Claude Skills by richfrem

Antigravity (`agy`) CLI sub-agent system for all Google Gemini models and cross-model access (Gemini, Claude, GPT-OSS) via the agy binary. Use when dispatching tasks to Gemini 3.1 Pro (cheapest real-world), Gemini 3.5 Flash, or other agy-hosted models. Replaces the deprecated gemini-cli-agent (gemini binary retired June 18 2026). Trigger with "use agy", "dispatch to antigravity", "run with agy", "use gemini model", "agy sub-agent", or "use cheapest gemini".

Interactive skill to scaffold and optimize the .agents/ directory for any project mapping up Antigravity configuration. Sets up .gemini/GEMINI.md, skills/, prompts/, and config.json using best practices. Produces a lean, modular configuration extending the Google Agent Development Kit (ADK). Trigger with "set up antigravity", "scaffold .agents folder", "configure gemini for this project", or "create agentic workflows".

Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.

Interactive skill to scaffold and optimize the .claude/ directory for any project. Sets up CLAUDE.md, .claude/rules/, .claude/settings.json with best practices, and optional hooks. Produces a lean, modular configuration that avoids monolithic context bloat. Trigger with "set up claude", "optimize my CLAUDE.md", "scaffold .claude folder", "configure claude for this project", or "create claude settings".

Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target.

Copilot CLI sub-agent system for dispatching tasks and persona-based analysis to GitHub Copilot models. Use for task delegation (agent reads/writes files directly), security audits, architecture reviews, or any work requiring a fresh model context.

Gemini CLI sub-agent system for cost-efficient analysis using the `gemini` binary. Use when piping large contexts to cheaper Google Gemini models (gemini-3-flash-preview, gemini-3.1-pro-preview) for security audits, architecture reviews, or QA analysis. For frontier models (Gemini 3.5 Flash and above), use agy-cli-agent instead.

Local Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical response. Use for fast, private, cost-free subtask delegation from any cloud primary agent. Part of the run_agent.py multi-LLM task router — cli=llama target.

Cross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile), model download, routing proxy daemon install (launchd/systemd/NSSM), and Mode A/B validation. Covers Day 1 bootstrap and Day 2+ reconfiguration.

Provides validation, setup guidance, and a local test harness simulator to run skills within the Microsoft Agent Framework (MAF).

Interactive skill to scaffold and optimize configuration files for both Claude Code (.claude/) and Google ADK/Gemini (.agents/) directories. Trigger with "set up project", "scaffold agent config", "setup cli agent settings", or "configure agents for this project".

Updates model catalogs and cheapest-model references for all CLI backends (copilot, agy, claude, codex, llama). Researches current model IDs and pricing from official sources, updates the per-CLI JSON files, refreshes cheapest_models.json/md if the cheapest pick changed, then propagates all copies via sync_cheapest_models.py. Trigger with "update cli models", "refresh model prices", "model costs are stale", "sync model catalog", or "update copilot/agy/claude model list".

Python dependency and environment management for multi-service or monorepo python backends. Use when: (1) adding, upgrading, or removing a Python package, (2) responding to Dependabot or security vulnerability alerts (GHSA/CVE), (3) creating a new service that needs its own requirements files, (4) debugging pip install failures or Docker build issues related to dependencies, (5) reviewing or auditing the dependency tree, (6) running pip-compile. Enforces the pip-compile locked-file workflow a...

ADR management skill. Auto-invoked for generating architecture decisions, documenting design rationale, and maintaining the decision record log. Uses native read/write tools to scaffold and update ADR markdown files.

Coding conventions enforcement agent. Auto-invoked when writing new code, reviewing code quality, adding headers, or checking documentation compliance across Python, TypeScript/JavaScript, and C#/.NET.

Interactively creates targeted code, design, and documentation bundles for external review (Markdown or ZIP). Includes a comprehensive library of review & delegation persona templates (Adversarial Security, Plan Critique, Refactoring Quality, Sub-Agent Task Handoff, Documentation Synthesis, Architecture, Compliance, TDD Contract Review), plus a Multi-Persona Fan-Out mode for parallel adversarial plan review (see graph-planning-superpowers-policy.md Phase 1).

Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization). V2 includes L5 Delegated Constraint Verification via verify_png for strict binary linting and Puppeteer-based rendering.

Agent skill for safe, dry-run-first, deduplicated, root-cause-consolidated, evidence-validated, and secret-redacted logging of repository execution friction into GitHub Issues. USE ONLY for durable repository bugs, execution friction (T1-T3), map debt, and architectural improvements. DO NOT USE for temporary intra-session checklists (use task-agent instead).

Bridge skill for escalating ephemeral local task scratchpad items (`tasks/*.md`) into durable, taxonomy-validated, evidence-rich GitHub Issues. USE ONLY when promoting a single-session local task into durable repository backlog. DO NOT USE for managing local kanban boards (use `task-agent` instead) or directly querying/commenting on issues (use `github-issue-agent` instead).

Automatically ranks GitHub issues (P0-P3) based on friction tier, frequency, and blockages, synchronizing priority labels and GitHub Projects v2 custom fields.

Download primitives for HuggingFace assets - files, folder snapshots, and model weights with exponential backoff on rate limits. Use when pulling models, datasets, or caches from HuggingFace to the local environment.

Initialize HuggingFace integration - validates .env variables, tests API connectivity, and ensures the dataset repository structure exists. Use when onboarding a new project to HuggingFace or when credentials change.

Upload primitives for HuggingFace Soul persistence - file, folder, snapshot, JSONL append, and dataset card management with exponential backoff. Use when persisting agent learnings, snapshots, or semantic caches to HuggingFace.

This skill should be used when the user wants to "humanize this", "make this sound less AI", "rewrite this naturally", "remove AI patterns", "make this more conversational", "this sounds robotic", "edit for voice or tone", or pastes text that reads like LLM output (parallel structure in threes, em dashes, semicolons, hedging phrases, hollow affirmations). Also trigger for "make this sound like me", "clean up this draft", or "rewrite this for LinkedIn/email/Slack". Use this skill even for a si...

Skill for orchestrating the end-to-end GitHub issue lifecycle flow: Issue -> Worktree -> Implementation -> PR Creation -> Resolution Closure. USE ONLY when running or dry-running full lifecycle orchestration for resolving an issue with a PR. DO NOT USE for isolated worktree management only (use `issue-worktree-agent`) or logging issues (use `github-issue-agent`).

Skill for creating and managing isolated git worktrees (`.worktrees/issue-NNN`) for issue execution branches. USE ONLY when setting up or cleaning up isolated git worktrees for specific issue execution. DO NOT USE for managing local task files (use `task-agent`) or escalating tasks to issues (use `github-issue-backlog-agent`).

Specialized Quality Assurance Operator for documentation link integrity and scans. Automatically handles automated link validation, auditing, fixing, and repairing broken documentation links and docs paths across repositories, with guidance on when to commit changes.

Reduces AI agent context bloat across three dimensions: (1) duplicate skill deduplication — clears stale agent directory copies since the IDE already reads from plugins/ directly; (2) instruction file optimization — rewrites CLAUDE.md, GEMINI.md, or .github/copilot-instructions.md to under ~80 lines, keeping only rules that directly change agent behaviour; (3) session token efficiency — guidance on cheap subagent delegation, context compounding across turns, and session hygiene. Trigger with ...

Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on Windows. Also trigger when the user reports that files are missing or wrong after switching between Mac and Windows machines using Git. This skill solves the common problem where sy...

Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories. USE ONLY for lightweight, ephemeral, intra-session scratchpads during a single mission run. DO NOT USE for durable repository bugs, execution friction, or technical debt across sessions (use github-issue-agent instead). V2 enforces Kanban Sovereignty constraints preventing manual task file edits.

Captures and refines business requirements, including functional requirements, non-functional requirements, business rules, constraints, assumptions, and success measures. Produces structured BRD-style documents with [CONFIRMED] and [UNCONFIRMED] confidence markers. Trigger with "capture requirements", "generate a BRD", "document business rules", "list the constraints", or "create a requirements document".

Generate Mermaid flowcharts documenting business processes, state machines, and workflow logic from session captures. Use when you need to map multi-step processes, approval flows, user journeys, or decision trees during exploration. Trigger with "map this workflow", "create a process diagram", "flowchart the business process", "document this workflow", or "visualize the state machine".

Guides a Subject Matter Expert through a structured discovery session to create and approve a Discovery Plan before any building begins. This is the HARD-GATE brainstorming skill — no prototype can be built until the SME explicitly approves the plan. Trigger phrases: "start a discovery session", "let's plan this out", "help me figure out what we're building", "I have an idea I want to explore", "let's start from scratch"

Interactive co-authoring skill for the narrow end of the exploration funnel. Synthesizes session briefs, BRDs, story sets, and prototype notes into a structured handoff package targeted at the correct downstream consumer (e.g., formal software specs, strategic roadmaps, or process documentation).

Evaluates and improves the exploration-cycle skills, prompts, routing, and artifact quality using baseline-first, one-hypothesis iteration loops with keep-discard decisions and experiment ledgers.

Interactive co-authoring skill for the wide end of the exploration funnel. Captures and refines the core intent, whether the outcome is a software app, a business process improvement, research analysis, or strategic roadmap. Guides users through gathering context, iteratively drafting the brief, and testing for blind spots.

SME-facing orchestrator for the Business Exploration Loop. Supports 4 session types (greenfield, brownfield, discovery-only, spike) with adaptive phase selection. Manages state via exploration-dashboard.md, enforces phase gates, and routes to child skills in sequence. Phases can be skipped based on session type. Single canonical entry point — invoke at the start of any exploration session or to resume an in-progress session. Trigger phrases: "start an exploration", "let's explore this idea", ...

Orchestrates the full prototype build cycle for a Subject Matter Expert. Coordinates layout confirmation and component building — it does not build components directly. Acts as the single entry point for all prototype-related requests. Trigger phrases: "build a prototype", "create a working prototype", "show me a working version", "prototype to clarify scope", "build an exploratory prototype"

Builds a prototype component by component, self-reviewing each component against the Discovery Plan before moving to the next. Invoked by prototype-builder after the layout direction is confirmed. Trigger phrases: "build the prototype", "let's build it", "start building". Also invoked by prototype-builder-agent after visual-companion confirms layout.

Derives, groups, and refines user stories from exploration work, prototype behavior, and business context, with prioritization for the first implementation slice. Supports standard "As a / I want / So that" format and Gherkin "Given / When / Then" Acceptance Criteria format. Trigger with "generate user stories", "write acceptance criteria", "create Gherkin scenarios", "derive stories from requirements", or "create a backlog".

Use when starting any conversation - establishes how to find and follow the business exploration workflow.

Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.

A visual & functional crawler operation utilizing Chrome DevTools Protocol (CDP) or Playwright/Puppeteer to audit prototype UI/UX and behavior.

Extracts pure, framework-free, IO-free domain models and deterministic business rules from a rapid prototype with strict preservation vs replacement classification and purity audit enforcement.

Top-level orchestration skill coordinating the entire 7-step surgical vibe-to-enterprise reengineering pipeline with automated safety and economic optimization controls.

Progressively migrates legacy prototype routes and features to a clean architecture layer slice-by-slice, verifying them against characterization tests, running purity/drift checks, and executing completion certifications.

A package builder skill that compiles specs/ documents into standard spec-kits and scaffolds the clean target codebase sandbox.

End-to-end pipeline that transforms an undocumented vibe-coded prototype into a Spec Kit-compatible specification package and a Superpowers-ready implementation handoff, including characterization tests, domain extraction, architecture decisions, task breakdown, TDD strategy, worktree guidance, and certification reports.

A system architecture scaffolder designed to synthesize visual discoveries and interactive Q&A responses into comprehensive C4 and TOGAF specs.

Presents layout options to the SME in plain language before any prototype construction begins. Invoked after the Discovery Plan is approved to confirm visual structure and direction. Trigger phrases: "what should it look like", "show me some layout options", "let me see the design options before we build". Also invoked by prototype-builder after plan approval.