agentleFS
Sign inStart free
yaqob3653yaqob3653/vlypse-skills/skills/vlypse-guide/SKILL.md

vlypse-guide

Skill1 starsChanged 6 days agoMITView on GitHub

Comprehensive guide and quick reference for Vlypse IDE, runtime environment, planning mode, and building modern web applications.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a task involves multi-step architectural changes or high-risk modifications:

    line 18
  2. Very specific:

    Research: Read only necessary files using view_file or grep_search.

    line 20
  3. Very specific:

    Plan: Create implementation_plan.md in the brain directory.

    line 21
  4. Distinctive:

    Stop & Wait: Ask the user to review the plan and click Proceed before touching any code.

    line 22
  5. Very specific:

    Execute: Create task.md with checklist items ([ ], [/], [x]).

    line 23
  6. Very specific:

    Verify: Run tests or build commands, then summarize accomplishments in walkthrough.md.

    line 24

≈ “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

Vlypse IDE Guide

This skill provides a comprehensive guide for working within Vlypse IDE, understanding the runtime environment, slash commands, planning workflows, and project best practices.

Key Capabilities

  • Direct Workspace Access: Vlypse executes actions directly on the user's workspace using standard terminal commands and file manipulation tools.
  • Isolated AppData Brain: Complex plans (implementation_plan.md), task tracking (task.md), walkthroughs (walkthrough.md), and temporary scratch scripts are isolated in .vlypse/brain/<conversation-id>/ to keep the user's workspace pristine.
  • Lightweight Skills System: Specialized playbooks loaded only when needed via view_file. Full instructions are never stuffed into prompt prefixes, preserving 100% prompt cache efficiency.

Planning Mode Workflow

When a task involves multi-step architectural changes or high-risk modifications:

  1. Research: Read only necessary files using view_file or grep_search. Do NOT modify code yet.
  2. Plan: Create implementation_plan.md in the brain directory. Mark files as [NEW], [MODIFY], or [DELETE]. Set RequestFeedback: true.
  3. Stop & Wait: Ask the user to review the plan and click Proceed before touching any code.
  4. Execute: Create task.md with checklist items ([ ], [/], [x]). Update it progressively as you work.
  5. Verify: Run tests or build commands, then summarize accomplishments in walkthrough.md.

Slash Commands Reference

  • /plan: Trigger structured planning before making changes.
  • /goal: Run long-running, autonomous tasks with extra thoroughness.
  • /compact: Compact conversation context when history grows long.
  • /learn: Save persistent project rules or preferences for future sessions.
  • /boost: Deep thinking and multi-perspective verification for complex problems.

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