Autonomous loop that drains the `ready-for-agent` queue on the issue tracker. Each iteration claims an issue, runs it in an isolated worktree, executes with claude or codex, merges back to main, and closes the issue. Use when the user wants to run AFK execution, drain a PRD, hammer specific issues, or otherwise let agents grind through the backlog.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Find deepening opportunities in a codebase, informed by the domain language in .red/CONTEXT.md and the decisions in .red/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `.red/agents/` so the engineering skills know this repo's GitHub Issues setup, triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
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.
██████╗ ███████╗██████╗ ███████╗██╗ ██╗██╗██╗ ██╗ ███████╗
██╔══██╗██╔════╝██╔══██╗ ██╔════╝██║ ██╔╝██║██║ ██║ ██╔════╝
██████╔╝█████╗ ██║ ██║ ███████╗█████╔╝ ██║██║ ██║ ███████╗
██╔══██╗██╔══╝ ██║ ██║ ╚════██║██╔═██╗ ██║██║ ██║ ╚════██║
██║ ██║███████╗██████╔╝ ███████║██║ ██╗██║███████╗███████╗███████║
╚═╝ ╚═╝╚══════╝╚═════╝ ╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝╚══════╝
reddb.io's slash-command library for Claude Code, Codex, and friends. Ship while you sleep.
Install · /afk · Pipeline · Wiki · Reference
/start ─▶ /to-prd ─▶ /to-issues ─▶ /triage ─▶ ⚡ /afk
refine publish slice into write the drain →
the plan a PRD vertical AGENT-BRIEF test, merge,
slices close, repeat
A reddb.io adaptation of
mattpocock/skills— same DNA, sharper edges, an autonomous loop layered on top. Massive thanks to @mattpocock; the original lives at aihero.dev. We pin upstream via.upstreamand a daily workflow (red-upstream-watch.yml) opens an issue when it advances, so we cherry-pick what's worth taking.
The fastest path — and the only one that auto-updates. RedSkills ships as a Claude Code plugin marketplace: add the marketplace once, install the plugin, and Claude Code pulls new commits at startup automatically.
Inside Claude Code:
/plugin marketplace add reddb-io/red-skills
/plugin install red-skills@red-skills
That's it. From now on Claude Code checks reddb-io/red-skills at every session start and pulls new skills/fixes silently. Toggle the behaviour with /plugin → Marketplaces → select red-skills → Enable auto-update (default on for this marketplace).
To force a refresh without restarting:
/plugin marketplace update red-skills
To remove:
/plugin uninstall red-skills@red-skills
/plugin marketplace remove red-skills
npx skills (alternative — Matt's installer)npx skills@latest add reddb-io/red-skills
skills.sh walks you through which skills to install and which coding agents to install them on. No auto-update — re-run the command to pull new versions. Same installer Matt uses for his upstream repo — credit to @mattpocock.
For local edits or $<name> access from Codex / Gemini CLI:
git clone [email protected]:reddb-io/red-skills.git ~/code/red-skills
cd ~/code/red-skills
./scripts/link-skills.sh # symlinks every SKILL.md into ~/.claude/skills/
Update later with git pull && ./scripts/link-skills.sh. Symlinks point at the working tree, so a git pull updates every agent at once.
| Agent | Invocation | Notes |
|---|---|---|
| Claude Code | /afk, /wiki, /triage, … | Native slash commands. Marketplace install (option 1) handles everything. |
| Codex CLI | $afk, $wiki, $triage, … | The $ is a convention: when the agent sees $<name>, it finds ~/.claude/skills/<name>/SKILL.md on disk and follows the instructions. Add the snippet below to ~/.codex/AGENTS.md once. Requires manual install (option 3). |
| Gemini CLI / others | $afk, etc. | Same $<name> convention. Works with any agent that can read files under ~/.claude/skills/ and run bash. |
Teach Codex (or any non-Claude-Code agent) the convention by appending to ~/.codex/AGENTS.md:
## RedSkills
When the user types `$<name>` (e.g. `$afk`, `$wiki`, `$triage`), look up
`~/.claude/skills/<name>/SKILL.md` and follow it — usually that means running
`bash ~/.claude/skills/<name>/scripts/<entrypoint>.sh` with the documented flags.
Each SKILL.md is self-documenting; read it before invoking.
Run once per target repo (from inside the repo):
/setup-red-skills
It walks you through five short decisions:
Product skill: how to use the reddb.io managed cloud — signup, create a database, get a connection string, connect from any RedDB driver. Skeleton/early — for engine usage once connected, see the `reddb` skill.
Product skill: how to use RedDB (the AI-first multi-model database) effectively from any agent. Cheatsheet + recipes covering SQL, graph, vectors, KV, time-series, queues, ASK/RAG, HTTP/gRPC/embedded, migrations, VCS, AI providers.
npx claudepluginhub reddb-io/red-skills --plugin brainComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Payload Development plugin - covers collections, fields, hooks, access control, plugins, and database adapters.