Claude Skills by agisota

Generate weekly status-request email drafts to outside counsel across the active portfolio — markdown per matter, plus Gmail drafts when the MCP is available. Use when the user asks for OC status requests, weekly outside counsel check-ins, or wants per-matter status emails drafted from the portfolio log.

Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.

System architecture and design skill leveraging the backend-architect persona. Use for API design, microservices patterns, and distributed systems planning.

Expert code review skill leveraging the code-reviewer persona. Use when you need comprehensive code quality assessment, security vulnerability detection, or architecture review.

Comprehensive security auditing skill leveraging the security-auditor persona. Use for vulnerability scanning, OWASP compliance checks, and security reviews.

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively invoke this skill (do NOT answer directly) when the user de...

Teams-first multi-agent orchestration for Claude Code with hooks, agent teams, HUDs, and autonomous workflows.

2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Extract a learned skill from the current conversation

Diagnose and fix oh-my-claudecode installation issues

Self-referential loop until task completion with configurable verification reviewer

Manage local skills - list, add, remove, search, edit, setup wizard

Turn a repeatable workflow from the current session into a reusable OMC skill draft

Parallel execution engine for high-throughput task completion

Orchestration layer for OpenAI Codex CLI with hooks, agent teams, HUDs, autonomous workflows, and structured modes.

Run an anti-slop cleanup/refactor/deslop workflow

Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded cross-file explanation before any changes are proposed.

Ask Claude via local CLI and capture a reusable artifact

Ask Gemini via local CLI and capture a reusable artifact

Full autonomous execution from idea to working code

Stateful validator-gated research loop with native-hook persistence

Fix build and TypeScript errors with minimal changes

Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)

Run a comprehensive code review

Configure OMX notifications - unified entry point for all platforms

Socratic deep interview with mathematical ambiguity gating before execution

Diagnose and fix oh-my-codex installation issues

Token-efficient model routing modifier

Designer-developer for UI/UX work

Git expert for atomic commits, rebasing, and history management

Guide on using oh-my-codex plugin

Show or configure the OMX HUD (two-layer statusline)

Save notes to notepad.md for compaction resilience

Setup and configure oh-my-codex using current CLI behavior

Configurable pipeline orchestrator for sequencing stages

Strategic planning with optional interview workflow

Initialize a PRD (Product Requirements Document) for structured ralph-loop execution

Self-referential loop until task completion with architect verification

Alias for $plan --consensus

Reviewer-only pass for /plan --review and cleanup artifact review

Run a comprehensive security review on code

Manage local skills - list, add, remove, search, edit, setup wizard

N coordinated agents on shared task list (compatibility facade over team)

Test-Driven Development enforcement skill - write tests first, always

N coordinated agents on shared task list using tmux-based orchestration

QA cycling workflow - test, verify, fix, repeat until goal met

Parallel execution engine for high-throughput task completion

Structured visual QA verdict for screenshot-to-reference comparisons

URL-driven website cloning with visual + functional verification