← all publishers

manu-brighter

@manu-brighter source repo

5 published skills

  1. Generalize · manu-brighter
    Use when the user wants to turn a personal skill, agent, or project into a clean, publishable version for others — stripping everything that ties it to *them* (real name, employer, private project names, internal tools/systems, local paths, emails, customer/ticket IDs) while KEEPING the functional preferences that make it good (e.g. "use trailing commas", commit conventions, code style). Produces a generalized COPY and a change report; never touches the original. Trigger on: "generalize this skill/agent/project", "make this shareable/publishable", "clean it up before I push it to GitHub", "remove my personal info", "anonymize this", "prep this for open-sourcing", and the German equivalents "generalisieren", "anonymisieren", "für andere veröffentlichen", "auf GitHub publishen", "veröffentlichungsreif machen", "persönliche Infos rausnehmen". Use this whenever someone is about to share something they built for private use, even if they don't say the word "generalize".
    0
    installs
  2. Erklaerbaer · manu-brighter
    Breaks any context (a concept, code, an error message, jargon) down into a simple explanation an absolute beginner can follow — friendly "Erklärbär" persona (ʕ•ᴥ•ʔ), everyday analogies, compact, ASCII diagrams where they help, kaomoji instead of emojis. Detects whether the user wants to understand it themselves or needs something forwardable, and answers in the language of the input. Use when the user explicitly asks for something explained simply or for someone with no background knowledge. English signals: "ELI5", "explain like I'm five", "for dummies", "in plain English", "break it down", "dumb it down", "I don't get X", "for my grandma". German signals: "erklärbär", "erklär mir das einfach", "für meine Oma", "auf normal-deutsch", "mach das simpel", "ich raff X nicht". Do NOT use for normal developer-level questions ("what does this function do", "why is the test failing", "make the code simpler") — without an explicit simple/beginner signal the bear does not trigger.
    0
    installs
  3. List Skills · manu-brighter
    Shows a compact overview of all available skills with a one-line description each — grouped into Custom (your own), Plugins/Add-ons, and built-in Claude Code skills. Meant as an at-a-glance overview so you don't lose track when you have many skills installed. Use this skill whenever the user wants to know which skills they have — even if they only say "which skills do I have", "skill overview", "list skills", "list custom skills", "show me my skills", "what skills are installed", "which custom skills exist", "short skill list", "overview of skills" or similar. Also triggers on questions about plugin skills or "which plugins/add-ons ship skills". Replaces the long, verbose scrolling through the system skill list with a terse table.
    0
    installs
  4. Project Refresh · manu-brighter
    Audits the project's documentation-adjacent artifacts — README, project brief, CHANGELOG, further docs (docs/, wiki exports), deployment info (compose files, reverse-proxy and orchestration config docs), and i18n/translation files — against the actual current state of the codebase, and fixes whatever has drifted out of date. Also translates new/changed UI strings directly into every existing locale file. EXPLICIT-INVOCATION ONLY: use this skill solely when the user invokes it by name or runs it as a slash command. Do NOT auto-trigger or infer it from generic requests like "update the docs", "sync the README", "add translations", or "bring the project up to date" — for those, do the work directly or ask which parts they mean. This skill is strictly opt-in, and distinct from `full-project-rework` (which is a heavy code-quality overhaul with its own docs-sync step) — this one is documentation, deployment-info and i18n only: lightweight, no branch, no multi-phase pipeline.
    0
    installs
  5. Full Project Rework · manu-brighter bundle
    Runs a complete, autonomous, three-phase project overhaul — parallel analyzer subagents, then reviewer subagents that decide what ships, then implementer subagents that apply the changes (each on a dedicated branch, one commit per category). EXPLICIT-INVOCATION ONLY: use this skill solely when the user invokes it by name or runs it as a slash command. Do NOT auto-trigger or infer it from general requests like "improve the codebase", "clean this up", "modernize", "audit the project", or "fix the whole project" — for those, do the work directly or ask. This skill is strictly opt-in.
    0
    installs