Agent skill

read-repo-references

Learn from reference materials and prior art in the .references/ directory

Stars 4
Forks 2

Install this agent skill to your Project

npx add-skill https://github.com/EYH0602/skillshub/tree/main/skills/read-repo-references

SKILL.md

Read Repo References

Use this skill when you need inspiration or guidance from prior art and reference implementations.

When to Use

  • Designing new features that have established patterns elsewhere
  • Stuck on architecture decisions
  • Need to understand how similar tools solve a problem

Reference Structure

References live in .references/<name>/ with this format:

.references/
└── <reference-name>/
    ├── REF.md              # Required: metadata and description
    └── [local files]       # Optional: PDFs, markdown, code samples

REF.md Format

yaml
---
name: reference-name
type: link | local | hybrid
url: https://...               # Required if type includes link
description: Brief description
---

# Reference Name

Notes on key patterns, architecture, and relevance...

Reference Types

  • link: Points to external resource (GitHub repo, docs). Use WebFetch or browse the URL.
  • local: Contains files directly. Read the files in the reference directory.
  • hybrid: Both a link and local supplementary materials.

How to Use References

  1. List available references:

    bash
    ls .references/
    
  2. Read a reference:

    bash
    cat .references/<name>/REF.md
    
  3. For link-type references: The REF.md contains the URL and notes about what to look for. Fetch specific files from the URL as needed.

  4. For local-type references: Read the files directly from the reference directory.

  5. Apply learnings: Extract relevant patterns and adapt them to the current project's conventions.

Best Practices

  • Read REF.md first to understand what the reference offers
  • Focus on patterns relevant to your current task
  • Adapt patterns to fit the project, don't copy blindly
  • Note any new insights in .agents/notes/ for future reference

Expand your agent's capabilities with these related and highly-rated skills.

EYH0602/skillshub

analyze-ci

Analyze failed GitHub Action jobs for a pull request.

4 2
Explore
EYH0602/skillshub

github-actions-templates

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

4 2
Explore
EYH0602/skillshub

paper-polish

This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structure.

4 2
Explore
EYH0602/skillshub

write-unit-tests

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

4 2
Explore
EYH0602/skillshub

fuzzing

Design, implement, debug, and maintain fuzzers for security testing. Use when building coverage-guided fuzzers (LibAFL, AFL++, LibFuzzer), writing fuzz targets/harnesses, debugging why a fuzzer isn't finding bugs or coverage isn't increasing, analyzing and triaging crashes, implementing mutation strategies, or working with grammar-based fuzzing for structured inputs.

4 2
Explore
EYH0602/skillshub

temporal-python-testing

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

4 2
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results