Shared Skills

Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.

Guides the LLM lifecycle from strategy to deployment. Use when planning, comparing, fine-tuning, distilling, compressing, migrating, or operating LLM systems.

Designs retrieval-augmented generation and search systems. Use when choosing retrieval, chunking, hybrid search, grounding, or RAG evaluation patterns.

Configures a language server so editor/agent tooling (diagnostics, go-to-definition, references, rename) works. Use when a project needs an LSP installed or wired, or a 'no LSP server configured' error appears.

Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.

Handles git work: atomic commits, rebase, squash, blame, bisect, reflog, and history questions. Use whenever a task needs a commit or a git-history investigation; skip for ordinary code edits.

Designs trustworthy LLM, agent, responsible-AI, and multimodal evaluations. Use when measuring quality, fairness, privacy, grounding, safety, or judge reliability.

Operates ML, LLM, responsible-AI, and multimodal systems. Use when deploying, monitoring, governing, or responding to production AI failures.

Applies strict, modern language practice (typed errors, exhaustive match, TDD) for Python, Rust, TypeScript, and Go. Use for work on .py, .rs, .ts, or .go files.

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

Executes a written Prometheus work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.

AI agent architecture, graph and loop composition, protocol choice, evaluation, and observability. Use when scoping or reviewing systems before implementation.

Configures and hardens MCP servers for Claude Code and Codex agents. Use when connecting databases, APIs, files, or SaaS via MCP, or building custom servers.

Writes PRDs and specs optimized for coding assistants. Use when authoring requirements or project context for Claude Code, Cursor, Copilot, or Codex.

Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or plotting a dataset.

Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.

Extracts, creates, and transforms PDF documents. Use when parsing text or tables, generating files, merging pages, or handling PDF forms.

Systematic debugging for crashes, regressions, flakes, and production bugs. Use when diagnosing stack traces, logs, traces, or profiling data.

Scans public GitHub repos for agent skills, dev practices, and code patterns. Use when enriching skills, setting team policy, or researching a build domain.

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.

Manages AGENTS.md, CLAUDE.md, and scoped repo rules for Claude Code and Codex. Use when fixing stale memory, ignored instructions, memory audits, or model-upgrade migration.

Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating, updating, or validating shared skills.

Automates Metabase cards, dashboards, Remote Sync, embedding, tenants, and the Agent API/MCP server for AI workflows. Use when scripting, promoting, or embedding Metabase content.

Create/edit .docx files with styles, templates, comments, and extraction workflows. Use when asked to generate Word reports, contracts, proposals, or convert Word content.

Create/edit .pptx presentations with charts, templates, and speaker notes. Use when asked for pitch decks, QBR decks, or slide automation.

Create/edit .xlsx spreadsheets with tables, formulas, charts, validation, and workbook automation. Use when asked to generate Excel reports, models, exports, or audit spreadsheets.

Designs and troubleshoots NUKE-based CI/CD pipelines for .NET services. Use when refactoring target graphs, splitting test flows, publishing reports, or diagnosing slow pipelines.

Designs and tests distributed-system resilience. Use when adding retries, deadlines, hedging, circuit breakers, overload protection, chaos experiments, or SLO reliability gates.

Builds a transformer/GPT and BPE tokenizer from scratch. Use when implementing autograd, self-attention, a nanoGPT-style pretraining loop, or a byte-level tokenizer.

Designs durable API contracts across REST, GraphQL, gRPC, tRPC, and AsyncAPI. Use when specifying interfaces, auth, versioning, errors, rate limits, or agent APIs.

Safe refactoring with behavior preservation. Use when reducing technical debt, planning codemods, applying strangler migrations, or tightening CI guardrails around risky changes.

Guides iOS testing with XCTest, XCUITest, Swift Testing, simctl, and xcresult. Use when choosing destinations, controlling flakes, or parsing test artifacts for native apps.

Mines academic papers, research blogs, and curator newsletters for stealable methods and frameworks. Use when scanning research for applicable techniques across AI/ML/SWE.

Reaches web pages a plain fetch cannot: renders JS, drives clicks and forms, captures screenshots, holds a login, and gets past WAF blocks through platform-native readers and stealth Chrome. Use for any page work beyond retrieving static text.

Guides mobile platform selection and delivery across native and cross-platform stacks. Use when planning auth, push, deep links, releases, or app architecture for iOS/Android.

Designs application search systems. Use when choosing engines, indexing, relevance tuning, facets, autocomplete, or search analytics.

Creates coding agents on Claude Code, Codex, and Agent SDK. Use when defining review, test, refactor, or team agents — not building a runtime.

Builds repeatable deep-research workflows for verified synthesis. Use when producing evidence-backed briefs, comparisons, dossiers, or research pipelines.

LLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when optimizing throughput, tail latency, or serving cost.

Time-series forecasting with temporal validation, panel models, probabilistic forecasts, and TS foundation models. Use when modeling ordered observations.

Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.

Designs team Git workflows for branching, PRs, and releases. Use when choosing branching models, stacked PRs, merge queues, worktree isolation for agents, or collaboration rules.

Builds QA harnesses for LLM agents. Use when evaluating tool, trace, red-team, regression, multi-agent, or carried-workspace trajectory behavior.

Audits and enforces documentation quality. Use when checking coverage, freshness, runbook validity, AI-instruction coverage, or cleaning stale/duplicate markdown after LLM edits.

Implement OpenTelemetry logs/metrics/traces, SLI/SLO gates, burn-rate alerts, and APM integrations. Use when adding or validating observability.

Designs NUnit-based C# test suites for API, component, and integration coverage. Use when creating fixtures, wiring Testcontainers, or reducing flaky CI behavior.

Builds backend services and APIs with durable defaults. Use when implementing REST, GraphQL, tRPC, or gRPC services with auth, queues, data, or observability.

Mobile QA for iOS and Android. Use when planning automation frameworks, device matrix, flake control, or CI/CD release gates.

Builds frontend applications across major web stacks. Use when implementing UI, fixing hydration or SSR issues, or setting up modern frontend architecture.

Designs production payment and billing systems. Use when implementing Stripe, Paddle, Adyen, subscriptions, tax, marketplaces, or mobile purchase flows.

Runs local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.

Builds ML, responsible-AI, and multimodal models. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.

Designs lakehouse platforms across Iceberg, Delta, Hudi, and Paimon. Use when choosing catalogs, CDC paths, query engines, governance, or cost controls.

Founder-PM toolkit for discovery, roadmaps, prioritization, and PMF measurement. Use when planning product strategy, metrics, or roadmaps.

Tests apps as an ICP persona through browser automation and reports friction, fixes, and risks. Use when running persona-based, ICP, or synthetic-user testing.

Designs Android testing with Espresso, UI Automator, and Compose. Use when planning device matrices, screenshot tests, CI flows, or flake-control workflows.

Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.

Designs DevOps and platform engineering systems. Use when planning Kubernetes, Terraform, GitOps, CI/CD, observability, incident response, or cloud-native operations.

Designs AI-first help centers and self-service support systems. Use when shaping taxonomy, article templates, support AI, or docs platform choices.

Risk-based test strategy for software delivery. Use when defining coverage, setting CI gates, managing flaky tests, choosing test layers, or establishing release criteria.