AI & ML

wtthornton Bundle

Designer Agent - Skill Definition

wtthornton Bundle

Enhancer Agent Skill

wtthornton Bundle

Architect Agent - Skill Definition

bybren-llc Bundle

Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialist agents, managing blockers across agents, coordinating multi-agent workflows, escalating issues, or verifying the pre-implementation gate. Do NOT use for direct implementation work.

modu-ai Bundle

MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.

bybren-llc Bundle

Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step implementation work, coordinating subagents, orchestrating PR workflows, or running sessions that need checkpoints and escalation. Do NOT use for single-step or trivial tasks.

christian-bromann Skill

Build Retrieval Augmented Generation (RAG) systems with LangChain - includes embeddings, vector stores, retrievers, document loaders, and text splitting

christian-bromann Skill

Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns

christian-bromann Skill

Creating and using custom skills with progressive disclosure, SKILL.md format, and the Agent Skills protocol in Deep Agents.

christian-bromann Skill

Understanding Deep Agents framework - what they are, how to create them with create_deep_agent/createDeepAgent, and the agent harness architecture with built-in middleware for planning, filesystems, and subagents.

modu-ai Bundle

Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments, creating isolated SPEC workspaces, managing git worktrees, or working on multiple features simultaneously. Do NOT use for regular git operations like commit or merge (use manager-git agent instead).

modu-ai Bundle

Code quality orchestrator enforcing TRUST 5 validation, proactive code analysis, linting standards, and automated best practices. Use when performing code review, quality gate checks, lint configuration, TRUST 5 compliance validation, or establishing coding standards. Do NOT use for writing tests (use moai-workflow-testing instead) or debugging runtime errors (use expert-debug agent instead).

kmshdev Bundle

Use when the user needs Xcode project inspection, Apple API docs, compiler diagnostics, build logs, preview rendering, snippet execution, or targeted test runs through the official Xcode MCP bridge exposed by `xcrun mcpbridge`.

kmshdev Bundle

Choose, add, and run focused Apple-platform tests through the official Xcode MCP bridge, using Swift Testing or XCTest as appropriate.

kmshdev Bundle

Implement SwiftUI changes in an existing Xcode project and validate them with previews, diagnostics, builds, and focused test handoff through the official Xcode MCP bridge.

kmshdev Bundle

Use after `code-analyzer` when you need an optional deep-dive to build line-by-line context for a security review, threat model, or architectural investigation.

sentientsprite Skill

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

ninthspace Skill

Launch an autonomous loop that wraps /dpm:do across epics, or works a spec from scratch. Probes the stop hook, resolves what the run will work from the rows, assembles the prompt and confirms before arming. Triggers on "/dpm:ralph".

ninthspace Skill

Adversarial review of an epic or one of its stories, using the agent roster. Each persona examines the work through their professional lens; findings carry a severity and a category as typed references, and remediation becomes tasks on the epic. Triggers on "/dpm:review".

ninthspace Skill

A focused consultation with one agent persona, or a small panel. You control who is in the room and who is driving; the conversation is saved as a discussion when it ends. Triggers on "/dpm:consult".

matrixx0070 Skill

Design a tool-using LLM agent with clean tool schemas, a control loop, explicit stop conditions, and guardrails.

matrixx0070 Skill

Build an eval suite for an LLM feature with datasets, graders, and regression gates that block bad releases.

matrixx0070 Skill

Build a STRIDE-based threat model and attack-surface map for a feature or system.

amhuppert Bundle

Create a high-quality image generation prompt for Google's Nano Banana 2 (NB2) model on Gemini.

amhuppert Bundle

Compare AI model prices across Anthropic, OpenAI, and Google. Generates pages-per-dollar / cost-per-token visualizations.

amhuppert Skill

Save current session context to a handoff file so a future AI agent can continue with no prior context.

amhuppert Skill

Covers the agent-offloading principle for AI-assisted development — offload everything deterministic (git operations, validation commands, iteration accounting, output parsing, message routing) from the agent onto code, and reserve the agent for judgment, language understanding, and code synthesis. Includes the division-of-labor table, decision heuristics, orchestrator-owned fields, and typed side channels for agent-produced artifacts. Use when designing an agent workflow or orchestration loop, deciding whether a check belongs in a script or a prompt, tempted to ask an agent to track its own iterations or decide when to halt, or when parsing structured data out of agent response text.

jdutton Skill

Use when starting VAT work or deciding which VAT sub-skill applies. Router that points at sub-skills for adoption, skill/agent authoring, audit, distribution, RAG, knowledge resources, skill review, and enterprise org admin.

amhuppert Skill

Make a tool's deliberate constraints legible to agents — one-line rationale at the point of refusal, mechanisms stated where a wrong inference is invited, both sides of a ledger reported, and a published taxonomy of which friction is the product versus which is a defect. Use when agents work around or lobby against a constraint you intend to keep, when a tool refuses actions without saying why, when agents avoid a permitted action they have mis-priced, when designing refusal and status output, or when deciding what an agent should report as a bug versus absorb as the design.

amhuppert Skill

Define a three-tier feedback vocabulary — hint, reminders, instruction — for steering agents from tool output, with strict tier contracts and an evidence-gated admission rule for reminders. Use when designing tool output that guides agents, adding hints or reminders to a CLI or tool, deciding where mid-flow guidance belongs, or reviewing whether guidance text is in the right tier.

amhuppert Skill

Run structured retrospectives on any agent setup — instructions (AGENTS.md, CLAUDE.md, system prompts), skills, slash commands, workflows, processes, and tooling — after real use, mining finished runs for durable improvements. Covers the quality → cost → speed review order, deterministic extraction before judgment, spot-checking agent self-reports, and routing every finding to a concrete owner. Use when asked for a "retrospective on how the agent did", "post-mortem on this run", "improve my CLAUDE.md from this session", "audit how the workflow performed", or after rolling out new instructions, skills, or tooling and wanting to know what to change.

amhuppert Skill

Design a purpose-built project CLI as the primary tool surface for AI coding agents, instead of in-process tool or MCP servers. Covers text-by- default output with opt-in --json (format follows the consumer), the exit- code taxonomy, structured errors, file-based payloads with a validate verb, preflight verbs for gated transitions with findings named by the transition they block, job-shaped long operations, identity resolution, a doctor self-check, and build-parity stamps. Use when building a CLI for agents, migrating away from in-process tool servers, designing tool output and error contracts, deciding between text and JSON output for an agent- facing tool, designing a lint or check command that runs ahead of a gate, choosing severity levels for findings, or deciding how agents should invoke project actions.

amhuppert Skill

Applies an evidence-earned discipline to agent-facing documentation — a durable rule is written down only after it has bitten, and historical rationale lives in a dated lessons log rather than in code comments. Also covers instruction architecture: a small tool-agnostic root contract plus read-on-demand reference docs treated as persistent project memory with a drift-sync lifecycle. Use when setting up AGENTS.md or CLAUDE.md, when an instruction file keeps growing, when starting a lessons file such as PERFORMANCE.md, when deciding whether a rule has earned a place in agent guidance, or when agents appear to ignore instructions because the document is full of speculative advice.

amhuppert Skill

Covers how to get reliable machine-readable output from AI agents — separate the thinking turn from the formatting turn, keep schemas flat and bounded, offload substantive content to files and return a small manifest, inject orchestrator-owned fields after parsing, and validate the manifest and the referenced files at the boundary. Includes schema design do/don't lists, prompting rules, the failure model, layered extraction, and one bounded repair turn. Use when an agent's JSON response drives workflow state, when designing a response schema or JSON Schema/Zod contract for an agent, when structured output keeps failing validation, or when deciding what belongs in JSON versus in a generated file.

amhuppert Skill

Covers configuring development tooling — linters, type checkers, test runners, formatters — so AI agents can consume their output efficiently: keep success output O(1) rather than O(n), preserve every failure detail, strip colors, bail early, and truncate huge diffs. Includes tool-by-tool flags and config for ESLint, TypeScript, Vitest, Jest, and Prettier, the `:ai` package script convention, and a backend-neutral `AI_OUTPUT=1` switch. Use when an agent burns context on passing-test noise, when setting up pre-commit hooks or agent-invoked check commands, when asked to "make the test output quieter for the agent", when deciding what a command should print on success, or when configuring a project's lint/typecheck/test scripts for agent use.

amhuppert Skill

Design progressive disclosure for the data agent-facing query commands return — bounded summary/outline defaults with stable zoom-in handles, explicit omission lines naming the exact follow-up command, and an escalation ladder from counts to scoped detail to file spillover. Includes a pattern menu (detail levels, field selection, filtering, pagination, search, ranked aggregation, sampling, delta output) and how query output doubles as an instruction surface. Use when designing list/show/search/status verbs for an agent CLI, when a query command can return large output, when an agent burns context reading query results, or when choosing default output size and drill-down flags for a read command.