using-mozg-pipelines

Separates look-alike mozg skills and chains several per task. Use when the user is unsure which of their tools fits or what they have ("which pipeline fits", "what plugins do I have", "route this"). N

SKILL.md

GitHub

Overview

This is a routing map, not a discipline skill. It loads on demand, when the user asks which skill fits or describes work without naming one, and tells Claude which concrete skill to invoke for that task phrase. Consult the map, then delegate to the matching skill. Do not attempt the work under this skill's own identity.

When to Use

Choosing which installed mozg skill or plugin fits a task, or seeing what is installed, when the user has not named a skill.

When NOT to use

  • The user already named a specific skill ("run audit", "use build") — invoke it directly.
  • The user is mid-phase inside another skill — stay inside that skill.
  • The user asked a direct question answerable without routing (code read, quick fix) — answer it.
  • The task matches exactly one obvious skill from context — invoke it without re-citing the map.

Core Process

  1. When the user states a task, map the phrase against the Techniques table BEFORE drafting an answer.
  2. If the phrase matches multiple skills, list all candidates with the distinguishing condition, ask which fits, or pick the most specific.
  3. If the phrase matches no entry, say so explicitly — do not invent a routing.
  4. Prefer the most specific skill over a general one (e.g., audit over debug certainty:low for security review).
  5. Do not paraphrase the user's task to fit a different skill's territory.
  6. After routing, invoke the target skill directly. Do not re-explain the routing decision to the user unless they asked.

Techniques

Routing table. Phrases are indicative, not exact matches.

Task phrase Skill Plugin
"build a feature", "implement X", "add capability" build mz-dev-pipe
"fix this bug", "debug", "why is this broken" debug mz-dev-pipe
"security review", "audit for vulns", "threat model" audit mz-dev-pipe
"polish this", "clean up", "refactor", "remove dead code", "strip AI comments", "clean up after the pipeline", "finalize" polish mz-dev-pipe
"optimize", "make it faster", "profile hotspot" optimize mz-dev-pipe
"why do we use Y", "does this project support Z", "quick sourced answer" ask mz-dev-pipe
"explain this code", "what does this do" explain mz-research-pipe
"investigate X", "dig into", "find root cause", "is X actually doing Y", "verify hypothesis" debug certainty:low mz-dev-pipe
"blast radius", "what breaks if I change X", "impact analysis" audit scope:branch or audit <path> (expands to impacted files) mz-dev-pipe
"deep audit", "pre-PR audit", "ship audit", "before publishing", "before I open a PR" audit depth:deep mz-dev-pipe
"research topic deeply", "survey the field" deep-research mz-research-pipe
"synthesize past research", "combine findings", "consolidate prior work" combine mz-research-pipe
"translate this", "localize", "translate to <lang>" translate mz-research-pipe
"bootstrap rules", "init project rules" init-rules mz-rules
"promote lessons", "turn lessons into rules" lessons-promote mz-memory
"write a handoff", "hand off before /clear", "resume from the handoff" handoff mz-handoff
"remember that", "note this", "pin this decision" memory-note mz-memory
"review my branch", "what changed locally" review-branch mz-dev-git
"review this PR", "what's wrong with this PR" github-review-pr mz-dev-git
"scan open PRs", "triage PRs" github-scan-prs mz-dev-git
"help me author a new skill", "write a SKILL.md", "construct a skill" construct-skill mz-base
"which skill fits", "route this", "what plugins do I have" using-mozg-pipelines mz-base
"draft an outreach brief", "prep outreach", "research local market for outreach", "scope outreach campaign", "outreach brief" outreach-brief mz-biz-outreach
"find leads", "customers matching X", "outreach list", "research targets", "find contacts at <company>", "decision-makers at X", "who do I write to" outreach-research mz-biz-outreach
"draft outreach letters from this card", "write letters from <card path>", "enrich this card", "deepen research on <card>", "go deeper on <card>" outreach-enrich-company mz-biz-outreach
"log action on <card>", "update card with <action>", "record interaction on <card>", "I just <action>, add to <card>" outreach-update-card mz-biz-outreach
"find a job", "search for vacancies", "job hunt", "match jobs to my CV" job-search mz-job-outreach
"find a recruiter", "hiring manager for X", "careers email for X", "who do I apply to" job-recruiter-info mz-job-outreach
"find freelance gigs", "freelance search", "contract work for my CV" freelance-search mz-job-outreach
"pitch this gig", "draft a proposal for gig 3", "freelance pitch" freelance-pitch mz-job-outreach
"brainstorm", "generate ideas", "creative options" brainstorm mz-creative
"write a landing page", "draft a launch email", "write release notes" copywrite mz-creative
"write docs for", "document this", "polish the README" document mz-creative
"critique this idea", "poke holes in my plan", "strengths and weaknesses of" expert mz-creative
"humanize this text", "make this sound less like AI" naturalize mz-creative
"should I do X or Y", "record this decision", "write an ADR", "RFD for X", "is this decision sound" govern mz-gov
"install governance policy", "init governance", "set up decision records" gov-init mz-gov
"review our ADRs", "audit decision records", "are our design docs sound" gov-review mz-gov
"roast this code", "make fun of this PR", "character roast" do-roast mz-funny
"design a UI for X", "design spec", "UX spec" design-document mz-design
"init vault", "bootstrap obsidian", "set up a knowledge base" obsidian-init mz-knowledge
"ingest audio", "transcribe this voice memo", "ingest this PDF" vault-ingest mz-knowledge
"triage inbox", "clear inbox", "fleeting review" vault-triage mz-knowledge
"process fleeting notes", "atomize this note" process-notes mz-knowledge
"import this research report into the vault", "research to notes" vault-research mz-knowledge
"link notes", "suggest wikilinks", "improve link density" vault-connect mz-knowledge
"what does my vault say about X", "search my vault for Y" vault-answer mz-knowledge
"review session", "notes due for review", "weekly review" vault-review mz-knowledge
"vault health check", "find orphan notes", "broken wikilinks" vault-health mz-knowledge
"vault schema", "validate frontmatter", "schema migration" vault-schema mz-knowledge
"rename note", "move note and update wikilinks" vault-refactor mz-knowledge
"epistemic status", "mark claims", "check this note's sources" vault-provenance mz-knowledge
"add a callout", "use a wikilink", "OFM syntax" obsidian-markdown mz-knowledge
".base file", "Bases view", "vault database" obsidian-bases mz-knowledge
"obsidian CLI", "edit vault notes from the shell" obsidian-cli mz-knowledge

mz-memory contributes SessionStart, SessionEnd, UserPromptSubmit and PostToolUse (AskUserQuestion) hooks, the /memory-note skill (notes, and lessons after a correction) and the /lessons-promote skill (recurring lessons into project rules); it is referenced by agents that need persistent state.

mz-handoff contributes SessionStart and Stop hooks and the /handoff skill, which writes a handoff file for a fresh session after repeated compactions and resumes from it after /clear.

Red Flags

  • You answered a routing-type question by attempting the task directly without checking the routing table.
  • You routed to a general skill (debug certainty:low) when a specific one (audit, audit depth:deep) exists for the phrase.
  • You paraphrased the user's task into a different skill's territory to justify a skill you prefer.

Verification

Before handing off, confirm:

  • The chosen skill appears in the routing table above, or you told the user that no entry matches.
  • When several skills matched, you named the condition that decided between them, or asked the user.
  • You invoked the target skill instead of doing the work under this skill's identity.