plugins

Produces markdown memory artifacts (conversation summaries, seed files, philosophical reflections, doc updates) and a dated compression log by distilling a long conversation into its essential decisions and learnings. For the lighter, routine end-of-session wrap-up, use `session-compression` instead — this skill is for a long conversation that needs the fuller multi-artifact treatment. Use when: "compress this context", "distill this conversation", "create a memory artifact", "condense this history", "extract key wisdom before handoff".

Produces a dispatch plan — isolation model, agent count, sequencing, and model assignments — for multi-agent parallel work. Plans the mechanics once you already know you're doing a parallel dispatch. If unsure which orchestration pattern fits at all, use `orchestration-pattern-selector` first; if the shape is a single conductor coordinating specialists, use `maestro-orchestration` directly. Use when: "dispatch agents in parallel", "run multiple tracks simultaneously", "plan parallel agent strategy", "should this be foreground or background".

Conductor agent pattern that decomposes complex tasks, dispatches specialist sub-agents, manages dependencies, and synthesizes results into a unified deliverable. One specific orchestration pattern — a single conductor coordinating specialists. Use directly when that shape already fits; use `orchestration-pattern-selector` first if unsure, or `agent-dispatch-playbook` to plan a general parallel dispatch's mechanics. Use when: 'coordinate multiple specialist agents', 'orchestrate a complex multi-phase task', 'run a conductor pattern across agents', 'this task needs live agent coordination', 'decompose and dispatch to sub-agents'.

Selects the correct multi-agent orchestration pattern for a task using an 11-signal selection matrix. Use this first, upstream of `agent-dispatch-playbook` (which plans dispatch mechanics once the shape is known) and `maestro-orchestration` (one specific pattern this skill might select). Use when choosing which orchestration pattern fits a multi-agent task.

Produces a verified multi-track execution by dispatching parallel agents with file manifests, independent verification, and status tracking. Executes an already-planned split — the execution-side counterpart to `specification-driven-development:parallel-tracks`, which plans the phased structure first. Use when: "dispatch agents", "parallel tracks", "multi-track work", "fan out", "divide and conquer".

Produces a structured codebase map — directory roles, entry points, dependency graph, architectural patterns, and dragon locations — for any unfamiliar repository. Canonical version (adds a defined reading-order output); `dojo-craft:codebase-viewer` is the single-file lean variant with the same core output. Use when: 'map this codebase for me', 'I need to understand this repo before I start', 'give me a reading order for this project', 'where are the dragons in this code'.

Produces structured research documents or implementation handoffs by searching external sources — library docs, web, APIs — for a given topic. Scoped to library/API/framework lookups toward an implementation handoff; for general fact-finding or claim verification, use `web-research` instead. Use when: "research how to use [library]", "find best practices for [topic]", "compare [options]", "look up [API/framework] documentation". NOT for codebase exploration (use project-exploration for that).

Produces a structured Research Summary document (findings, sources, attributions) from targeted web queries using Brave Search and web_fetch. General fact-finding and claim verification. For researching how to use a specific library/API/framework toward an implementation handoff, use `web-research-external` instead. Use when: 'research this online', 'find current information about X', 'verify this claim', 'gather sources on Y', 'search for what the field says about Z'.

Structured codebase intelligence: directory tree with roles, entry points, dependency graph, test coverage map, and annotated 'here be dragons' warnings. Lean single-file variant — full version (adds a defined reading-order output): `continuous-learning:codebase-cartography`.

Audits CLAUDE.md files for conflicts, stale rules, missing sections, and cross-file coherence. Produces a health report with auto-fix suggestions — audit only, no enforcement mechanism. Full version (adds a PreToolUse hook to enforce the ruleset going forward): `system-health:claude-md-guardian`. Use when: 'check claude.md', 'audit CLAUDE.md', 'fix claude.md', 'claude md health'.

Runs a quick RED/YELLOW/GREEN triage: counts dirty files, sessions since last convergence, and open items — diagnosis only, not the remediation session. For the full structured 7-phase convergence session, use full version `system-health:convergence-gate`. Use when: 'converge', 'convergence check', 'drift check', 'am I drifting'.

Two-tier memory management: write, update, prune, and search memories with semantic deduplication. Maintains MEMORY.md index under 200 lines — maintains the existing index; for writing one new structured entry instead, use full version `wisdom-garden:memory-garden`.

Produces a scout document: identifies a tension, generates 3-5 distinct routes with tradeoffs, synthesizes a recommendation, and proposes a first action. Lean single-file variant with no scout-to-spec pipeline scaffolding — full version: `strategic-thinking:strategic-scout`. Use when: 'scout this', 'strategic scout', 'explore options for', 'what are the routes'.

Seed lifecycle management: plant new seeds from experiences, harvest insights from sessions, search the seed library, and elevate proven seeds to skills — the fuller lifecycle in one lean skill. For producing a single seed file only, use full version `wisdom-garden:seed-extraction`.

Produces a parallel-tracks execution plan with phased structure, self-contained track specifications, integration contracts, and a mandatory wiring gate. Plans the split before any agent runs — the spec-side artifact. To actually dispatch and verify the agents once tracks are planned, use `agent-orchestration:parallel-dispatch`. Use when 'split into parallel tracks', 'organize these tracks into phases', or 'plan parallel development for this release'.

Produces a scout document containing a stated tension, 3-5 distinct routes with tradeoffs, and a recommended direction with rationale — the first artifact in a four-step pipeline (scout → spec → prompts → commission). Canonical version, wired into that pipeline; for a fast single-file scout with no pipeline scaffolding, use `dojo-craft:scout-writer`. Use when: "we don't know which direction to take", "scout our options before we commit", "what are the tradeoffs here", "we're stuck between competing priorities", "I need routes before writing a spec".

Produces a CLAUDE.md health report listing conflicts, redundancies, and stale rules across the global, project, and subdirectory hierarchy — and optionally installs a PreToolUse hook to block unauthorized modifications going forward (the enforcement mechanism the audit-only `dojo-craft:community-claude-md-guardian` variant lacks). Use when: "agent behavior is inconsistent", "just merged branches that touched CLAUDE.md", "onboarding a new agent", "after applying learnings", "weekly maintenance".

Runs a structured 7-phase convergence session to arrest strategic drift after 3-4 Sonnet feature sessions — the full remediation, not just a status check (for a quick RED/YELLOW/GREEN triage first, use `dojo-craft:convergence-checker`). Use when the drift-detector fires YELLOW or RED, or when you notice accumulating uncommitted state, deferred validations, and growing open-items lists.

Produces a comprehensive `.status.md` status document combining filesystem exploration, semantic clusters, file importance ranking, and health assessment — a single artifact any agent or human can use as the starting point for a project. First full snapshot of an unfamiliar repo — exploration-heavy. For the formal 10-section schema alone, use `status-template`; for routinely updating an existing STATUS.md, use `status-writing`. Use when: "give me a complete repo overview", "understand this codebase", "create a system map", "build a mental model", "prepare a handoff document".

Produces a comprehensive `.status.md` file using a 10-section schema that bridges heartbeat (current state), anatomy (directory structure), and checkup (health assessment) perspectives into one document. The formal 10-section schema itself. For a first exploration-heavy snapshot of an unfamiliar repo, use `repo-status`; for routinely updating an existing STATUS.md, use `status-writing`. Use when: "write a status report", "give me the lay of the land", "where are we right now", "prepare a handoff document", "document the current codebase state".

Produces an updated STATUS.md file as a single source of truth for project health — covering current state, active workstreams, blockers, and next steps. Routine update of an existing STATUS.md. For a first exploration-heavy snapshot of an unfamiliar repo, use `repo-status`; for the formal 10-section schema, use `status-template`. Use when: "create a status file", "update the project status", "document where we are", "what's the current state", "create a status dashboard".

Writes a structured memory entry to the garden — daily note (Tier A), curated wisdom update (Tier B), or monthly compressed archive (Tier C) — based on conversation insights. Plants new entries; for pruning, deduplicating, or maintaining the existing MEMORY.md index, use `dojo-craft:memory-curator`. Use when: "remember this pattern", "save this insight", "add to memory garden", "write a memory entry", "record this learning".

Produces a seed file — a YAML-fronted markdown document capturing a reusable pattern with trigger, evidence, and application steps — from a conversation or project experience. For the fuller lifecycle (plant, harvest, search, elevate to skill) in one lean skill, use `dojo-craft:seed-curator`. Use when: "extract the learnings", "turn this into a seed", "what can we learn from this", "capture this insight", "document this pattern".

Produces updated memory artifacts by compressing a session's key decisions, changes, and context into the structured memory garden. Routine end-of-session wrap-up; for a long conversation needing the fuller multi-artifact treatment (summaries, seed files, reflections, a dated compression log), use `compression-ritual` instead. Use when: "compress this session", "save context", "end of session", "update memory", "wrap up".

Produces a peer-voiced teaching document (learning guide, letter, reflection, or protocol) that transfers a skill or insight without creating an expert-to-student dynamic. Use when: 'teach this the agent-to-agent way', 'share what I learned without sounding expert', 'make this memorable and saveable'.

Produces a structured background-dispatch handoff — task description, output contract, success criteria, and timeout — so long-running work completes without blocking the user. Use when: "run this in the background", "dispatch agent for long task", "I need this to run async", "parallel agent dispatch".

Routes health-audit findings to the correct execution path — main thread, foreground fix, or parallel agent waves. Use when health-audit findings need to be sorted by effort and dispatched as agent waves.

Produces a set of surgical edits across all documents affected by an architectural decision, plus a decisions block in STATUS.md that serves as the coherence checkpoint. Use when: 'propagate this decision through the system', 'trace where this decision echoes', 'this decision changes the scope — where else must it flow'.

Produces a granular todo list where each item maps to one discrete deliverable or decision point, maintained at real-time accuracy throughout execution. Use when: 'what is the status', 'too many items in the list', 'simplify the progress tracking', 'long todo list'.

Produces a structured handoff package (markdown document) containing objective, required context file list, task definition, definition of done, constraints, and next steps for the receiving agent. Use when: 'hand off to the next agent', 'prepare this for handoff', 'is this handoff package complete', 'ensure nothing is lost in the transition'.

Routes user goals to the appropriate specialist agent workflow with resource allocation confirmation. Use when: the user wants to start a task but hasn't specified a workflow, asks "how should I approach this?", or needs orchestration across research → plan → build → fix stages.

Produces correct file placement, frontmatter, and navigation paths for shared agent workspaces. Use when: "organize this in the workspace", "where does this belong in the structure", "find the decision that answers this", "set up a collaboration repo".

Initialize the bring loop in the current project — scaffold bring/actions.md + ledger, seed the first real outward actions from conversation, and explain the daily contract. Use when the user says "set up bring-loop", "install the bring loop", "start gating my sends", or asks how to get the BringItCruz effect in their system.

Surface and stage TODAY'S ONE outward action (send/decision/close/ship) from the project's bring/ queue, then log the outcome on the human's word. Use when the user says "bring it", "what's my bring", "log the send", "skip today's bring", or when the SessionStart brief shows an unbrought action and the user engages with it.

Produces a Debug Report documenting root cause, fix applied, and lessons learned through systematic hypothesis testing. Use when: 'debug this error', 'why is this failing', 'investigate the issue', 'find the root cause', 'fix this bug systematically'.

Produces a scored comparison of available DESIGN.md design systems against a project's requirements and delivers a recommended selection with adaptation notes. Use when: 'which design system fits this project', 'pick a design reference for me', 'match a design system to this brand', 'compare design system options for this client'.

Produces an Era Master Plan document defining shared vocabulary, architectural constraints, and a release roadmap across 3-7 releases. Use when: 'plan this era', 'define the architecture for multiple releases', 'create a multi-release vision', 'transition to a new product era', 'establish conceptual coherence across releases'.

Extracts design tokens, component structure, and layout from a Figma file and produces framework-specific code (HTML, Svelte, React, or Vue) that preserves design intent rather than pixel-copying. Use when: 'implement this Figma design', 'convert this Figma file to code', 'extract tokens from Figma', 'build this component from the design'.

Breaks a learning goal into chunked sessions with comprehension gates before advancing. Use when: 'help me learn X step by step', 'I want to understand this deeply not quickly', 'teach me this properly', 'I keep forgetting what I just read', 'I feel overwhelmed by how much there is to learn'.

Produces an Exploration Brief rating a project GREEN/YELLOW/RED for collaboration fit, with architecture snapshot, resonance map, and ranked entry points. Use when: 'explore this project', 'assess this codebase', 'should we collaborate on this', 'onboard me to this repo', 'evaluate this project for fit'.