Find deepening opportunities in the codebase, informed by the domain language in docs/glossary.md and the architecture in docs/architecture.md. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.
Assemble a context package (code graph, requirements, constraints, blast radius) before a downstream generation task runs - human-approved, source-attributed. Do NOT use for simple lookups.
Register, resolve, and validate where a project's path-slots actually live via .layout-slots.yaml markers, so relocating a slot needs zero SKILL.md edits. Do NOT use for single-file lookups.
Use when driving a uigraph workspace over MCP — building or auditing the UI transition graph, reconciling LLM proposals, or running Tier-3 runtime verification. Load before calling any uigraph tool.
Drive Gusset, the repo custodian: index a repository into a verified code graph, run blast-radius impact analysis before changes, keep architecture docs fresh, find dead code and stale doc references, and install the autonomous mode that reviews PRs. Use when the user asks what a change affects, wants…
Use the Weavatrix MCP when a repository task benefits from indexed evidence: codebase orientation, symbol/source search, dependency or call graphs, change impact, API/event tracing, architecture checks, Git/coverage evidence, duplicates, dead-code review, or semantic context. Skip it for trivial single-file edits or…
Use the Weavatrix MCP when a repository task benefits from indexed evidence: codebase orientation, symbol/source search, dependency or call graphs, change impact, API/event tracing, architecture checks, Git/coverage evidence, duplicates, dead-code review, or semantic context. Skip it for trivial single-file edits or…
Trace the structural blast radius of a proposed or actual code change with ai-architect. Use for implementation planning, pull-request review, regression analysis, dependency checks, or identifying callers, importers, users, communities, and processes affected by a symbol or diff.
Build an evidence-backed map of an unfamiliar repository with the ai-architect code graph. Use before implementing a feature, debugging an unfamiliar subsystem, explaining architecture, or making structural claims about symbols and dependencies.
Check whether a proposed implementation plan matches the current code graph. Use before coding or approving a plan that names files, symbols, dependencies, boundaries, or expected blast radius; this is structural plan validation, not full PRD or semantic correctness verification.
Turn on token-efficient code-graph routing for the current repository. Builds a structural code index and installs the routing agent so the host CLI answers "who calls X / what breaks if I change Y" from a prebuilt graph instead of repeated grep, cutting cumulative context tokens. Use when the user types /token-master…
Continue AICodeGrapher next-feature work under extensions/ (impact, incremental, symbol search, monorepo, dashboard, presets, GitHub Action, VS Code extension). Use when implementing or promoting the next feature set beyond core MCP/task/budget.
Navigate repositories with AICodeGrapher compact code graphs, task→file packs, and token-budget maps via CLI or MCP. Use when starting work on an unfamiliar codebase, when the user asks to save tokens / avoid dumping the whole repo, or when picking which files to read for a coding task in Cursor, Claude, or Codex.
Route code search, symbol lookup, call-graph analysis, and codebase understanding through the nexus-mcp MCP server tools instead of Read/Grep/Glob. Use whenever exploring an indexed codebase, finding a symbol/function/class, tracing callers/callees or transitive change-impact before refactoring, getting a project…
Connect Claude Code (or any MCP client) to a running Celmis instance and query the code index — symbols, callers, cross-repo edges, dependency audits — instead of grepping a checkout. Use when setting up the MCP connection, when an MCP call fails, or when deciding which Celmis tool answers a question.