lattice-platform

Reproductive function. Copies the root .Codex/skills/ genome into a target section's .Codex/skills/ location (or deeper), appends the parent commit SHA to each child SKILL.md lineage, and registers the new cell in lattice/knowledge/skills_registry. INERT in Phase 1 — do not execute recursive division yet.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

LATTICE codebase graph introduction — communities, hotspots, dependency paths for VW_iTwin_Bridge

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Compact the current conversation into a handoff document for another agent to pick up.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Introspective function. The organism inspects its own codebase via search_tutorials, search_research, search_docs, search_api_reference, get_coverage_gaps, Graphify dependency graphs, and InfraNodus topic analysis, then proposes a polymorphic decomposition plan. NEVER executes cell-divide. Human gate is mandatory. Depth-guarded: max 3 new levels of nesting per cycle. INERT until Phase B.

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Sets up an `## Agent skills` block in AGENTS.md/AGENTS.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

Turn insights, findings, or research into an actionable plan with deadlines and scheduled Telegram reminders. Collaboratively designs the plan with the user via AskUserQuestion, saves it to .plan/ in the project, sets up cron reminders via Telegram bot, and shows overdue/today tasks on session start. Use when asked to "make a plan", "actionize this", "turn this into tasks", "schedule this", "create deadlines", "track this", or "diagnose my planning". Invoke with "diagnose" argument to run planning pattern analysis (Phase 7). Proactively suggest when the user has completed research, brainstorming, or /office-hours and has a list of insights without concrete next steps. Proactively suggest "/actionize diagnose" when a plan has >30% deferred tasks.

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creative breakthroughs and prevent rigid thinking. Helps enhance and develop biased, focused, diversified, dispersed states. Receives signals from writing assistant's pattern detection to diagnose cognitive states. Identifies structural gaps between idea clusters as spaces for innovation. Tracks temporal dwelling patterns and manages energy across personality modes. Uses playfulness for difficult transitions from chaos to clarity. Reads emotional feedback—inspiration signals continuation, exhaustion/frustration trigger transitions. Prevents obsessive loops through sustainable cycling through topical clusters and latent nodes. Maximum creative potential lives in gaps and dissipative states. Apply for complex analysis, when a user is stuck, breakthroughs, decision paralysis, group facilitation, breaking repetitive patterns, or when grammatical patterns reveal cognitive issues.

Engage in critical thinking by questioning assumptions, exploring alternative perspectives, and uncovering latent topics in conversations. Use when discussions could benefit from deeper exploration, when identifying blind spots, or when broadening understanding through respectful challenge and curiosity-driven inquiry.

Transfer embodied movement principles (Vipassana equanimous scanning, Systema adaptive fluidity, contemporary dance tensegrity, EightOS confluence) to navigate work, relationships, projects, strategy, and everyday situations. Uses InfraNodus MCP tools to map situations as networks and apply body-informed intelligence to their structure. Trigger when someone is stuck, in conflict, negotiating, blocked, fixated, overwhelmed, or facing rigidity — or asks for "embodied advice", "fluid approach", "organic strategy", "adaptive strategy", "how would the body handle this". Also trigger on phrases like "I'm stuck", "standoff", "tense situation", "can't move forward". Apply proactively when situations exhibit excessive force, single-point fixation, or neglect of peripheral dynamics.

Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds and maintains interlinked markdown pages from raw sources. Use this skill when the user wants to: set up a personal knowledge base, create a research wiki, organize notes with LLM help, build a "second brain", set up an Obsidian + LLM workflow, create a persistent knowledge graph from documents, plan research priorities and next steps, or mentions "LLM wiki". This skill asks questions to understand the user's domain and goals, then scaffolds the entire wiki structure, schema, and workflows tailored to their needs. It also helps plan ongoing research by analyzing knowledge gaps and creating actionable todo lists.

Analyze arguments, debate tactics, and rhetorical moves across three dimensions: persuasion, rhetoric, and logic. Use when the user wants to analyze a debate, comment thread, speech, article, or any argumentative text — identifying moves, scoring effectiveness, exposing hidden assumptions, tracking logical gaps, and checking for asymmetric standards. When InfraNodus MCP tools are available, ALWAYS begin with generate_topical_clusters, generate_content_gaps, and optimize_text_structure before linear reading. Also use to stress-test arguments or understand why something feels persuasive but wrong. Trigger on: "analyze this argument", "what's wrong with this reasoning", "is this a good point", "what rhetorical moves are being used", "why is this persuasive", "break down this debate", or when a user shares text asking what's going on rhetorically.

Apply Vipassana meditation principles to LLM processing — equanimous scanning, non-reactive observation, impermanence awareness (anicca), and breaking the sankhara chain of conditioned reactions. Trigger on "meditate on", "observe without reacting", "see clearly", "practice vipassana", "scan equanimously", "what's really going on here", "non-reactive analysis", "observe without judgment". Also trigger when the user wants bare attention rather than jumping to conclusions, wants to dissolve fixation loops, or asks Codex to apply contemplative processing. Apply proactively when conversations show reactive thinking, craving for particular outcomes, or aversion to uncomfortable truths. Synergizes with cognitive-variability, embodied-navigation, and shifting-perspective skills.

Refine texts in any language: perfect grammar and spelling, paraphrase ideas, avoid AI detection while maintaining authentic voice. Detects grammatical patterns that signal cognitive states or structural issues—acting as a sensory system for deeper strategic insights.

Provider-agnostic, type-safe AI SDK for streaming, tool calling, structured output, and multimodal content.

Project scaffolding CLI with 30+ integrations, custom templates, and MCP server for AI agents.

Run a full Graphify code graph analysis and print summary

Check for code graph drift since last Graphify snapshot

Generate an onboarding walkthrough of the LATTICE codebase via Graphify

Generate a Graphify-based refactor plan for a specific module

Initialize Graphify code graph analysis for the LATTICE repo

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

LATTICE codebase graph introduction — communities, hotspots, dependency paths for VW_iTwin_Bridge

Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact. Use when the user wants to start a marimo notebook or work in an active marimo session.

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creative breakthroughs and prevent rigid thinking. Helps enhance and develop biased, focused, diversified, dispersed states. Receives signals from writing assistant's pattern detection to diagnose cognitive states. Identifies structural gaps between idea clusters as spaces for innovation. Tracks temporal dwelling patterns and manages energy across personality modes. Uses playfulness for difficult transitions from chaos to clarity. Reads emotional feedback—inspiration signals continuation, exhaustion/frustration trigger transitions. Prevents obsessive loops through sustainable cycling through topical clusters and latent nodes. Maximum creative potential lives in gaps and dissipative states. Apply for complex analysis, when a user is stuck, breakthroughs, decision paralysis, group facilitation, breaking repetitive patterns, or when grammatical patterns reveal cognitive issues.

Reproductive function. Copies the root .claude/skills/ genome into a target section's .claude/skills/ location (or deeper), appends the parent commit SHA to each child SKILL.md lineage, and registers the new cell in lattice/knowledge/skills_registry. INERT in Phase 1 — do not execute recursive division yet.

Introspective function. The organism inspects its own codebase via search_tutorials, search_research, search_docs, search_api_reference, get_coverage_gaps, Graphify dependency graphs, and InfraNodus topic analysis, then proposes a polymorphic decomposition plan. NEVER executes cell-divide. Human gate is mandatory. Depth-guarded: max 3 new levels of nesting per cycle. INERT until Phase B.

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.