blind-spot-pass
Use *before* starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to…
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Claude Code
$ npx -y skills add sangrokjung/claude-forge --skill strategic-compact --agent claude-code
Codex
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a codex -y
Cursor
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a cursor -y
Gemini CLI
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a gemini-cli -y
GitHub Copilot
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a github-copilot -y
OpenCode
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a opencode -y
Windsurf
$ npx skills add sangrokjung/claude-forge --skill strategic-compact -a windsurf -y
name: strategic-compact description: Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Suggests manual `/compact` at strategic points in your workflow rather than relying on arbitrary auto-compaction.
Auto-compaction triggers at arbitrary points:
Strategic compaction at logical boundaries:
The `suggest-compact.sh` script runs on PreToolUse (Edit/Write) and:
1. **Tracks tool calls** - Counts tool invocations in session 2. **Threshold detection** - Suggests at configurable threshold (default: 50 calls) 3. **Periodic reminders** - Reminds every 25 calls after threshold
Add to your `~/.claude/settings.json`:
{
"hooks": {
"PreToolUse": [{
"matcher": "tool == \"Edit\" || tool == \"Write\"",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/strategic-compact/suggest-compact.sh"
}]
}]
}
}Environment variables:
1. **Compact after planning** - Once plan is finalized, compact to start fresh 2. **Compact after debugging** - Clear error-resolution context before continuing 3. **Don't compact mid-implementation** - Preserve context for related changes 4. **Read the suggestion** - The hook tells you *when*, you decide *if*
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
Use *before* starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to…
Use when detecting and running project build systems automatically. Supports npm/yarn/pnpm/pip/poetry/gradle/maven/cargo/go/make.…
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill…
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel…
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves…
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.