agentleFS
happycapy-aihappycapy-ai/Happycapy-skills/skills/happycapy-skill-creator/SKILL.md

happycapy-skill-creator

Skill137 starsChanged 6 months agoMITView on GitHub

Automate HappyCapy skill creation by finding and adapting existing skills from anthropics/skills repository. Handles environment constraints (Python 3.11, Node.js 24, no Docker). Use when user wants to create or adapt skills for specific tasks.

  • Reads credentials

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Search anthropics/skills for similar skills (semantic + LLM)

    line 17
  2. Distinctive:

    Add requested features using LLM

    line 19
  3. Distinctive:

    Add new features using LLM fine-tuning

    line 35
  4. Distinctive:

    Create distributable .skill file (zip format)

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HappyCapy Skill Creator

Automate skill creation through adaptation rather than building from scratch.

Workflow

python scripts/create_skill.py "Your requirement here" --name skill-name

Process:

  1. Search anthropics/skills for similar skills (semantic + LLM)
  2. Clone the closest match
  3. Add requested features using LLM
  4. Auto-fix HappyCapy compatibility (remove Docker, adapt dependencies)
  5. Package as .skill file

Core Scripts

create_skill.py

Main orchestrator - runs full workflow end-to-end

semantic_search.py

LLM-powered semantic search of anthropics/skills repository

clone_skill.py

Clone skill from GitHub (anthropics/skills)

integrate_feature.py

Add new features using LLM fine-tuning

check_compatibility.py

Scan for HappyCapy incompatibilities (Docker, unsupported runtimes, memory issues)

auto_fix.py

Auto-fix compatibility issues with LLM rewrites

package_skill.py

Create distributable .skill file (zip format)

Examples

Compress PDFs:

python scripts/create_skill.py "I need to compress PDF files"
# Finds pdf skill → Clones → Adds compress function → Packages

Extract video frames:

python scripts/create_skill.py "Extract frames from videos every second"
# Finds video-frames skill → Clones → Adds interval parameter → Packages

Environment Constraints

HappyCapy provides:

  • ✅ Python 3.11, Node.js 24
  • ✅ pandoc, ImageMagick, jq
  • ✅ 4GB RAM, 2 CPU cores

HappyCapy does NOT support:

  • ❌ Docker, Java, Ruby, Go

The tool automatically fixes incompatibilities.

Requirements

  • Python 3.11+
  • AI_GATEWAY_API_KEY environment variable (auto-configured in HappyCapy)
  • Internet connection (to clone from anthropics/skills)

Advanced

Use improved auto-fix with batching:

from scripts.auto_fix_improved import fix_compatibility_issues

fix_compatibility_issues(
    skill_path=path,
    issues=issues,
    batch_size=5,      # Process 5 issues per batch
    max_retries=2      # Retry failed fixes up to 2 times
)

Troubleshooting: See references/bugfixes.md for known issues and solutions

Environment details: See references/happycapy-environment.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.