SKILL·9D1C12

go-semantic-tools

eduardo-sl
Updated Yesterday
63
9
63
View on GitHub
Documentationwordaiapi

About

This skill helps developers semantically analyze Go codebases using the official toolchain instead of text search. It leverages gopls for references and implementations, go list for dependency graphs, and go doc for API exploration. Use it for tasks like finding callers, tracing dependencies, or mapping module usage before making changes.

Quick Install

Claude Code

Recommended
Primary
npx skills add eduardo-sl/go-agent-skills -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/eduardo-sl/go-agent-skills
Git CloneAlternative
git clone https://github.com/eduardo-sl/go-agent-skills.git ~/.claude/skills/go-semantic-tools

Copy and paste this command in Claude Code to install this skill

Documentation

Go Semantic Tools

grep finds strings; the toolchain finds meaning. Method names repeat across types, interfaces are satisfied implicitly, and dot-imports lie to text search. Before changing shared code, get the truth from tools that understand types.

1. Choose the Tool

QuestionCommand
Where is this symbol used?gopls references file.go:LINE:COL
Where is it defined?gopls definition file.go:LINE:COL
Who implements this interface? / which interfaces does this type satisfy?gopls implementation file.go:LINE:COL
Who calls this function (transitively)?gopls call_hierarchy file.go:LINE:COL
What's in this package's API?go doc ./internal/service / go doc pkg Symbol
Which packages exist / depend on what?go list ./..., go list -deps, go list -json
Find a symbol by name across the modulegopls workspace_symbol Name
Symbols in one filegopls symbols file.go

Positions are file.go:line:column (1-based). Get line/column from a prior search or gopls symbols. All gopls commands run from within the module and need a warm build cache — run go build ./... once first.

2. Standard Investigation Flows

Before changing a function

gopls references internal/service/user.go:42:6   # every call site, typed
gopls call_hierarchy internal/service/user.go:42:6

Text search for Process( would surface every type's Process; references returns only this one's call sites — including usages via interfaces and embeddings that grep cannot see.

Mapping an interface

# On the interface name: all implementations
gopls implementation internal/store/store.go:15:6

# On a method of a concrete type: interfaces it satisfies
gopls implementation internal/store/postgres/user.go:30:18

Run this before adding a method to an interface — every implementation listed will break.

Understanding the dependency graph

go list ./...                                    # all packages
go list -f '{{.ImportPath}} -> {{join .Imports " "}}' ./... # direct edges
go list -deps ./cmd/api | grep myorg             # everything a binary pulls in
go list -json ./internal/service | jq .Imports   # machine-readable

Use this to verify layering claims ("domain imports nothing") instead of trusting directory names.

Exploring an unfamiliar API

go doc ./internal/payments            # package overview
go doc ./internal/payments Gateway    # one symbol, with doc comment
go doc -all ./internal/payments       # full API surface

Prefer this to opening files: it shows the exported contract without implementation noise.

3. Semantic Rename

gopls rename -w internal/service/user.go:42:6 ProcessOrder

Renames the symbol everywhere it's referenced — through interfaces, embedding, and test packages. Never rename an identifier with find-and-replace; UserID the field and UserID the local variable are different symbols with the same spelling.

4. Diagnostics Without an Editor

gopls check ./internal/...   # type errors + analyzer findings per file
go vet ./...                 # the vet suite standalone

gopls check surfaces the same diagnostics an IDE user sees — run it when reviewing code you haven't opened in an editor.

5. When grep Is Still Right

  • String literals: log messages, SQL, config keys, error text.
  • Comments, TODOs, documentation.
  • Code that doesn't compile yet — gopls needs a type-checkable package; grep works on broken trees.
  • Quick existence checks ("is this env var referenced anywhere?").

Rule of thumb: identifiers → gopls; literals and prose → grep.

Verification Checklist

  1. Call sites enumerated with gopls references (not grep) before changing any shared symbol
  2. Interface changes preceded by gopls implementation on the interface
  3. Renames performed with gopls rename -w, never text replacement
  4. Layering assumptions verified with go list import data
  5. Unfamiliar packages explored via go doc before reading implementations
  6. gopls check / go vet run when reviewing without an editor
  7. grep reserved for literals, comments, and non-compiling code

GitHub Repository

eduardo-sl/go-agent-skills
Path: skills/(workflow)/go-semantic-tools
0
FAQ

Frequently asked questions

What is the go-semantic-tools skill?

go-semantic-tools is a Claude Skill by eduardo-sl. Skills package instructions and resources that Claude loads on demand, so Claude can perform go-semantic-tools-related tasks without extra prompting.

How do I install go-semantic-tools?

Use the install commands on this page: add go-semantic-tools to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.

What category does go-semantic-tools belong to?

go-semantic-tools is in the Documentation category, tagged word, ai, and api.

Is go-semantic-tools free to use?

Yes. go-semantic-tools is listed on AIMCP and free to install.

Related Skills

railway-docs
Documentation

This skill fetches current Railway documentation to answer questions about features, functionality, or specific docs URLs. It ensures developers receive accurate, up-to-date information directly from Railway's official sources. Use it when users ask how Railway works or reference Railway documentation.

View skill
n8n-code-python
Documentation

This Claude Skill provides expert guidance for writing Python code in n8n's Code nodes, specifically for using Python's standard library and working with n8n's special syntax like `_input`, `_json`, and `_node`. It helps developers understand Python's limitations within n8n and recommends using JavaScript for most workflows while offering Python solutions for specific data transformation needs.

View skill
archon
Documentation

The Archon skill provides RAG-powered semantic search and project management through a REST API. Use it for querying documentation, managing hierarchical projects/tasks, and performing knowledge retrieval with document upload capabilities. Always prioritize Archon first when searching external documentation before using other sources.

View skill
n8n-code-javascript
Documentation

This Claude Skill provides expert guidance for writing JavaScript code in n8n's Code nodes. It covers essential n8n-specific syntax like `$input`/`$json` variables, HTTP helpers, and DateTime handling, while troubleshooting common errors. Use it when developing n8n workflows that require custom JavaScript processing in Code nodes.

View skill