github-gem-seeker
Skill0 starsChanged 3 months agoMITView on GitHub
Search GitHub for battle-tested solutions instead of reinventing the wheel. Use when the user's problem is universal enough that open source developers have probably solved it already—especially for: format conversion (video/audio/image/document), media downloading, file manipulation, web scraping/archiving, automation scripts, and CLI tools. Prefer this skill over writing custom code for well-trodden problems. Apply automatically when the request matches; the user does not need to mention this skill.
In this repository76 other files it gives its agents.
- app-store-submission-packagerSkill
- digital-product-inventorSkill
- ios-testflight-github-actionsSkill
- meta-ads-analyzerSkill
- get-to-know-a-clientSkill
- investigate-before-recommendSkill
- production-system-auditSkill
- similarweb-analyticsSkill
- stock-analysisSkill
- system-architectSkill
- autonomous-github-syncSkill
- autonomous-sync-scriptSkill
- organize-github-reposSkill
- using-git-worktreesSkill
- brainstorm-logosSkill
- brand-driven-ux-overhaulSkill
- canvas-designSkill
- excel-generatorSkill
- frontend-designSkill
- inspirational-music-video-productionSkill
- theme-factorySkill
- video-generatorSkill
- multiplayer-game-builderSkill
- promo-code-systemSkill
- realistic-ai-persona-builderSkill
- role-based-access-controlSkill
- serverless-debuggingSkill
- vertical-expansion-blueprintSkill
- manus-mcp-configuratorSkill
- mcp-auto-recoverySkill
- mcp-builderSkill
- mcp-connector-testerSkill
- mcp-ecosystem-optimizerSkill
- voice-ai-integrationSkill
- api-endpoint-builderSkill
- database-schema-generatorSkill
- testing-frameworkSkill
- deployment-automationSkill
- error-monitoring-setupSkill
- github-workflow-automationSkill
- analytics-dashboardSkill
- email-system-builderSkill
- feature-flag-systemSkill
- user-authentication-systemSkill
- cron-job-schedulerSkill
- file-upload-systemSkill
- notification-systemSkill
- payment-integrationSkill
- search-implementationSkill
- debug-mining-engineSkill
- doc-coauthoringSkill
- docxSkill
- internet-skill-finderSkill
- pdfSkill
- pptxSkill
- project-handoff-ingestionSkill
- serverless-debuggingSkill
- skill-arsenal-builderSkill
- skill-creatorSkill
- skill-demo-builderSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this skill when the request matches its description.
- Distinctive: line 35
Search for GitHub projects using effective query patterns:
- Distinctive: line 58
Run it with the user's input/files
- Distinctive: line 76
Do NOT skip crediting the project.
- Distinctive: line 87
Prefer higher tiers for reliability.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
Search GitHub for battle-tested solutions instead of reinventing the wheel. Use when the user's problem is universal enough that open source developers have probably solved it already—especially for: format conversion (video/audio/image/document), media downloading, file manipulation, web scraping/archiving, automation scripts, and CLI tools. Prefer this skill over writing custom code for well-trodden problems. Apply automatically when the request matches; the user does not need to mention this skill.
This skill should apply automatically when the request matches; the user does not need to mention this skill.
Usage
Use this skill when the request matches its description. The skill is discovered automatically; the user does not need to mention the skill explicitly.
GitHub Gem Seeker
Find and use battle-tested open source projects on GitHub to solve the user's problem immediately. After successfully solving the problem, offer to package the solution into a reusable skill.
Core Philosophy
Classic open source projects, tested by countless users over many years, are far more reliable than code written from scratch. Solve the problem first, skill-ify later.
Workflow
Step 1: Understand the Need
Clarify what the user wants to accomplish. Ask only if truly ambiguous:
- What specific problem are you trying to solve?
- What format/input/output do you expect?
Step 2: Find the Right Tool
Search for GitHub projects using effective query patterns:
| Need Type | Query Pattern | Example |
| Tool/utility | github [task] tool | github video download tool |
| Library | github [language] [function] library | github python pdf library |
| Alternative | github [known-tool] alternative | github ffmpeg alternative |
Step 3: Evaluate Quality (Quick Check)
Assess candidates using key indicators:
| Indicator | Gem Signal | Warning Signal |
| Stars | 1k+ solid, 10k+ excellent, 50k+ legendary | <100 for mature projects |
| Last commit | Within 6 months | >2 years ago |
| Documentation | Clear README, examples | Sparse or outdated docs |
Step 4: Solve the Problem
This is the priority. Install the tool and use it to solve the user's actual problem:
- Install the chosen tool (pip, npm, apt, or direct download)
- Run it with the user's input/files
- Deliver the result to the user
- Troubleshoot if needed—iterate until solved
Step 5: Credit the Gem & Offer Next Steps (Post-Success Only)
Only after the problem is successfully solved:
Credit the open source project — Always share the GitHub repo URL and encourage support:
"This was powered by [Project Name] — an amazing open source project! GitHub: [URL] If it helped you, consider giving it a ⭐ star to support the maintainers."
Offer to skill-ify — Optionally mention:
"If you'll need this again, I can package it into a reusable skill for instant use next time."
Do NOT skip crediting the project. Open source thrives on recognition.
Quality Tiers
| Tier | Criteria | Examples |
| Legendary | 50k+ stars, industry standard | FFmpeg, ImageMagick, yt-dlp |
| Excellent | 10k+ stars, strong community | Pake, ArchiveBox |
| Solid | 1k+ stars, well-documented | Most maintained tools |
| Promising | <1k stars, active development | Newer niche projects |
Prefer higher tiers for reliability.
Example Interaction
User: I need to download this YouTube video: [link]
Correct approach:
- Identify yt-dlp as the legendary-tier solution
- Install yt-dlp
- Download the video for the user
- Deliver the downloaded file
- After success: "This was powered by yt-dlp — https://github.com/yt-dlp/yt-dlp — give it a ⭐ if it helped! If you download videos often, I can turn this into a skill for instant use next time."
Wrong approach:
- ❌ "I found yt-dlp, want me to make a skill for it?"
- ❌ Presenting options without solving the problem
Common Gems Reference
| Category | Go-to Gems |
| Video/Audio processing | FFmpeg, yt-dlp |
| Image processing | ImageMagick, sharp |
| PDF manipulation | pdf-lib, PyMuPDF |
| Web scraping | Playwright, Puppeteer, Scrapy |
| Format conversion | Pandoc, FFmpeg |
| Archiving | ArchiveBox |
| Desktop app packaging | Electron, Tauri, Pake |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.