all publishers

Moonweave-Systems

@moonweave-systems source repo

8 published skills

  1. ▌
    Compass 2 · moonweave-systems bundle
    User-invoked mid-session audit skill. Detects (1) drift between current task and original session intent via transcript analysis, and (2) codebase rot — git uncommitted accumulation, test/lint state from cached artifacts, file bloat, TODO accumulation, circular dependencies, module boundary degradation. Manually triggered via `/compass` only — never auto-invoked. Use when the user types `/compass` optionally followed by a baseline intent string. Without arguments, derive baseline via cascade — most recent spec (24h), then task-init heuristic, then explicit user prompt. Never use the literal first user message of the transcript as baseline.
    4 installs
  2. ▌
    Anneal 2 · moonweave-systems bundle
    A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate directions, cheaply score each by that fitness, and pick the winner by the number — not by taste, and not by polish. Lightweight and inline: it is a discipline, not a multi-agent engine. Manually triggered via `/anneal` only — never auto-invoked. Use when the user types `/anneal`, typically at a fork where the best approach is not obvious.
    4 installs
  3. ▌
    Decide 2 · moonweave-systems bundle
    User-invoked research skill. Investigates current industry best practice via parallel WebSearch + context7 + GitHub adoption signals, then either decides autonomously (reversible actions) or escalates with factual-context questions (contested or information-requiring decisions). Manually triggered via `/decide` only — never auto-invoked. Use when the user types `/decide` optionally followed by a question. Without arguments, extract the pending decision from the prior assistant message.
    5 installs
  4. ▌
    Anneal · moonweave-systems bundle
    A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate directions, cheaply score each by that fitness, and pick the winner by the number — not by taste, and not by polish. Lightweight and inline: it is a discipline, not a multi-agent engine. Manually triggered via `/anneal` only — never auto-invoked. Use when the user types `/anneal`, typically at a fork where the best approach is not obvious.
    6 installs
  5. ▌
    Decide · moonweave-systems bundle
    User-invoked research skill. Investigates current industry best practice via parallel WebSearch + context7 + GitHub adoption signals, then either decides autonomously (reversible actions) or escalates with factual-context questions (contested or information-requiring decisions). Manually triggered via `/decide` only — never auto-invoked. Use when the user types `/decide` optionally followed by a question. Without arguments, extract the pending decision from the prior assistant message.
    5 installs
  6. ▌
    Workflow Router · moonweave-systems bundle
    Use when a request is broad, ambiguous, or multi-step and the right workflow (implementation, debugging, review, GitHub, research, workflow design, system triage, artifacts) must be chosen before execution. Also use when choosing or designing whether a repeatable workflow belongs in a skill, plugin, MCP, script, repo doc, or direct implementation path.
    4 installs
  7. ▌
    Compass · moonweave-systems bundle
    User-invoked mid-session audit skill. Detects (1) drift between current task and original session intent via transcript analysis, and (2) codebase rot — git uncommitted accumulation, test/lint state from cached artifacts, file bloat, TODO accumulation, circular dependencies, module boundary degradation. Manually triggered via `/compass` only — never auto-invoked. Use when the user types `/compass` optionally followed by a baseline intent string. Without arguments, derive baseline via cascade — most recent spec (24h), then task-init heuristic, then explicit user prompt. Never use the literal first user message of the transcript as baseline.
    4 installs
  8. ▌
    Done Gate · moonweave-systems bundle
    A completion-boundary gate that distinguishes built-done (tests pass) from useful-done (a real consumer gets real value) at the moment work is declared finished. Manually triggered via `/done-gate` only — never auto-invoked. Use when the user types `/done-gate` after declaring work done.
    3 installs