Graph Search Skill for Claude
Searches the code knowledge graph by function, class, or type using FTS5 full-text search. Use when locating code entities by name or qualified path.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/athola/claude-night-market --skill graph-searchThe instruction itself
6 sections, as written by the authorSearch Code Knowledge Graph
Search .gauntlet/graph.db for code entities by name.
When NOT To Use
- The graph is missing or stale (use
gauntlet:graph-build) - Scoring the impact of a change (use
pensive:blast-radius)
Steps
- Accept query: Get the search term from the user.
- Run the query script:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/graph_query.py \
--action search --query "<term>" --limit 20
Optional filters:
--kind Functionto search only functions--kind Classto search only classes
- Display results: Show qualified name, file path,
line numbers, and relevance score for each match.
- Offer to read: Ask if the user wants to read the
top result's source file.
Query Intelligence
The search engine detects query patterns:
- PascalCase (e.g.,
UserService): boosts Class
and Type results
- snake_case (e.g.,
get_users): boosts Function
results
- Dotted path (e.g.,
app.models.User): boosts
qualified name matches
Prerequisites
The graph must be built first. If .gauntlet/graph.db
does not exist, suggest running the graph-build skill.
Exit Criteria
- [ ] If
.gauntlet/graph.dbdoes not exist, the skill surfaces
the missing-prerequisite error and suggests gauntlet:graph-build
rather than failing silently
- [ ] Results display qualified name, file path, line numbers, and
relevance score for each match (up to --limit results)
- [ ] Query intelligence applies correct boost: PascalCase boosts
Class/Type results, snake_case boosts Function results, dotted
path boosts qualified name matches
- [ ] User is offered to read the top result's source file after
results are shown
Other skills for the same job
different authors, same section of the catalogue
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
How to use it
Take athola/graph-search from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.