notebook-audit
Adversarial consistency audit over the notebook knowledge base — finds contradictions in a document corpus: the same category with conflicting amounts, the…
A command is the one you type. It runs exactly when you ask it to, and never before.
8,043 commands across 582 plugins.
Adversarial consistency audit over the notebook knowledge base — finds contradictions in a document corpus: the same category with conflicting amounts, the…
Turn a notebook knowledge base into a knowledge GRAPH — a node-link graph.json + a self-contained interactive graph.html — with NO agy calls and NO extra deps.…
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which…
Context and session management - save, restore, optimize
Discard all pending learnings without applying.
Sync skills between Cursor (source) and Claude (generated flat) formats
Run skill validation (frontmatter, naming, triggers, links)
[beta] Run quick, deep, or audit scan profiles and emit a shared findings artifact
[stable] Prepare focused analysis scope for large codebases, list workspaces in monorepos
[beta] Search for dangerous functions (sinks) and auto-discover output patterns
Full design pipeline for a web or web-app target: brief → tokens → generation → motion → review. Use /design:mobile for iOS/Android instead.
Generate a single component using existing design-system.md tokens. Skips inspiration browsing — fast path for isolated UI elements.
iOS or Android mockup + handoff spec. Argument: ios|android. Produces tokens, a device-framed HTML mockup, and a spec for swift-expert or an Android developer…
Detect and, on explicit consent, additively append the languages Serena is not indexing to the `languages:` list in `.serena/project.yml`, then prompt a Serena…
Author an immutable SPEC artifact through Socratic discovery (spec-kit wrapper), then STOP. Terminal, never runs /gaia-plan; it prints a /gaia-plan prompt the…
Maintainer-only autonomous health audit + auto-heal loop. Runs N=3 fresh-team audit-fix-audit cycles with circuit breakers, reports an F-to-A+ verdict (folding…
Validate _router.md — check every referenced skill file exists; surface stale entries + orphan files; --fix prunes or stubs
List every active tool across all MCP servers and flag cross-MCP duplicates and semantic overlaps
Scaffold a new spawnable specialist agent def and register it in the agent taxonomy
Run pre-merge checklist — branch freshness, docs, version, CHANGELOG, tests
Run a comprehensive PR review, post results, then independently assess each finding
Fix specific issues from a PR review using feature-dev
Add and validate production infrastructure one bundle at a time
Initialize the Apex Spec System in the current project
Plan and execute Unity version or render pipeline migration — identifies deprecated APIs, package compatibility, and executes migration steps.
Set up multiplayer networking — writes network scripts, configures NetworkManager via MCP. Supports Netcode, Mirror, Photon, Fish-Net.
Profile and optimize performance — uses MCP profiler for frame timing, memory, rendering stats. Identifies bottlenecks and applies fixes.
Archive completed milestone and prepare for next version
Configure settings: depth, model profiles, features, git, and gates.
Add a note to the active task - progress, decisions, context. --pre-compact writes a resume-grade session snapshot before /compact.
Technical decision analysis from expert agents launched in parallel, with clear recommendation
Structured planning - explore codebase, design architecture, evaluate options, produce detailed implementation plan
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic