all publishers

puukis

@puukis source repo

28 published skills

  1. ▌
    Docs · puukis
    Writes accurate documentation by reading source first — never invents API signatures
    0 repo stars
  2. ▌
    Ship · puukis
    Pre-ship checklist that gates the release — runs 5 checks and blocks until all pass
    0 repo stars
  3. ▌
    Test · puukis
    Writes tests only — reads source and existing tests first, never touches source files
    0 repo stars
  4. ▌
    Work · puukis
    Start structured AI coding work with Brain overview, Repo Passport, Context Governor, Change Receipts, and AI Mistake Firewall awareness
    0 repo stars
  5. ▌
    Debug · puukis
    Systematic root cause analysis — reproduce, isolate, hypothesize, verify before any fix
    0 repo stars
  6. ▌
    Guard · puukis
    Enable maximum safety workflow by combining careful safety mode with a freeze edit boundary.
    0 repo stars
  7. ▌
    Learn · puukis
    Manually store a typed, trust-aware structured learning in lstack.
    0 repo stars
  8. ▌
    Forget · puukis
    Delete structured learnings or legacy observations from lstack memory.
    0 repo stars
  9. ▌
    Freeze · puukis
    Restrict Edit, Write, and MultiEdit to approved paths for the current Claude Code session.
    0 repo stars
  10. ▌
    Recall · puukis
    Search structured learnings and legacy observations in lstack memory.
    0 repo stars
  11. ▌
    Careful · puukis
    Enable opt-in warnings or denials for risky Bash commands in the current Claude Code session.
    0 repo stars
  12. ▌
    Debrief · puukis
    End-of-session structured reflection — what worked, what broke, what to do differently. Run before /exit.
    0 repo stars
  13. ▌
    Planner · puukis
    Structured task breakdown with clarifying questions before planning — no code written
    0 repo stars
  14. ▌
    Receipt · puukis
    Manage Change Receipts from Claude Code — wraps lstack brain receipt CLI
    0 repo stars
  15. ▌
    Engineer · puukis
    Writes production-ready code — reads patterns first, runs tests after, no gold-plating
    0 repo stars
  16. ▌
    Parallel · puukis
    Spawn isolated sub-agents across git worktrees for genuinely independent tasks
    0 repo stars
  17. ▌
    Passport · puukis
    Show or refresh Repo Passport and context — wraps lstack brain passport/context/overview CLI
    0 repo stars
  18. ▌
    Refactor · puukis
    Improves code structure without changing behavior — tests before and after each step
    0 repo stars
  19. ▌
    Remember · puukis
    Store a user-confirmed structured learning or durable observation in lstack memory.
    0 repo stars
  20. ▌
    Reviewer · puukis
    Code review producing only numbered actionable findings — no rewrites, no praise
    0 repo stars
  21. ▌
    Security · puukis
    Security audit — scans for secrets, injection, bad deps, auth issues; reports findings only
    0 repo stars
  22. ▌
    Unfreeze · puukis
    Clear the current Claude Code session freeze boundary.
    0 repo stars
  23. ▌
    Analytics · puukis
    Show lstack memory analytics, including structured learning health.
    0 repo stars
  24. ▌
    Architect · puukis
    Architect
    0 repo stars
  25. ▌
    Blueprint · puukis
    Generates a .blueprint.md spec file before any code is written. Agents implement against the blueprint, not vague prompts.
    0 repo stars
  26. ▌
    Changelog · puukis
    Generate a CHANGELOG.md entry from git log since last tag — invoked via /changelog
    0 repo stars
  27. ▌
    Interrogate · puukis
    Socratic requirement clarification — one question at a time before any planning or code. Auto-activates when a request is vague, large, or unclear.
    0 repo stars
  28. ▌
    Orchestrate · puukis
    Intelligent task routing — evaluates complexity and asks the user whether to handle in the main session or dispatch to specialist sub-agents. Entry point for any medium or large task. Run this before /build or /engineer on anything non-trivial.
    0 repo stars