By ondrej-svec
Blocks destructive database commands and warns when file edits may expose secrets during bash operations
Context engineering agent. Builds and maintains structured knowledge docs — CLAUDE.md files, knowledge bases, onboarding guides. Use when creating or reorganizing context documents that AI will consume repeatedly.
Reviews SKILL.md and agent .md files against the toolkit's quality bar. Grades A-F based on methodology anchoring, safety mechanisms, and CONVENTIONS.md compliance. Use when creating or upgrading skills/agents, or for periodic quality audits of the toolkit.
Capture knowledge — solutions, context docs, learnings, and principles. Use after fixing non-trivial bugs, creating context for AI, or discovering patterns worth preserving. Triggers: compound, document solution, capture fix, save solution, knowledge compound, document this, save this fix, context, create context, update context, build context, learn, save learning, remember this.
Two-layer copy editor. Layer 1 is a deterministic typography audit (regex-level, auto-closeable). Layer 2 is LLM judgment — reject-list hits, nominal-style detection, clarity/ambiguity pass for participant-facing content, voice/register check, and spoken- readability read. Loads repo-local .copy-editor.yaml to compose the baked-in language profile with the repo's style guide, reject list, examples, and voice doctrine. Czech is a full profile; English is a stub. **Activate automatically when the conversation edits or creates any file matching a repo's .copy-editor.yaml include scope, when the user asks about Czech or participant-facing copy, when reviewing content PRs, or when a work slice would otherwise close without a Layer 2 pass on edited visible-surface content.** Do not wait to be invoked by name. Explicit trigger phrases: copy edit, editorial pass, czech review, czech copy review, audit copy, check typography, review prose, tighten copy.
Fast opinionated quality pass — simplicity, test integrity, and correctness. Not a deep review. One pass, one voice. For depth, use /review (deep-thought). Triggers: quick review, quality check, sanity check, check my code, is this good.
Adversarial review — find weaknesses and expose them with failing tests. Checks architecture conformance, stub detection, security, and story completeness. Never modifies implementation. Standalone or pipeline-aware via env vars. Triggers: redteam, adversarial review, attack, probe, find weaknesses.
Prepare a project for development — create directories, configs, install dependencies. Never creates source or test files. Standalone or pipeline-aware via $ARCH_PATH. Triggers: scaffold, setup project, prepare project, init project, create structure.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Don't Panic.
32 skills for AI coding agents. Five plugins. Works with Claude Code, Codex, OpenCode, Pi, and any tool supporting the agentskills.io standard. Named after The Hitchhiker's Guide to the Galaxy because the universe is absurd and your tools should at least have personality.
/plugin marketplace add ondrej-svec/heart-of-gold-toolkit
/plugin install deep-thought@heart-of-gold-toolkit
bunx @heart-of-gold/toolkit install --to codex
The Codex target also applies Codex-specific wording transforms for flagship shared skills so interactive flows like brainstorm and plan more strongly encourage Codex's structured user-input UI instead of falling back to plain text when richer selection UX is available. It also rewrites slash-command references in installed skill text — both plain (/plan, /work) and plugin-prefixed (/deep-thought:review, /marvin:compound) — to Codex-style $... skill invocations.
bunx @heart-of-gold/toolkit install --to opencode
# Option A: install the package directly in Pi to get skills + pi-native extensions
pi install npm:@heart-of-gold/toolkit
# Option B: install shared skills only into Pi's native skill directory
bunx @heart-of-gold/toolkit install --to pi
Important: choose one Pi install path or the other.
Do not use both the Pi package install and install --to pi at the same time, or Pi will report duplicate skill collisions on reload.
The CLI now refuses install --to pi when your Pi settings already reference @heart-of-gold/toolkit as a package. If you intentionally want both paths for debugging, rerun with --force.
Pi also discovers skills from the shared ~/.agents/skills/ location, so installs done with the OpenCode target are usable from Pi too.
When installed as a Pi package, Heart of Gold exposes Pi-native extension commands for the flagship workflows:
/deep-thought-brainstorm — start a brainstorm (collaborative discovery)/deep-thought-plan — start planning (research and produce a plan document)/deep-thought-architect — turn brainstorm decisions into stories and architecture docs/share-html — publish an HTML file or static site directory through the portable share-html skill/share-server-setup — set up or adopt the local share server through the portable share-server-setup skill/share-server-control — control the local share server lifecycle through the portable share-server-control skill/marvin-work — start executing a plan (with always-on safety guardrails)Pi package installs also include a Pi-only guided workflow enhancer for supported Heart of Gold skills. For brainstorm, plan, and architect, when the assistant asks a high-confidence structured question, Pi can upgrade it into a custom interactive TUI and feed the answer back into the same workflow. Shared skills remain plain-text portable in every other harness.
For extension debugging, Pi also exposes /deep-thought-guided-debug to toggle notices explaining when a guided prompt was extracted, skipped, dismissed, or answered.
The skills themselves enforce their own boundaries (read-only for brainstorm/plan, safe commands for work) via allowed-tools and prompt constraints — no manual mode switching needed.
The work extension also provides always-on guardrails that protect .env, .git/, and node_modules/ from edits, block git add . and destructive rm, and require confirmation for git push / npm publish.
bunx @heart-of-gold/toolkit list
Some skills in this repository can, when configured by the user, interact with personal services and local tooling such as:
Treat skills and helper scripts as executable automation, not passive text. Review their contents before installing them, especially for plugins like Guide and Babel Fish that can access personal data or third-party services.
Ten ways to think clearly about hard problems.
Brainstorm before you plan. Plan before you build. Investigate when something breaks. Review when it ships. Map where it could go when you can't see the futures yet. And when the stakes are high, simulate an expert panel that argues with itself until the right answer falls out.
10 skills · 9 agents · 16 knowledge files
npx claudepluginhub ondrej-svec/heart-of-gold-toolkit --plugin marvinThe Hitchhiker's Guide — content creation suite with automated pipeline, daily briefs, and blog writing
The Answer Computer — reasoning tools for brainstorming, planning, architecture design, and deep thinking
Universal Translator — media generation tools for audio, image, video, and visualization
5 essential safety hooks for Claude Code. Blocks rm -rf, force-push, hard-reset, .env overwrites, and package publish. The minimum viable safety net from 800+ hours of autonomous operation.
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows
Specialized security review subagent
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Editorial "Essentials" bundle for Claude Code from Antigravity Awesome Skills.
Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.