skill-forge-benchmark
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across…
Package and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install scripts, documentation, and .skill packages. Use when user says "publish skill", "share skill", "package skill", "distribute skill", or "release skill".
$ npx -y skills add AgriciDaniel/skill-forge --skill skill-forge-publish --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/skill-forge-publishContext preview
The summary Claude sees to decide when to auto-load this skill.
Package and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install scripts, documentation, and .skill packages. Use when user says "publish skill", "share skill", "package skill", "distribute skill", or "release skill".
name: skill-forge-publish description: > Package and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install scripts, documentation, and .skill packages. Use when user says "publish skill", "share skill", "package skill", "distribute skill", or "release skill".
Run the full review before publishing: 1. Execute `/skill-forge review <path>` and ensure score >= 80/100 2. Fix any critical or high-priority issues 3. Test with at least 5 trigger queries 4. Verify all cross-references resolve
Generate `install.sh` that handles:
#!/usr/bin/env bash
# Install script for [skill-name]
# Usage: bash install.sh
set -euo pipefail
SKILL_DIR="$HOME/.claude/skills"
AGENT_DIR="$HOME/.claude/agents"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
echo "Installing [skill-name] skill..."
# Create directories
mkdir -p "$SKILL_DIR" "$AGENT_DIR"
# Copy main skill
cp -r "$SCRIPT_DIR/skill-name" "$SKILL_DIR/"
echo " Installed: skill-name"
# Copy sub-skills
for skill in "$SCRIPT_DIR/skills"/skill-name-*/; do
if [ -d "$skill" ]; then
skill_basename=$(basename "$skill")
cp -r "$skill" "$SKILL_DIR/"
echo " Installed: $skill_basename"
fi
done
# Copy agents (if any)
if [ -d "$SCRIPT_DIR/agents" ]; then
cp "$SCRIPT_DIR/agents"/*.md "$AGENT_DIR/" 2>/dev/null || true
echo " Installed agents"
fi
echo ""
echo "Installation complete!"
echo "Test with: /skill-name"# [Skill Name] [1-2 sentence description focusing on outcomes, not features] ## What it does [Bullet list of key capabilities] ## Installation ### Claude Code
git clone https://github.com/[user]/[repo] cd [repo] bash install.sh
### Claude.ai 1. Download the latest release (.zip) 2. Go to Settings > Capabilities > Skills 3. Click "Upload skill" 4. Select the downloaded .zip file ## Commands | Command | Description | |---------|-------------| | `/skill-name` | [description] | | `/skill-name cmd` | [description] | ## Examples ### [Example 1 title]
User: "[example input]"
[Description of what happens and expected output] ## Architecture
[file tree diagram]
## License [License type]
**For Claude.ai upload:** Run `python scripts/package_skill.py <path> <output-dir>` to create a `.skill` zip file.
**For GitHub:** 1. Create repository with README.md at root 2. Skill folder(s) at root level 3. install.sh at root level 4. Add LICENSE file 5. Add .gitignore (exclude .tmp/, __pycache__/, *.pyc)
**For team deployment (Claude.ai admin):**
__pycache__/ *.pyc *.pyo .tmp/ *.egg-info/ dist/ build/ .env *.skill
After publishing: 1. Test installation from scratch on a clean environment 2. Run all trigger test queries 3. Collect initial user feedback 4. Plan first iteration based on feedback 5. Set up issue templates for bug reports
| Channel | Best For | Format | |---------|----------|--------| | GitHub | Open source, community | Repository + install.sh | | Claude.ai upload | Personal use | .skill zip | | Team admin | Organization-wide | .skill zip via admin console | | Claude Plugin Marketplace | Wide distribution | .claude-plugin/ manifest |
Blog: Learn how to build Claude Code skills Design, scaffold, build, review, evolve, and publish production-grade Claude Code skills following the Agent Skills open standard.
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across…
Scaffold and build Claude Code skills from plans or descriptions. Generates SKILL.md files, sub-skills, scripts, references,…
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. Analyzes platform-specific…
Run evaluation pipelines on Claude Code skills to test triggering accuracy, workflow correctness, and output quality. Spawns…
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Handles…
Architecture and design planning for new Claude Code skills. Guides through use case definition, complexity tier selection,…