~ / rigs / rolandtolnay / llm-toolkit

rolandtolnay/llm-toolkit

Slash commands, mental frameworks, and prompt engineering resources for Claude Code — grounded in LLM research

↗ GitHub ★ 1 MIT updated 27d ago collection Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~10.1k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit rolandtolnay/llm-toolkit/agents ./rig-llm-toolkit/agents
$ npx degit rolandtolnay/llm-toolkit/commands ./rig-llm-toolkit/commands
$ npx degit rolandtolnay/llm-toolkit/skills ./rig-llm-toolkit/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit rolandtolnay/llm-toolkit/.agents/skills/docx .claude/skills/docx
$ npx degit rolandtolnay/llm-toolkit/.agents/skills/pdf .claude/skills/pdf
$ npx degit rolandtolnay/llm-toolkit/skills/app-icon-studio .claude/skills/app-icon-studio
$ npx degit rolandtolnay/llm-toolkit/skills/audit-prompt .claude/skills/audit-prompt
$ npx degit rolandtolnay/llm-toolkit/skills/bootstrap-goal-project .claude/skills/bootstrap-goal-project
$ npx degit rolandtolnay/llm-toolkit/skills/boy-scout .claude/skills/boy-scout
$ npx degit rolandtolnay/llm-toolkit/skills/brand-naming .claude/skills/brand-naming
$ npx degit rolandtolnay/llm-toolkit/skills/create-engineering-skill .claude/skills/create-engineering-skill
$ npx degit rolandtolnay/llm-toolkit/skills/create-pr .claude/skills/create-pr
$ npx degit rolandtolnay/llm-toolkit/skills/elevenlabs .claude/skills/elevenlabs
$ npx degit rolandtolnay/llm-toolkit/skills/firebase-admin .claude/skills/firebase-admin
$ npx degit rolandtolnay/llm-toolkit/skills/firebase-hosting-basics .claude/skills/firebase-hosting-basics
$ npx degit rolandtolnay/llm-toolkit/skills/gmail .claude/skills/gmail
$ npx degit rolandtolnay/llm-toolkit/skills/linear .claude/skills/linear
$ npx degit rolandtolnay/llm-toolkit/skills/nano-banana-app-icon .claude/skills/nano-banana-app-icon
$ npx degit rolandtolnay/llm-toolkit/skills/new-project .claude/skills/new-project
$ npx degit rolandtolnay/llm-toolkit/skills/plain .claude/skills/plain
$ npx degit rolandtolnay/llm-toolkit/skills/pr-qa-browser .claude/skills/pr-qa-browser
$ npx degit rolandtolnay/llm-toolkit/skills/product-research .claude/skills/product-research
$ npx degit rolandtolnay/llm-toolkit/skills/publish-research .claude/skills/publish-research
$ npx degit rolandtolnay/llm-toolkit/skills/readme-best-practices .claude/skills/readme-best-practices
$ npx degit rolandtolnay/llm-toolkit/skills/research .claude/skills/research
$ npx degit rolandtolnay/llm-toolkit/skills/ripple-check .claude/skills/ripple-check
$ npx degit rolandtolnay/llm-toolkit/skills/roadmap-page .claude/skills/roadmap-page
$ npx degit rolandtolnay/llm-toolkit/skills/scope .claude/skills/scope
$ npx degit rolandtolnay/llm-toolkit/skills/searchexa .claude/skills/searchexa
$ npx degit rolandtolnay/llm-toolkit/skills/slack .claude/skills/slack
$ npx degit rolandtolnay/llm-toolkit/skills/triage-pr-comments .claude/skills/triage-pr-comments
$ npx degit rolandtolnay/llm-toolkit/skills/write-loop .claude/skills/write-loop
$ curl -fsSL --create-dirs -o .claude/agents/research-subagent.md https://raw.githubusercontent.com/rolandtolnay/llm-toolkit/main/agents/research-subagent.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (29)

Subagents (1)

research-subagent
model: opus
Research subagent with API usage logging. Use instead of general-purpose when spawning subagents from the research skill. Has full tool access plus PostToolUse hooks that log WebSearch/WebFetch calls.

Slash commands (21)

/analyze-problem/consider/10-10-10/consider/5-whys/consider/eisenhower-matrix/consider/first-principles/consider/inversion/consider/occams-razor/consider/one-thing/consider/opportunity-cost/consider/pareto/consider/second-order/consider/swot/consider/via-negativa/explain/finalize-ticket/generate-readme/handoff/reflect/tidy-commits/verify/work-ticket

Similar rigs

copied ✓