an exact user request and an available candidate.
  5. Announce selected capabilities briefly, then follow their instructions exactly. If none match, say so and use base tools.

Runtime Discovery

RuntimeDiscovery path
CodexUse tool_search for deferred plugin, connector, and MCP tools.
Claude/Copilot/GeminiUse the runtime's native skill/plugin activation or discovery tool.
UnknownState the limitation and continue with exposed base tools.

Hard Limits

  • Do not load all skills or plugin docs into context.
  • Do not install, enable, or invoke unavailable plugins by assertion.
  • Do not bypass user instructions, AGENTS.md, system/developer rules, permissions, sandboxing, Plan Mode, safety policy, or tool schemas.
  • Do not use file reads instead of proper skill/tool activation.
  • Do not keep searching once the relevant capability set is clear.

Output Shape

When using this skill, start with one concise status line:

Using ALL-IN-ONE to route this task: process=[...]; domain=[...]; tools=[...]; unavailable=[...]; reason=[...].

Keep it short. Use none for empty slots. If discovery fails, say what was unavailable and use the best safe fallback.

Validation Scenarios

Use these checks when editing this skill:

ScenarioExpected routing
"Fix this frontend bug and open a PR"Debugging/TDD/verification, frontend if relevant, GitHub only if available
"Analyze this Google Sheet and build a dashboard"Google Drive/Sheets, data analytics, artifact tools
"Create a new skill"writing-skills plus test-driven-development background
"Generate an image"image generation/editing capability, no unrelated coding skills
"Use a plugin that is not installed"Discover candidates; request install only for an exact explicit plugin request

Pass means relevant routing without full-context loading.

Common Mistakes

MistakeCorrection
"ALL-IN-ONE means load everything"It means route to the smallest relevant set.
Assuming a plugin existsDiscover it through available tooling first.
Treating installation as automaticRequire an exact user request and available candidate.
Skipping process skillsLoad them before domain skills.
Ignoring higher-priority instructionsHigher-priority instructions always win.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free