Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

mfraunhofer

@mfraunhofer source repo

8 published skills

  1. ▌
    Pm · mfraunhofer bundle
    Project-management chat skill that coordinates parallel spawn chats through a shared PM inbox. The PM chat never does the work, it maintains a state file (`<workspace>/.scratch/pm-state.md`), keeps the overview, and hands work out as dispatch prompts written to disk; spawn chats do the actual work and report back through the inbox. Measurable facts (branch, worktrees, inbox backlog, file size, board state) are stamped by bundled scripts instead of written by hand. Use when the user says "box <project>", a bare "box", "/pm", "status [project]", "recap", "what's next?", "where are we on [project]?", "pm status", or pastes a report from a spawn chat. NOT for deep issue thinking, code edits, research, TDD, or reviews (all spawn-chat work).
    0
    installs
  2. ▌
    Pitch · mfraunhofer bundle
    Lightweight pre-planning skill that turns a fuzzy idea into a structured Feature Pitch (pitch.md) before any deeper planning or PRD step runs. Asks 6 questions one at a time with adaptive multiple-choice anchors, then writes the pitch file. Use when the user says "/pitch", "I have an idea for", "let's pitch this", "new feature idea", "I want to build", or whenever a software idea needs to be shaped before a domain/spec review. NOT for full PRDs, abstract strategy, or ideas that already have a detailed spec.
    0
    installs
  3. ▌
    Handover · mfraunhofer bundle
    Handover
    0
    installs
  4. ▌
    Auto Wave · mfraunhofer bundle
    Sequential wave runner. Drives a queue of "waves" automatically, one after another, each wave as a FRESH headless `claude -p` process (empty context, so nothing piles up), branch isolated so nothing auto-deploys, with an exception stop: it holds only when a wave is not green or a real product decision comes up. A wave counts as green ONLY with proof (executed_tests > 0, no skips, a real proof artefact; a non-empty caveat is a stop signal), self-attestation counts as red. After a green run the end-of-run hook does everything UP TO the merge: push, open the PR, post a fresh code review, write a deploy handoff, notify, report. It NEVER merges and NEVER deploys. Use when the user says "/auto-wave", "run the waves", "start auto-wave", "work through the queue", "start the wave runner", "build the waves automatically". Mode "full" chains waves, pre-deploy and deploy behind one word, with a fixed abort list as the gate. NOT for planning a single wave, building a single issue, reviewing, or deploying on its own.
    0
    installs
  5. ▌
    Check Domain · mfraunhofer bundle
    Check domain availability with a whois lookup against the official registrars (DENIC for .de, EURid for .eu, Verisign for .com/.net, PIR for .org). Use when checking if a domain is available, during brand/naming research, or before registering a new domain.
    0
    installs
  6. ▌
    SEO Geo Audit · mfraunhofer bundle
    seo-geo-audit
    0
    installs
  7. ▌
    Usage Dashboard · mfraunhofer bundle
    Local token-usage dashboard for Claude Code. Parses all session transcripts (~/.claude/projects/**/*.jsonl), aggregates usage per day / model / project / session / time-of-day / main-chat-vs-subagent, and renders a self-contained HTML dashboard with a USD cost equivalent (API list prices). Use when you want to see how much you've spent, what a day/project/model cost, or your token usage over time. NOT for the rate-limit status line (the harness renders that itself).
    0
    installs
  8. ▌
    Process Interviewer · mfraunhofer bundle
    Relentless process interviewer that extracts a complete, unambiguous plan from the user's head before any building begins. Use when the user wants to plan a complex task, design a process, build a skill, create a workflow, scope a project, or says things like "I want to build", "let's plan", "help me think through", "I have an idea for", "scope this out", "interview me", "help me figure out the process", "I need a skill that", or any variation where the user has a fuzzy idea that needs to be sharpened into a concrete plan. Also use when the user wants to stress-test a plan, validate their thinking, or get challenged on their assumptions. If the user's goal is to build a skill, this interviewer will automatically create it after the interview is complete. ALWAYS use this skill before jumping into building anything complex. Even if the user seems confident, the interview reveals gaps they didn't know they had.
    0
    installs