engneer-hamachan/mruby-ti/ti-install-sig

Claude Code and agent skill by engneer-hamachan/mruby-ti

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Load project-specific mruby class and method signatures into context using the ti type checker

Install

npx vskill@latest install engneer-hamachan/mruby-ti/ti-install-sig

SKILL.md

You load the classes and method signatures relevant to the current task into your context using the ti type checker.

Why This Is Needed

In mruby development, the available classes and methods vary per project. This skill lets you discover and internalize the project's type landscape before implementing anything, so you can work with accurate type knowledge.

Usage

The user will invoke this skill with a prompt describing the task: ti-install-sig {prompt}

Available Commands

Code understanding (current file)
  • ti filename.rb --llm-nav - List classes and top-level methods that have callers or callees in the code
  • ti filename.rb --llm-nav --target=Name - Display detailed signatures, callers/callees for a specific class or method in the code
API reference (available features in the type system)
  • ti filename.rb --llm-class - List all classes available in the project
  • ti filename.rb --llm-define --class=ClassName - Display method signatures and type info for a class

IMPORTANT: Always run these commands as-is. Never pipe through head, tail, or any other truncation tool. The full output is required — partial output leads to missing call points and incomplete understanding.

Workflow

Step 1: Review the prompt

Understand what the user is trying to implement and what kinds of types might be involved.

Step 2: Browse the code structure

Run ti {target_file.rb} --llm-nav first. It lists classes and top-level methods that are actively used in the code. Identify which ones are relevant to the task.

Step 3: Drill into relevant targets

For each relevant class or method identified in Step 2, run:

bash
ti {target_file.rb} --llm-nav --target=Name

This gives you method signatures, callers/callees, file locations, and document: fields. Use this to understand what types are already in use and what additional classes you need to load.

Step 4: Load API reference for relevant classes
  1. Run ti {target_file.rb} --llm-class to see all available classes in the project.
  2. Select relevant classes — from the class list, pick the classes that are likely needed for the task. Consider both what you saw in --llm-nav output and what the prompt requires.
  3. Run ti {target_file.rb} --llm-define --class={class} for each selected class to retrieve detailed method signatures and type information.

Be selective: only pick classes that are clearly relevant to the task. Loading too many is noisy; loading too few means missing needed context.

Step 5: Report completion

Once all selected classes have been loaded, inform the user that the signatures are ready and summarize what was loaded.

Notes

  • If the target file is not specified in the prompt, ask the user which file to use as the ti target.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
70
Repository forks
2
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/engneer-hamachan/mruby-ti/ti-install-sig/badge)](https://verified-skill.com/skills/engneer-hamachan/mruby-ti/ti-install-sig)

Something wrong with this skill or its page? Tell us.