skills/codex/github-research/SKILL.md
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: github-research description: Find reputable GitHub repositories with quality filters (stars, recency, license). Use when searching for code samples, reference implementations, libraries, or templates on GitHub. Prioritizes curated Awesome Lists, then searches with star thresholds to ensure code quality. Requires gh CLI (version 2.14+). --- # GitHub Research Find reputable GitHub repositories using quality filters. Prioritize c
npx skillsauth add frank-luongt/faos-skills-marketplace skills/codex/github-researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Find reputable GitHub repositories using quality filters. Prioritize curated Awesome Lists, then search with star thresholds.
Awesome Lists are community-curated collections of quality resources. Search them first:
gh search repos "awesome <topic>" --stars=">=5000" --limit=5 \
--json name,stargazersCount,url,description
If a relevant Awesome List exists (e.g., awesome-python, awesome-react), recommend it as the primary source.
gh search repos "<query>" \
--language=<lang> \
--stars=">=1000" \
--archived=false \
--limit=10 \
--json name,url,stargazersCount,license,description,pushedAt
Star thresholds by use case:
| Use Case | Threshold | Flag |
|---|---|---|
| Production code | 1000+ stars | --stars=">=1000" |
| Learning/examples | 500+ stars | --stars=">=500" |
| Exploration | 100+ stars | --stars=">=100" |
| Filter | Flag | Example |
|---|---|---|
| Topic | --topic | --topic=cli |
| Recency | --updated | --updated=">2024-01-01" |
| License | --license | --license=mit |
| Owner | --owner | --owner=microsoft |
| Sort | --sort | --sort=stars |
For the top 3-5 candidates, check quality indicators:
gh api "repos/<owner>/<repo>" --jq '{
stars: .stargazers_count,
forks: .forks_count,
issues: .open_issues_count,
updated: .pushed_at,
license: .license.spdx_id
}'
Quality indicators:
Save research to docs/research/ as Markdown:
docs/research/YYYY-MM-DD-<topic>-github-repos.md
Include: repo name, stars, license, URL, and brief description.
# FastAPI templates
gh search repos "fastapi template" --language=python --stars=">=500" --archived=false --limit=10
# CLI tools in Go
gh search repos --topic=cli --language=go --stars=">=1000" --limit=10
# React component libraries (recent)
gh search repos "react component library" --language=typescript \
--stars=">=1000" --updated=">2024-01-01"
gh api rate_limit --jq '.resources.search.remaining'gh search repos commandgh auth status| Avoid | Why | Instead |
|---|---|---|
| No star threshold | Returns low-quality repos | Use --stars=">=500" minimum |
| Skipping Awesome Lists | Miss curated resources | Always check Awesome Lists first |
| Ignoring recency | Stale repos cause issues | Filter by --updated or check pushedAt |
| Ignoring license | Legal risk | Filter by --license or verify in results |
| Single search query | Misses relevant repos | Try multiple query variations |
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grpo-rl-training description: GRPO reinforcement learning training with TRL. Use when applying Group Relative Policy Optimization for reasoning and task-specific model training. --- # GRPO/RL Training with TRL Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-r
tools
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: graphql-architect description: Master modern GraphQL with federation, performance optimization, --- ## Use this skill when - Working on graphql architect tasks or workflows - Needing guidance, best practices, or checklists for graphql architect ## Do not use this skill when - The task is unrelated to graphql architect - You need a different domain or tool outside this scope ## Instructions - Clarify goals, constraints, and
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grafana-dashboards description: Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces. --- # Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. ## Do not use this skill when - The task is unrelated
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: gptq description: GPTQ post-training quantization for generative models. Use when quantizing large models to 4-bit with calibration-based weight compression. --- # GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. ## When to use GPTQ **Use GPTQ when:** - Need to fit large models (70B+) on limited GPU