code-context-finder_skill

This skill helps you discover relevant context from knowledge graphs and code relationships while coding, surfacing decisions, dependencies, and architecture

Python

2

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill 89jobrien/steve --skill code-context-finder

SKILL.md4.7 KB

Overview

This skill automatically finds and surfaces relevant context while you code by combining knowledge-graph search with code-relationship analysis. It detects moments when extra context would help (opening unfamiliar files, new features, refactors, debugging) and returns related entities, prior decisions, and code dependencies. The result is a concise, actionable summary you can use before making changes.

How this skill works

The skill watches for signals that suggest context is needed, then queries a project knowledge graph and scans the codebase for relationships like imports, callers, and test coverage. It synthesizes findings into a short report listing relevant knowledge-graph entities, dependent files, and suggested actions. Search strategies include mapping module names to project entities, matching error types to past issues, and grepping for callers/implementations.

When to use it

Opening an unfamiliar file or module
Starting a new feature or implementation
Debugging errors or unexpected behavior
Refactoring shared or core modules
Making architectural or configuration decisions
Touching deployment or infrastructure config

Best practices

Run the context finder before editing shared modules to surface dependents and tests
Review any prior decisions or ADRs returned by the knowledge graph before changing architecture
Use code-relationship results to update or extend tests for affected callers
Annotate or update the knowledge graph when you make lasting design changes
Filter results by ownership or expertise to consult the right teammates

Example use cases

A developer opens a legacy module: the skill shows imports, callers, and related ADRs to explain why code exists
When fixing a recurring error: it surfaces past issue nodes and similar fixes from the knowledge graph
During a refactor: it lists all dependent files and tests so you can plan safe changes
When adding a feature: it finds prior decisions and similar implementations to avoid duplicated effort
Touching infra config: it shows deployment notes, environment constraints, and past incidents

FAQ

It monitors signals like opening unfamiliar files, error messages, questions about how something works, and edits to shared modules to trigger searches.

What sources does it search?

It queries the project knowledge graph for entities and decisions and scans the codebase for imports, callers, class hierarchies, and tests.

How are results presented?

Results are synthesized into a concise summary listing knowledge-graph entities, code relationships, and suggested actions to review before changing code.