ralph
claudeRalph Loop — an autonomous agentic coding workflow with sandbox isolation, scoped memory, and self-managing task iteration.
4 skills · 4 agents · 1 MCP server · hooks
Self-hosting toolkit for managing this skills marketplace: setup-project, promote-skill, sync-skill, new-skill, new-plugin, list-skills, skills-doctor.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin skill-ops in zakattack9/agentic-coding. Commands read from the repo's manifest — 4 days ago.
list-skillsShow the central skills catalog grouped by plugin, and which plugins are enabled in the current project. Use whenever the user asks "what skills do I have", "what's in my marketplace", "which plugins are on for this project", "list my skills", or wants an overview of available vs enabled skills.
new-pluginCreate a new plugin in the central skills repo and register it in the marketplace catalog. Use whenever the user wants a new grouping of skills, says "create a plugin", "add a new plugin", "I need a category for <domain> skills", or tries to promote a skill into a plugin that doesn't exist yet. Do n
new-skillScaffold a new SKILL.md with correct frontmatter, either in the current project or directly in a central plugin. Use whenever the user wants to start a new skill from scratch and says "create a skill", "scaffold a skill", "new skill for X", or "add a skill to <plugin>". For turning an existing proje
promote-skillPush a skill that was created locally inside this project up into the centralized skills repo so every project can use it. Use whenever the user builds or drafts a skill in a project and says "promote this", "push this skill to the central repo", "add this to my marketplace", "make this skill availa
setup-projectConfigure which centralized skill plugins this project uses and write them into the project's .claude/settings.json. Use this whenever the user opens a new repo and wants to wire up their skills, says "set up skills for this project", "which skills does this project use", "configure plugins here", o
skills-doctorDiagnose the centralized skills setup — config, repo clones, marketplace registration, user-scope enablement, and whether the installed marketplace clone has drifted behind the central repo. Use whenever skills aren't loading, a promoted skill isn't showing up, the marketplace seems stale, or the us
sync-skillPush local edits to a skill that already lives in the central repo back up to it, without leaving the project. Use whenever the user has iterated on a centralized skill inside a project (often after pulling it down) and says "sync this skill", "push my changes back", "update the central version", or
Ralph Loop — an autonomous agentic coding workflow with sandbox isolation, scoped memory, and self-managing task iteration.
4 skills · 4 agents · 1 MCP server · hooks
A spec-driven development workflow that turns a rough idea into a verified implementation. It elicits and hardens an acceptance-criteria-first spec against your codebase, compiles it into an execution driver, then checks the built code against every criterion — with read-only adversarial judges gating quality at each stage and every spec change committed automatically. When OpenAI Codex CLI is available it adds an optional, fail-open second judge of a different provider, so every quality gate is cross-checked rather than one model auditing itself.
6 skills · 3 agents
Run a small team's entire software lifecycle on GitHub Projects v2 — deterministic, free, GitHub-native, and with no metered AI. It provisions a golden-template board and repo automation across an org, then drives work from issue intake through sprint planning and the full branch → PR → merge flow with check-gated, never-squashed merges, kept safe by GitHub App-token writes and skill-scoped guards.
8 skills
Manage your Claude Code skills and plugins from inside any project — switch which plugins are active, publish and sync local skills to a central marketplace, and diagnose and auto-repair a broken setup. Adapts to any repo layout and delegates skill authoring to the native skill-creator.
5 skills
Run the OpenAI Codex CLI from inside Claude Code as a cross-model escape hatch: hand a one-off review, question, or write task to a different provider's model for a second opinion, grounded in your repo with web search always on. Every call routes through one fail-open bridge — if Codex is absent, unauthenticated, or broken the skill reports and stops rather than answering as Claude, and Codex's output is surfaced verbatim as untrusted external text. Assumes an OpenAI-authenticated Codex setup.
3 skills · 1 agent
A git worktree workflow for running multiple Claude Code sessions in parallel — no restarts, no manual checkouts. Built on native worktrees, it covers the full lifecycle from spinning up an isolated worktree to finishing it through a guarded, never-squashed PR merge, with a live dashboard of in-flight work and deterministic guards against squash merges and committing unresolved conflicts.
4 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.