Claude code starter template with memory bank rules
This repository also configures its own agents. See what claude-skills tells them →
Skill Claude CodeCodex
Use when the user wants a git-history health check of an unfamiliar or inherited repository — triggers on "git recon", "codebase health check", "analyze this repo's history", "where are the landmines", or onboarding/due-diligence framing. Do NOT use for architecture review, bug-fixing, or feature work; this skill…
Skill Claude CodeCodex
Use when the user needs to create a presentation, pitch deck, slide deck, or visual summary about a project, codebase, website, or topic. Triggers on requests like 'build a deck', 'create a presentation', 'make slides about', or 'pitch deck for'.
Skill Claude CodeCodex
Migrate docs from bd (beads) to br (beadsrust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.
Skill Claude CodeCodex
Use this skill when debugging Kubernetes deployments, troubleshooting failed rollouts, investigating ArgoCD sync issues, fixing GitOps deployment problems, analyzing pod failures, resolving image pull errors, or diagnosing service connectivity issues. This includes working with kubectl, ArgoCD CLI, GitOps…
Skill Claude CodeCodex needs its repo
Use this skill when debugging Node.js applications, fixing service startup issues, resolving npm/dependency errors, troubleshooting runtime failures, investigating connection problems, or when stuck on seemingly simple Node.js issues. This includes analyzing error messages, testing services systematically, checking…
Skill Claude CodeCodex
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
Skill Claude CodeCodex
Use when scripting, controlling, debugging, or building UI for a Hyprland (Wayland) compositor configured in Lua (hyprland.lua — native since Hyprland 0.55, not hyprland.conf). Symptoms — hyprctl dispatch/keyword fail with Lua parse errors; a special/scratchpad workspace toggles the wrong (default special:special)…
Skill Claude CodeCodex
Autonomous work mode that lets Claude work continuously while the user is away. Activates pre-flight risk assessment, dangerous-ops approval, and a blocker decision framework. Use "/nonstop" to activate, "/nonstop off" to deactivate. Use this skill whenever the user says things like "go nonstop", "keep working"…
Skill Claude CodeCodex
Use when operating, upgrading or debugging Frappe/ERPNext on Kubernetes: config that won't take (bench set-config), a first site (encryptionkey), bench migrate or a major upgrade, a Helm chart bump (Valkey), the Error Log, email, PDF / chromium errors, or a report that looks permission-locked.
Skill Claude Code
Use before you finalize a written deliverable (a PR or commit message, design doc, README, runbook, report, or release note), or when asked to de-slop, tighten, plain-English, or cut hedges and filler from text. Also before you claim a writing deliverable is done.
Skill Claude CodeCodex
Use when tightening, shortening, cleaning up, restructuring, or de-waffling a draft — email, memo, status update, PR description, proposal, or announcement — especially when it opens with context instead of the conclusion, buries the recommendation or ask at the end, reads as a chronological recap, rambles, or needs…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: