audit
01Command
description: Run the audit swarm (security, review, QA, architect) and output P0-P3 classified findings.
Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
Command
description: Run the audit swarm (security, review, QA, architect) and output P0-P3 classified findings.
Command
description: Create or revise a durable architecture constitution, or check a plan, change, PR, or release for architectural drift.
Command
description: Turn a rough request into an intent-faithful execution brief, then run or route it within the user's authority.
Command
description: Execute the implementation plan with a TDD loop (test, code, verify).
Command
description: Analyze a call transcript for persona insights, objection patterns, and feature requests.
Command
description: Document a solved problem in the correct Diataxis quadrant so it is never re-discovered.
Command
description: Generate a B2B cold-call script using the 6-part permission-based framework.
Command
description: Challenge an analysis or high-risk decision through relevant specialist reviews, debate, scenarios, and reconciliation.
Command
description: Root-cause a bug via the Scientific Method. Reproduction script required, no fix without a proven cause.
Command
description: Design or audit UI with elite craft: hierarchy, perceptual color, motion, and the subconscious detail layer.
Command
description: Teach the operator, not the repo: a dense explainer of a concept, diff, or recent work, with an optional predict-then-reveal check-in.
Command
description: Friction Collider: simulate the anti-persona to find and remove conversion drag.
Command
description: The autonomous goal loop: frame, decompose, then build and verify each slice against real checks, bounded, never auto-ship.
Command
description: Stress-test a plan or design before any code: relentless one-question-at-a-time interrogation to shared understanding.
Command
description: Stress-test and expand a go-to-market campaign concept into a strategic blueprint with kill criteria.
Command
description: Write an end-of-session handover doc: what was done, decisions, open TODOs, backlog.
Command
description: Work the eval scorecard: sharpen the weakest skills or their rubrics and keep only changes that raise the measured lift.
Command
description: Drive a live production incident: triage, severity, mitigate, comms, blameless postmortem.
Command
description: Bootstrap the .resonance/ project memory (soul, state, docs scaffold). Run once per new project.
Command
description: Discover Existential Data Points in a B2B SaaS vertical. Positioning from nice-to-have to must-have.
Command
description: First-principles experience audit of a page or whole site: job, value promise, clarity, CTA, craft, function, trust, plus a forward backlog.
Command
description: Turn a feature or idea into an atomic, approved implementation plan. Deep research, 4-pass spec.
Command
description: Atomic, behavior-preserving cleanup. Mikado method, safe sequence, SOLID.
Command
description: Git-driven retrospective: shipping streak, focus score, complexity delta.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: