Agent skill

Verify Multilang Support

by johnhuang316 in johnhuang316/code-index-mcp

A skill your agent uses when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser…

MITAuto-check passedAgent Workflows

Install Verify Multilang Support

skills CLI
$ npx skills add johnhuang316/code-index-mcp --skill verify-multilang-support -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install johnhuang316/code-index-mcp verify-multilang-support --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/johnhuang316/code-index-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/verify-multilang-support .claude/skills/verify-multilang-support && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-multilang-support
GitHub stars
1k
Token cost
~908 tokens
SKILL.md length
348 words
Files
2 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser…

  • Works in 6 steps: Call set_project_path with the sample… → Call refresh_index, then build_deep_index. → Run the query with search_code_advanced… → …
  • Validating code-index-mcp language strategies
  • SKILL.md covers Overview, When to Use, Verification Loop and Targets, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Verify Multilang Support is an agent skill from johnhuang316/code-index-mcp. Use when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser and indexing changes.

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/baselines.md`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and Java. The repository describes itself as: A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup. The licence is MIT.

When your agent uses it

  • Validating code-index-mcp language strategies
  • Tree-sitter symbol extraction
  • Import baselines
  • Sample projects under test/sample-projects after parser and indexing changes

Example prompts

  • “/verify-multilang-support”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Call set_project_path with the sample project's absolute path.
  2. Call refresh_index, then build_deep_index.
  3. Run the query with search_code_advanced in literal mode.
  4. Call get_file_summary for the preferred file, then read
  5. Call get_symbol_body; require status: success and non-empty code.
  6. Record SEARCH, SUMMARY, SYMBOL_BODY, and FINAL. Any failed assertion makes

What it can do on your machine

Read from SKILL.md and the folder at commit d395cbf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify Multilang Support loads about 908 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 348 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~908
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from johnhuang316/code-index-mcp at commit d395cbf, republished under its MIT licence (© johnhuang316). 348 words, ~908 tokens.

Download SKILL.mdSave it as .claude/skills/verify-multilang-support/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
verify-multilang-support
description
Use when validating code-index-mcp language strategies, tree-sitter symbol extraction, called_by or import baselines, or sample projects under test/sample-projects after parser and indexing changes.

Verify Multi-Language Support

Overview

Verify search and deep indexing for every supported sample language. Non-empty results are insufficient; summaries must match maintained baselines.

When to Use

  • A language strategy, tree-sitter query, symbol range, indexer, or sample changes.
  • Search, summaries, symbol bodies, imports, or called_by may have regressed.

Run focused unit tests first when a specific failing strategy is known.

Verification Loop

Use each row in Targets, resolving paths below test/sample-projects.

  1. Call set_project_path with the sample project's absolute path.
  2. Call refresh_index, then build_deep_index.
  3. Run the query with search_code_advanced in literal mode.
  4. Call get_file_summary for the preferred file, then read the baselines and compare:
    • exact language
    • symbol_count at or above the minimum
    • every expected function, method, class, import, and called_by relationship
  5. Call get_symbol_body; require status: success and non-empty code.
  6. Record SEARCH, SUMMARY, SYMBOL_BODY, and FINAL. Any failed assertion makes the language FAIL.

After the final target, restore set_project_path to the repository root and call refresh_index.

Targets

LanguageRelative pathLiteral queryExpected symbolPreferred file
Pythonpythonclass UserManagercliuser_management/cli.py
Gogo/user-managementUserServiceCreateUserinternal/services/user_service.go
Javajava/user-managementclass UserManagerUserManager.createUsersrc/main/java/com/example/usermanagement/services/UserManager.java
JavaScriptjavascript/user-managementclass UserServiceUserService.createUsersrc/services/UserService.js
TypeScripttypescript/user-managementclass UserServiceusersrc/services/UserService.ts
C#csharp/ordersclass OrderServiceOrders.Services.OrderService.Createsrc/Orders/Services/OrderService.cs
Kotlinkotlin/notes-apiclass NotesServiceNotesService.createNotesrc/main/kotlin/com/example/notes/NotesService.kt
Rustrust/conversationstruct ConversationConversation.appendsrc/conversation.rs
Objective-Cobjective-cinterface UserManagerUserManager.addUserUserManager.m
Zigzig/code-index-examplefn mainmainsrc/main.zig

Behavior Smoke Checks

After the language loop:

  • Search get.*Data with regex disabled and confirm literal behavior.
  • If regex is available, repeat with it enabled and confirm regex behavior.

Report these separately from the language table.

Failure Triage

Report the failed check and actual versus expected value, then read the sample:

  • If the sample legitimately changed, update references/baselines.md.
  • Otherwise, treat it as an indexer or language-strategy regression.

Do not weaken or delete a baseline merely to make verification pass.

Common Mistakes

  • Using a stale or cross-project file path.
  • Skipping deep indexing before inspecting summaries.
  • Treating one search hit as full language support.
  • Forgetting that Objective-C files sit directly under objective-c/.
  • Leaving the MCP server pointed at a sample project after verification.

© johnhuang316, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/verify-multilang-support of johnhuang316/code-index-mcp.

  • SKILL.md
  • references/baselines.md

Open the folder on GitHubat commit d395cbf

Compare with similar skills

Verify Multilang Support next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify Multilang Support compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify Multilang Support this skilljohnhuang316/code-index-mcp1k—~908Automated safety check: PassMIT
Amplicode InstallAmplicode/spring-skills128—~2.6kAutomated safety check: PassNone
Creator Tools CLIMojang/minecraft-creator-tools161—~1.1kAutomated safety check: PassCustom licence
Eclipse Editgradusnikov/eclipse-chatgpt-plugin172—~1.1kAutomated safety check: PassMIT
Edt MCP ArchitectureDitriXNew/EDT-MCP296—~1.2kAutomated safety check: PassAGPL-3.0
Dto CreatorAmplicode/spring-skills128—~7.5kAutomated safety check: PassNone

Similar skills

  • Amplicode Install

    Amplicode/spring-skills

    Installs the Amplicode IntelliJ plugin into IntelliJ IDEA (Ultimate/Community) and GigaIDE on the user's machine.

    128 GitHub stars~2.6k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Creator Tools CLI

    Mojang/minecraft-creator-tools

    Run the Minecraft Creator Tools command line (mct, the @minecraft/creator-tools npm package) for Minecraft Bedrock Edition add-ons.

    161 GitHub stars~1.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Eclipse Edit

    gradusnikov/eclipse-chatgpt-plugin

    Edit files in Eclipse projects using MCP tools. An agent skill from gradusnikov/eclipse-chatgpt-plugin.

    172 GitHub stars~1.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Edt MCP Architecture

    DitriXNew/EDT-MCP

    Map of the EDT-MCP plugin's target architecture — where the shared helpers live, the layering rules, and the canonical way to do project/metadata/code resolution.

    296 GitHub stars~1.2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Dto Creator

    Amplicode/spring-skills

    Creates a DTO (Data Transfer Object) class for an entity. An agent skill from Amplicode/spring-skills.

    128 GitHub stars~7.5k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Langchain4j MCP Server Patterns

    giuseppe-trisciuoglio/developer-kit

    Provides LangChain4j patterns for implementing MCP (Model Context Protocol) servers, creating Java AI tools, exposing tool calling capabilities, and integrating MCP clients with AI services.

    357 GitHub stars~1.6k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check: notes

More from johnhuang316/code-index-mcp

  • Release Prep

    johnhuang316/code-index-mcp

    A skill your agent uses when code-index-mcp implementation is complete and a version bump, release notes, tag, package publication, or GitHub release is being prepared.

    1k GitHub stars~680 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Verify Multilang Support

What does Verify Multilang Support do?

A skill your agent uses when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser…. Verify Multilang Support is an agent skill from johnhuang316/code-index-mcp. Use when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser and indexing changes.

When should I use Verify Multilang Support?

Verify Multilang Support fits situations like: validating code-index-mcp language strategies; tree-sitter symbol extraction; import baselines; sample projects under test/sample-projects after parser and indexing changes.

How do I install Verify Multilang Support in Claude Code?

Run `npx skills add johnhuang316/code-index-mcp --skill verify-multilang-support -a claude-code`. Or copy the skill folder (.agents/skills/verify-multilang-support in johnhuang316/code-index-mcp) into .claude/skills/verify-multilang-support in your project. Claude Code loads it when a task matches its description.

How do I install Verify Multilang Support in Codex?

Run `npx skills add johnhuang316/code-index-mcp --skill verify-multilang-support -a codex`. Or copy the skill folder (.agents/skills/verify-multilang-support in johnhuang316/code-index-mcp) into .agents/skills/verify-multilang-support in your project. Codex loads it when a task matches its description.

Can I use Verify Multilang Support in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add johnhuang316/code-index-mcp --skill verify-multilang-support -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-multilang-support, .gemini/skills/verify-multilang-support, .github/skills/verify-multilang-support and .opencode/skills/verify-multilang-support in your project.

What does Verify Multilang Support need to run?

SKILL.md names no scripts, command-line tools or credentials: Verify Multilang Support is instructions for the agent only. Our summary lists: Python 3.

Does Verify Multilang Support access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Verify Multilang Support safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verify Multilang Support use?

Verify Multilang Support is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify Multilang Support use?

About 908 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Verify Multilang Support?

Skills that share tags, products or a category with Verify Multilang Support: Amplicode Install (Amplicode/spring-skills, 128 stars), Creator Tools CLI (Mojang/minecraft-creator-tools, 161 stars), Eclipse Edit (gradusnikov/eclipse-chatgpt-plugin, 172 stars) and Edt MCP Architecture (DitriXNew/EDT-MCP, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Multilang Support?

johnhuang316 (a GitHub user) maintains it in johnhuang316/code-index-mcp, which has 1,002 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 27, 2026.

Source: johnhuang316/code-index-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.