Setup
18 AI agent skills that catch what your agent misses: hidden code debt, false completions, missing error handling, context amnesia, imprecise UI edits. Self-improving with TF-IDF routing + SkillOpt loop. Cursor, Claude Code, Codex, Copilot. Install: npx skills@latest add Adit-Jain-srm/skill-forge
npx -y skills add Adit-Jain-srm/skill-forge --skill setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
One-time setup for skill-forge. Asks user preferences (search sources, creation style, target platforms, GitHub username, skill categories of interest) and configures all other skills to use those preferences. Run once before using any other skill-forge capability. Use when user says setup, configure, or invokes /setup.
SKILL.md
2.3 KB, as published. Nobody here has run it
Overview
One-time configuration that asks your preferences (platforms, domains, GitHub username, discovery style) and generates a config all other skill-forge capabilities use.
Setup skill-forge
Run this ONCE per environment. It configures skill-forge to work the way YOU work.
I'll ask you a few questions, then create a config that all other skill-forge capabilities use.
Questions I'll Ask
- GitHub username — Where should published skills be created?
- What platforms do you use? — Cursor / Claude Code / Codex / Gemini / Windsurf / Other
- What domains interest you most? — Frontend / Backend / DevOps / AI / Security / Data / Other
- How aggressive should discovery be? — Conservative (weekly) / Normal (daily) / Maximum (continuous)
- Publishing preferences — Auto-publish when quality passes? Or always ask first?
- Existing skills to integrate with — Which installed skills should skill-forge know about?
What Gets Created
After answering, I'll generate:
memory/user-config.json
All other skills read this config. Your preferences persist across sessions.
Example Config
{
"github_user": "your-username",
"platforms": ["cursor", "claude-code"],
"domains_of_interest": ["backend", "devops", "ai"],
"discovery_aggression": "normal",
"auto_publish": false,
"installed_skills_to_integrate": ["superpowers/*", "azure-skills/*"],
"quality_bar": "validate_before_ship",
"configured_at": "2026-06-04T03:00:00Z"
}
Why This Matters
Without setup:
- skill-forge doesn't know YOUR GitHub username (can't publish for you)
- Discovery is generic (not tuned to your interests)
- Doesn't know what you already have installed (creates duplicates)
With setup:
- Personalized discovery (your domains, your platforms)
- Publishing goes to YOUR account
- Integrates with YOUR existing skills (no duplication)
- Respects your automation preferences