Resonance

Resonance

Operator-grade AI agent skills for builders. A cross-tool skill library and slash-command system for Claude Code, Cursor, Codex, and opencode, covering strategy, design, engineering, marketing, sales, and ops.

---

What it is

Resonance is an AI agent skill library you drop into any project. It turns a general coding agent into a roster of specialists that follow the same expert protocol every time, on whatever tool you use.

• 50+ domain-tested skills across strategy, engineering, design, marketing, sales, ops, and research. Each skill is a structured procedure with prerequisites, a step-by-step algorithm, a Recovery path, and a Definition of Done, backed by a deep reference library. Not a prompt. A protocol.
• 32 slash commands like /plan, /grill, /build, /debug, /design, /test, /improve, and /ship. Type the command, or describe the job and let the specialist auto-fire.
• Cross-tool by design. One source compiles to the native format of every major agent tool. The SKILL.md / AGENTS.md open standard is the shared content; the Forge emits the per-tool command shims so /ship works after a clone in Claude Code, Cursor, Codex, and opencode.
• A project memory (.resonance/) the agent reads before every task and writes to after. It does not forget your architecture, your decisions, or your voice.
• Token-efficient. The shared operating standard is stated once in AGENTS.md, not repeated in every skill. Compiled skills are lean, so per-session context stays cheap.

You get consistent, high-quality output because the agent runs the same protocol every time, not because you remembered to ask nicely.

---

Works in your tool

Tool	How commands are delivered	Status
Claude Code	Native skills in .claude/skills/<cmd>	/plan, /ship, ...
Cursor	Skills in .cursor/skills/<cmd>	/plan, /ship, ...
Codex	Custom prompts in .codex/prompts/<cmd> plus AGENTS.md routing	/plan, /ship, ...
opencode	Commands in .opencode/command/<cmd> plus AGENTS.md routing	/plan, /ship, ...
Antigravity and other AGENTS.md tools	AGENTS.md command map	describe the job

The command shims are generated from one source (.forge/commands.json) by the Forge. Adding a new tool is one host-config line.

---

Quickstart (60 seconds)

git clone https://github.com/manusco/resonance
cd resonance

Open the folder in Claude Code, Cursor, Codex, or opencode. The slash commands are already committed, so they work immediately. In your AI chat:

/init          # scaffold this project's memory (.resonance/)
/plan          # turn an idea into an atomic, approved plan
/grill         # stress-test that plan before any code
/build         # execute it with a TDD loop
/ship          # release with pre-flight checks

That is the whole setup. No install step, no plugin required.

---

The command catalog

Every command is a structured procedure with a Definition of Done, not a loose prompt. Full map in AGENTS.md.

The autonomous loop /goal "<outcome>" frames the goal, decomposes it, then builds and verifies each slice against real checks (tests, validators, audit), bounded and never auto-shipping. The conductor for the skills below.

Inception /init bootstrap project memory · /venture-model business and revenue math · /plan atomic implementation plan · /grill stress-test a plan before code · /gtm-thinker go-to-market blueprint · /market-research B2B vertical intelligence · /update-roadmap sync state with git

Execution /build TDD build loop · /debug root-cause analysis · /refactor behavior-preserving cleanup · /design elite UI craft and audit · /studio production visual assets · /friction conversion friction removal

Verification /test 8-Path test matrix · /audit security + review + QA + architect swarm · /review-pr PR gatekeeper · /second-opinion independent second-model review · /system-health health score 0-100