By adamziel
Adam's portable skills: code-review, autonomous-loop, supervised-team, docs, writing-pr-descriptions, documenting-code, and llm-wiki. Works in Claude Code (as a plugin) and Codex (via prompts/AGENTS.md).
Compatibility alias for /autonomous-loop. Creates a durable autonomous build loop instead of the old bounded implementer/verifier loop.
Create a durable autonomous loop that repeatedly reprompts Codex or Claude with persistent memory, progress, quiet logs, Git commits, tests, and fail-fast observability.
Review the pending changes on the current branch (or a specified PR) for correctness, security, tests, and clarity.
Write tutorial / onboarding documentation for a software library — taking developers from zero to familiarity, with embedded interactive code examples.
Document code in a useful, developer-friendly way.
Compatibility alias for autonomous-loop. Use when the user asks for the old adversarial-loop workflow; create a durable autonomous build loop with persistent memory, progress, quiet logs, Git commits, tests, and optional verifier tasks instead of the old bounded implementer/verifier loop.
Create a durable repo-local bash loop that repeatedly reprompts Codex or Claude to advance a product or codebase, with persistent memory, progress checklists, quiet logs, Git commits, tests, and fail-fast observability. Use when the user wants an unattended build loop, self-propelling implementation loop, or a replacement for an adversarial implementer/verifier loop.
Review the pending changes on the current branch (or a specified PR) for correctness, security, tests, and clarity. Use when the user asks for a code review, says "review my branch", "review this PR", invokes `/code-review`, or finishes a chunk of work and wants a second pair of eyes before merging.
Use when writing onboarding documentation for a software library, framework, or developer tool — tutorials, conceptual guides, getting-started flows, and the surrounding learning surface. Specifically tuned for taking a developer from zero to productive familiarity, and for content that pairs prose with embedded interactive code examples (REPLs, sandboxes, live previews). Covers information architecture, concrete page templates, writing voice, example patterns, and how to integrate interactivity. Distilled from analysis of 21 highly-praised OSS docs sites (Svelte, Vue, React, Rust Book, FastAPI, Django, MDN, Tailwind, Astro, Next.js, Stripe-shaped Supabase, etc.).
Documents code in a useful, developer-friendly way.
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.
A small, portable skills plugin. Currently ships:
/adversarial-loop remains a compatibility alias.The skill files (skills/*/SKILL.md) are plain markdown with YAML frontmatter and are the single source of truth — both Claude Code and Codex read the same files.
.claude-plugin/
plugin.json # Claude Code plugin manifest
marketplace.json # Claude Code marketplace entry (so this repo is its own marketplace)
skills/
code-review/SKILL.md
autonomous-loop/SKILL.md
adversarial-loop/SKILL.md # compatibility alias for autonomous-loop
supervised-team/SKILL.md
docs/SKILL.md
docs/references/ # page-templates.md, source-projects.md
writing-pr-descriptions/SKILL.md
documenting-code/SKILL.md
llm-wiki/SKILL.md
commands/
code-review.md # /code-review slash command
autonomous-loop.md # /autonomous-loop slash command
adversarial-loop.md # compatibility alias for /autonomous-loop
docs.md # /docs slash command
writing-pr-descriptions.md # /writing-pr-descriptions slash command
documenting-code.md # /documenting-code slash command
llm-wiki.md # /llm-wiki slash command
scripts/
install-codex.sh # symlink skills + commands into ~/.codex/
AGENTS.md # entry point Codex reads automatically
Clone this repo, add the working copy as a marketplace, then install the plugin:
git clone https://gitea.zielinscy.dev/adam/ai-skills.git ~/code/ai-skills
/plugin marketplace add ~/code/ai-skills
/plugin install skills@adamziel-skills
After install, /code-review, /autonomous-loop, /adversarial-loop, /docs, /writing-pr-descriptions, /documenting-code, and /llm-wiki are available as slash commands, and the skills auto-trigger when their descriptions match the request. supervised-team is a skill-only workflow; invoke it as $supervised-team or by asking for a supervised parallel Codex/tmux team.
To develop locally, edit the cloned working copy and pull updates with git pull.
Codex doesn't have a plugin system yet, but it does read ~/.codex/prompts/*.md for slash commands and (when enabled) ~/.codex/skills/<name>/SKILL.md for skills. The installer script symlinks both:
git clone https://gitea.zielinscy.dev/adam/ai-skills.git ~/code/ai-skills
~/code/ai-skills/scripts/install-codex.sh
Then in Codex, /code-review, /autonomous-loop, /adversarial-loop, /docs, /writing-pr-descriptions, /documenting-code, and /llm-wiki work the same way. The supervised-team skill is symlinked into ~/.codex/skills/supervised-team.
If your Codex build doesn't yet support skill auto-discovery, the slash commands still work because commands/*.md reference the skill files explicitly — Codex will read them via the prompt body.
Both installs use symlinks to the cloned repo, so git pull is the update path.
npx claudepluginhub adamziel/skills --plugin skillsUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.