soleri

Triggers: "learn from this", "harvest knowledge", "harvest this codebase", "extract patterns from". Bulk-extracts patterns from code/docs/PRs/articles into vault. Use vault-capture for single patterns, intake for ingesting external sources.

Triggers: "add a facade", "new tool", "extend vault", "add brain feature", "new skill", "extend agent". Extends agent internals with vault-first knowledge gathering.

Triggers: "AgentName, ...", "Hey AgentName", "what commands do I have", "what can you do with MCP", "command reference". Routes ambiguous intent to correct facade + op. Also handles vague phrases like "save this", "remember this", "search for patterns".

Triggers: "I want to build something", "let's think about", "what if we", "creative exploration", "ideate". Open-ended creative exploration when requirements are not yet clear.

Triggers: "check against patterns", "pattern compliance", "convention check", "review against vault", "institutional review". Reviews code against vault patterns/conventions. Use deep-review for general quality/architecture.

Triggers: "curator status", "vault health", "how is the vault", "curator health", "check vault quality", "what needs grooming". Quick vault health + grooming recs. Use vault-curate for full maintenance.

Triggers: "deep review", "code smells", "architecture review", "is this well architected", "optimization review". Multi-pass structural health/smells/quality review. Use code-patrol for vault pattern compliance.

Triggers: "ship it", "pre-PR check", "delivery checklist", "is this ready", "final review", "ready to deploy". Pre-delivery quality gates. Use verification-before-completion for mid-workflow checks.

Triggers: "I don't know where to start", "investigate", "research this", "explore the problem", "discovery". Structured exploration before committing to a plan, produces options with tradeoffs.

Triggers: "setup environment", "post-clone setup", "broken build", "missing dependencies", "MODULE_NOT_FOUND". Detects project needs, diagnoses gaps, produces setup checklist.

Triggers: "finish branch", "ready to merge", "PR ready", "submit PR", "close branch". Pre-merge checks, PR creation, merge strategy, branch cleanup.

Triggers: "fix it", "apply the fix", "patch this and remember", "fix and capture". Executes fix after root cause identified, captures learning to vault. Use systematic-debugging first.

Triggers: "system health", "agent health", "run diagnostics", "system status", "check health". Read-only knowledge base health assessment. Use vault-smells for deep quality analysis.

Triggers: "ingest this", "add this URL", "import this book", "read and capture", "ingest batch". Imports external content (URLs, text, books, batches) into vault with knowledge extraction.

Triggers: "start a loop", "run until done", "iterate until X", "loop status", "cancel loop". Iterative execution until condition met or grade threshold reached.

Triggers: "onboard me", "I'm new here", "project overview", "what should I know about this codebase". Structured tour of vault knowledge about this project.

Triggers: "run in parallel", "fan out", "concurrent execution", "batch execute", "dispatch subagents". Concurrent task execution via subagents. Use executing-plans for sequential.

Triggers: "scout", "research scout", "find new info", "what's new", "scan the web". Discovers new info that challenges or updates vault knowledge via web search.

Triggers: "sprint retro", "weekly summary", "what went well", "end of sprint", "monthly report". Time-bound work reflection with actionable improvements. Use brain-debrief for pattern intelligence.

Triggers: "second opinion", "technical decision", "comparing approaches", "which approach". Informed recommendations backed by vault, brain, and web research.

Triggers: "use subagents", "parallel agents", "subagent driven", "isolated execution". Decomposes work into isolated units, dispatches subagents.

FIRST response for "bug", "failing test", "not working", "debug this", "error", "crash", "weird issue". Diagnoses root cause before fixes. Hand off to fix-and-learn for repair.

Triggers: "save this to vault", "capture this", "remember this pattern", "add to vault", "vault capture". Durable patterns/decisions/anti-patterns. Use memory_capture for session notes, knowledge-harvest for bulk extraction.

Triggers: "clean vault", "deduplicate vault", "groom knowledge", "merge patterns", "vault maintenance". Vault quality via dedup, grooming, contradiction detection.

Triggers: "search the vault", "find patterns for", "have we seen this before", "vault search", "best practice for". Queries knowledge base for existing solutions and prior art.

Triggers: "create a plan", "write up a plan", "break this down", "plan the implementation". Produces markdown plan file. Priority over orchestrate_plan for explicit requests. Use brainstorming for ideation.

Triggers: "implement X", "build Y", "fix Z", "add feature", or any work task needing planning + execution. Full orchestration loop: plan, execute, complete with vault context and brain recs.

Triggers: "yolo", "autonomous", "skip approvals", "full auto", "hands off". Autonomous execution skipping approval gates, safety invariants preserved.

Triggers: "terse mode", "be brief", "less tokens", "fewer tokens", "compress output", "caveman", or invokes /terse. Token-efficient responses with full technical accuracy.

Triggers: "compress this file", "compress CLAUDE.md", "compress memory", "shrink this", "reduce tokens in file", or invokes /compress. Compresses natural language files to save input tokens.

Triggers: "what can you do", "how do I use this", "what features", "what tools available", "who are you", "show capabilities". Agent capability discovery and tool reference.

Triggers: "create issue", "file bug", "gh issue", "create task", "report bug", "create tickets". Creates structured GitHub issues optimized for agent execution.

Triggers: "activate persona", "be yourself", "stay in character", "hello [agent name]". Reinforces character persistence across session and context compaction.

Triggers: "brain stats", "pattern strengths", "intelligence report", "show brain data", "what patterns are strongest". Surfaces brain pattern intelligence. Use retrospective for time-bound work reflection.

Triggers: "create a skill", "new skill", "build skill", "add a skill", "write a skill", "skill template", "scaffold skill". Creates/updates/scaffolds Soleri agent skills.

Triggers: "where did I leave off", "what was I working on", "catch me up", "resume session", "continue where we stopped". Reconstructs working context from memory, plans, sessions.

Triggers: "dream", "consolidate memory", "clean up memory", "memory cleanup", "dream status". Automatic memory consolidation: dedup, archive stale, resolve contradictions.

Triggers: "execute my plan", "run the plan", "start executing", "implement the plan". Sequential task execution with review checkpoints. Use parallel-execute for concurrent.

Triggers: "MCP not working", "tools missing", "fix MCP", "mcp doctor", "server not connecting". Diagnoses and repairs MCP server connectivity.

Triggers: "release", "bump version", "publish packages", "cut a release", "version bump", "npm publish". Bumps monorepo versions, commits, tags, pushes to trigger CI release. Use deliver-and-ship for quality gates.