superomni

Trigger the **brainstorm** skill.

Update all project documentation after shipping.

Trigger the **executing-plans** skill.

Trigger the **frontend-design** skill in **animate mode**.

Trigger the **frontend-design** skill in **arrange mode**.

Trigger the **frontend-design** skill in **audit mode**.

Trigger the **frontend-design** skill in **clarify mode**.

Trigger the **frontend-design** skill in **colorize mode**.

Trigger the **frontend-design** skill in **critique mode**.

Trigger the **frontend-design** skill in **distill mode**.

Trigger the **frontend-design** skill in **harden mode**.

Trigger the **frontend-design** skill in **polish mode**.

Trigger the **frontend-design** skill in **typeset mode**.

Run a full **harness engineering audit** on the superomni skill framework — evaluate context efficiency, tool action space, evaluation gate coverage, feedback loops, and documentation freshness.

Run YC-style product discovery before building anything.

Trigger the **code-review** skill.

Activate the full **superomni** skill framework and launch the default guided workflow.

Trigger the **writing-plans** skill.

You are the **superomni Architect** — an AI agent specialized in system design, architectural review, and technical decision-making.

You are the **superomni CEO Advisor** — an AI agent specialized in product strategy, scope decisions, and finding the 10-star product hiding inside a feature request.

You are the **superomni Code Reviewer** — an expert AI agent specialized in providing structured, actionable code reviews.

You are the **superomni Debugger** — a systematic AI agent specialized in root-cause analysis and bug resolution.

You are the **superomni Designer** — an AI agent specialized in UX design, information architecture, and identifying "AI slop" — design patterns that look polished but fail real users.

**Specialty:** Systematic evaluation of agent output quality — catching errors, inconsistencies, and quality regressions before they reach production.

You are the **superomni Planner** — a strategic AI agent specialized in breaking down complex tasks into clear, executable plans.

You are the **superomni Security Auditor** — an AI agent specialized in identifying and remediating security vulnerabilities.

You are the **superomni Test Writer** — an AI agent specialized in writing comprehensive, behavior-verifying tests.

Use when you need to find, install, create, or manage AI agents. Supports installing agents from local paths or GitHub URLs, scaffolding custom agents, and assigning skills to agents. Triggers: "install agent", "create agent", "manage agents", "list agents", "new agent", "add agent".

Use when starting a new feature, project, or design decision. Guides from fuzzy idea to concrete spec through structured dialogue. Triggers: "brainstorm", "design", "spec this out", "let's think through".

Safety guardrails that activate before high-risk operations. Prevents destructive, irreversible, or security-sensitive changes without explicit confirmation. Triggers: destructive operations, production configs, database migrations, security-sensitive files, "be careful", "careful mode".

Use when reviewing code changes, PRs, or preparing code for review. Triggers: "review this", "code review", "ready for PR", "check this code".

Post-ship documentation update. Cross-references the diff, updates README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md to match what shipped. Polishes CHANGELOG voice, cleans up TODOs, optionally bumps VERSION. Triggers: "update docs", "sync documentation", "post-ship docs", "update the readme", "document what shipped". Proactively suggest after a PR is merged or code is shipped.

Use when executing an implementation plan step by step. Triggers: "execute plan", "implement this plan", "start executing", "run the plan". Requires: a docs/superomni/plans/plan-*.md or similar plan document to exist.

Use when a feature branch is complete and ready to merge. Performs final cleanup, verification, and merge preparation. Triggers: "finish branch", "ready to merge", "branch complete", "merge this".

Create distinctive, production-grade frontend interfaces with high design quality. Use when building UI components, pages, or applications. Guides from context gathering through implementation to quality gate. Triggers: "frontend design", "build UI", "design this page", "make it look good"

Use when working on multiple features or branches simultaneously. Git worktrees allow multiple branches to be checked out at the same time. Triggers: "work on multiple features", "parallel branches", "worktree".

Design, audit, and improve the agent harness — the environment, constraints, context management, evaluation gates, and feedback loops that surround and guide AI agents. Inspired by OpenAI and Anthropic harness engineering best practices. Triggers: "harness", "harness audit", "improve harness", "agent environment", "context management", "evaluation gates", "feedback loop", "harness engineering".

Use for open-ended exploration and investigation of unfamiliar codebases, systems, or problems. Complements systematic-debugging (which is for known errors). Use investigate when: "how does X work", "understand this codebase", "map this system". Triggers: "investigate", "explore", "understand how", "map the codebase".

superomni Office Hours — product discovery and validation. Two modes: Startup mode: six forcing questions that expose demand reality, the narrowest wedge, and implementation alternatives. Builder mode: design thinking for side projects and open source. Saves a design doc. Triggers: "brainstorm this idea", "office hours", "validate my idea", "think about this product", "I want to build", "help me think through".

Multi-stage plan review pipeline: Strategy (CEO) → Design (if UI) → Engineering. Applies 6 decision principles. Auto-resolves mechanical decisions, surfaces taste decisions. Triggers: "review this plan", "autoplan", "auto review", "is this plan good", before executing any plan.

Use before deploying any code to production. Verifies observability, reliability, operability, and goal alignment. The gate between "tests pass" and "safe to deploy". Triggers: "production ready", "ready to deploy", "pre-deploy check", before using ship skill.

Use when performing quality assurance on code changes. Identifies test gaps, writes missing tests, explores edge cases, and auto-fixes with caution. Triggers: "QA", "quality check", "test coverage", "run QA", "check quality".

Use when responding to code review feedback on your changes. Guides you through processing comments, making fixes, and re-requesting review. Triggers: "address review", "fix review comments", "respond to feedback", "review feedback".

Engineering retrospective. Analyzes commit history, work patterns, code quality metrics, session detection, streak tracking. Triggers: "/retro", "weekly retro", "what did we ship", "engineering retrospective".

Use when auditing code or systems for security vulnerabilities. Combines OWASP Top 10 checklist with STRIDE threat modeling. Triggers: "security audit", "security review", "threat model", "vulnerability scan".

Post-task performance evaluation. Applies first-principles reflection to evaluate how well the current session's workflow, agents, and skills performed. Produces a structured improvement report saved to docs/superomni/improvements/. Triggers: "self-improve", "evaluate performance", "reflect on execution", "how did we do", "what could be better", "evaluate this sprint", "improve process", "first principles review".

Complete release workflow: verify → build → test → deploy → announce. Use when releasing software to production or any public environment. Triggers: "/ship", "deploy", "release", "ship this", "publish".

Default working mode for all non-trivial tasks. Decompose any task that benefits from specialization, parallelism, or independent verification into sub-agents. Use sub-agents by default unless the task is trivially small (< 5 min, single file). Triggers: any implementation, review, or analysis task; "use subagents", "parallel implementation", "too complex for one pass".

Use when encountering any bug, test failure, or unexpected behavior. Iron Law: no fixes without root cause investigation first. Four phases: Investigate → Analyze → Hypothesize → Implement. Triggers: any error, test failure, "it's broken", "why isn't X working".

Use when writing any new code, fixing bugs, or refactoring. Globally enforced: this skill is MANDATORY whenever code is written. Enforces Red-Green-Refactor cycle and the Delete Untested Code rule. Triggers: any code writing task, "implement", "add feature", "fix bug", any step in executing-plans that touches source code.

Meta-skill: explains the superomni skill framework to the AI agent. Always active. Read this first.

Use before claiming any task is complete. Performs a structured self-check to ensure all acceptance criteria are met. Triggers: "I'm done", "that's complete", "finished", before reporting DONE.

Unified entry point for the superomni framework. Activates all skills, detects current pipeline stage, and launches the guided workflow. Triggers: "/vibe", "activate framework", "start workflow", "what's next".

Documents the end-to-end sprint workflow and inter-skill data flow. Use to understand which skills to use, in what order, and how data flows between them. Triggers: "workflow", "sprint", "pipeline", "what's next", "how do skills connect".

Use when turning a spec or idea into a concrete, executable implementation plan. Triggers: "write a plan", "plan this out", "create implementation plan", "how should we implement".

Meta-skill: use when creating a new skill for the superomni framework. Guides through the process of designing and writing a well-structured skill. Triggers: "create a new skill", "write a skill for", "add a skill that".

1 hook across 1 event