Track agent, skill, and model performance metrics for optimization. Use when measuring agent success rates, tracking model latency, analyzing routing effectiveness, or optimizing cost-per-task. Trigger keywords - "performance", "metrics", "tracking", "success rate", "agent performance", "model latency", "cost tracking", "optimization", "routing metrics".

Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided tour of Pinecone's tools.

Set up aggressive recurring project execution loops (“Crank Engines”) using cron + agent turns, with a strict finish contract. Use when the user asks to keep cranking on a project/sprint (e.g. “set up an aggressive crank engine”, “keep pushing until sprint is done”, “run status every X minutes”), and needs configurable project, recipients, focus scope, quantifiable completion criteria, screenshot evidence, and manager-go/no-go enforcement.

ERC-8004 on-chain agent reputation management — submit and revoke feedback, append responses, approve clients, and query reputation summaries, feedback entries, and client lists.

Designs retrieval strategies for querying knowledge graphs in RAG systems, covering pattern selection (global-first, local-first, U-shaped hybrid), query decomposition for multi-hop reasoning, ranking and constraint configuration, and provenance tracking for citation. Use when designing retrieval pipelines, orchestrating search over knowledge graphs, or when user mentions retrieval strategy, search orchestration, query decomposition, multi-hop reasoning, provenance tracking, or citation in GraphRAG.

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)

Creates, refines, and validates Agent Skills following the open standard at agentskills.io, Claude Code extensions, and Anthropic best practices. Use when building, creating, generating, or designing new skills.

Use when an agent needs a deep external survey, literature review, multi-source comparison, or GPT Pro Deep Research prompt queued for Arthur/Oracle instead of spending live agent tokens.

Hand off the current task to the SLICC browser agent, or install a new skill into SLICC from a GitHub repo. Use this skill when the user says things like "handoff to slicc", "move this to slicc", "move to the browser", "test in the browser", "handoff to browser", "install this skill in slicc", "upskill slicc with this repo", "add this skill to slicc", or otherwise asks you to continue the work inside the SLICC browser agent.

Write and save structured specifications that pass the Stranger Test — precise enough for someone with zero context to evaluate agent output. Produces spec files in $HOME/.ai-first-kit/ at task, workflow, or governance layers, aligned with the organizational genome. Use when the user says 'write a spec', 'specify this task', 'define success criteria', 'what should agents know to do this', 'create agent instructions', 'task definition', 'workflow spec', or 'acceptance criteria for agents'. Also use when the user wants to document a repeatable process, create reusable agent prompts, turn a one-off task into a template, or define any work for autonomous agent execution — even if they don't use the word 'specification'. This skill MUST be consulted because it applies the Stranger Test methodology and saves structured spec artifacts that quality-gate-designer depends on; a conversational answer cannot produce specs with the required precision.

Use when managing an ACTIVE agent team — coordinating tasks between teammates, handling team messaging, plan approval, delegate mode, display modes, or graceful shutdown. Triggers: "task management", "team communication", "delegate mode", "plan approval", "shutdown teammates", "team messaging", "how do I manage my team", "feedback gate", "dedup guard". Do NOT trigger for choosing a team blueprint or describing what agent teams are at a high level — those route to `team-blueprints` and `agent-teams` respectively. This skill is for running a team that's already spawned.

Receive and respond to inbound messages and track outbound delivery status via Twilio webhooks — across SMS, MMS, WhatsApp, and RCS. Covers webhook request parameters, replying with TwiML, validating webhook signatures for security, and handling status callbacks. Use this skill whenever an agent needs to handle incoming messages on any channel or track outbound message delivery in real time.

Run adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skills:pm-critic); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads agents/pm-critic.md and executes the system prompt inline. Returns findings graded P0/P1/P2/P3 with concrete fix suggestions per finding, plus a layered Status Summary section and machine-readable Status YAML block per master plan D26.

Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skills:pm-skill-auditor); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads agents/pm-skill-auditor.md and executes the system prompt inline. Returns a layered audit report (full findings + Status Summary prose + Status YAML envelope per master plan D26) with cross-cutting findings graded P0/P1/P2/P3 plus aggregate counter audit and validator results table.

Create or update CLAUDE.md and AGENTS.md files following official best practices. Use when asked to create, audit, or improve agent config files (CLAUDE.md, AGENTS.md). Don't use for README/contributor docs or non-Claude IDE plugins.

Import an agent migration bundle into Starchild from the relay service. Use when moving an agent from another platform into Starchild (e.g. import my OpenClaw export, load this 8-char migration code).

Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

Use when working with AliCloud Milvus (serverless) with PyMilvus to create collections, insert vectors, and run filtered similarity search. Optimized for Claude Code/Codex vector retrieval flows.

Agent-powered limit orders on Bitflow — set price targets, auto-execute swaps when conditions are met.

Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.

Creates or modifies agent skills, including single-workflow and multi-workflow (orchestrator) skills. Use when the user wants to create, write, author, scaffold, edit, update, fix, or refactor a skill, or migrate a skill from single to multi-workflow.

Use this skill when the user needs to set up a DataHub connection, install the DataHub CLI, configure authentication, verify connectivity, set default scopes, or create agent configuration profiles. Triggers on: "set up DataHub", "connect to DataHub", "install datahub CLI", "configure DataHub", "set default platform", "focus on domain X", "create profile", or any request to establish, configure, or troubleshoot DataHub connectivity.

Manage agent skill dependencies with dotagents. Use when asked to "add a skill", "install skills", "remove a skill", "dotagents init", "agents.toml", "agents.lock", "sync skills", "list skills", "set up dotagents", "configure trust", "add MCP server", "add hook", "wildcard skills", "user scope", "dotagents doctor", or any dotagents-related task.

Generates a minimum version enforcement system with hard-block and soft-prompt update flows, App Store redirect, and remote config or App Store lookup for version checks. Use when user wants force update, mandatory update, or minimum version check.

Expert knowledge of GitHub Copilot CLI - installation, configuration, usage, custom agents, MCP servers, and version management. Use when asking about copilot cli, copilot commands, installing copilot, updating copilot, copilot features.

Create a new Herdr workspace/pane for a repo and kick off a Pi session with a structured handoff prompt. Use when the user asks to start a new Herdr workspace, space, pane, or Pi session for delegated work.

Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or custom permissions, (4) set up pre/post tool execution actions, (5) configure session initialization or cleanup (SessionStart/SessionEnd), (6) auto- approve or deny permission requests (PermissionRequest), or (7) asks about any of the 10 hook events.

Index a repository's ADRs, OpenSpec specs, and source code into qmd collections for hybrid (BM25 + vector + reranker) semantic search. Use when the user says "index this repo", "load into qmd", "make my code/specs searchable", "set up qmd for this project", or wants agents to be able to search architecture artifacts and code semantically.

Use this skill for ANY question about CREATING evaluators. Covers creating custom metrics, LLM as Judge evaluators, code-based evaluators, and uploading evaluation logic to LangSmith. Does NOT cover RUNNING evaluations.

Traces a specific business logic flow across multiple repositories from user-provided starting points. Explores only prompt-relevant code, discovers repos the user missed, traces the algorithm end-to-end, and produces tech-agnostic BMAD specs with reference IDs (BR/DC/EC/ERR/FLOW).

Build a positioning map for 3–5 competitors and identify the empty quadrant the founder could own. Use when a founder asks "where's the positioning gap?", "how do I position against X?", "what's the competitive landscape look like on hero / pricing / hiring / customers?", or needs a structured comparison before a launch, repositioning, or fundraise. Combines Anysite MCP (LinkedIn company entity + post search + jobs search; SEC for late-stage) with Exa MCP (fetch JS-heavy SaaS marketing pages, find case studies and changelogs). Returns a comparison table across 5 axes (hero / pricing / specialities / recent shipping / hiring), 3 candidate positioning moves with explicit choice criteria, and a one-sentence positioning statement. Requires customer pain themes as input — positioning without pain context is just rearranging marketing copy. Run competitor-discovery and customer-pain-mining first if you don't have a curated competitor list + pain themes.

Optimize prompts for LLMs and AI systems with structured techniques, evaluation patterns, and synthetic test data generation. Use when building AI features, improving agent performance, or crafting system prompts.

Three-layer PII anonymization for session transcripts (therapy, coaching, consulting, mentoring). Runs Natasha (Russian NER), OpenAI Privacy Filter, and local LLM (Ollama) in sequence for maximum coverage. Fully local by default. This skill should be used when anonymizing session transcripts, notes, or any text containing client PII before AI analysis. Triggers on "anonymize", "redact PII", "anonymize session", "protect client data", "strip personal data", "anonymize transcript".

Converts interactive Claude Code or GitHub Copilot session goals and processes into a reusable goal-seeking agent with memory. Extracts goals, constraints, and approaches from session transcripts and generates agent prompts via the amplihack goal_agent_generator CLI.

Create new Agent Skills from templates with best-practice structure, pre-populated SKILL.md, and optional scripts/assets directories.

Optimize Claude Code skills for token efficiency using progressive disclosure and content loading order. Use when optimizing skills, reducing token usage, restructuring skill content, improving skill performance, analyzing skill size, applying 500-line rule, implementing progressive disclosure, organizing reference files, optimizing YAML frontmatter, reducing context consumption, improving skill architecture, analyzing token costs, splitting large skills, or working with skill content loading. Covers Level 1 (metadata), Level 2 (instructions), Level 3 (resources) loading optimization.

Structured spec-to-ticket export pipeline — maps document sections to project management tickets (Linear, GitHub Issues) via MCP, preserving hierarchy and acceptance criteria. Use this skill when the user says "export spec", "push to linear", "create tickets from spec", "spec to issues", or "export to jira".

Output templates and scoring rubrics for multi-agent team workflows. Use when generating final deliverables from agent team debates, formatting validation verdicts, or scoring PRD reviews. Trigger on: 'format the team output', 'validation verdict template', 'PRD review report format', 'competitive synthesis template', 'scoring rubric'.

Turso SQLite database. Covers encryption, sync, agent patterns. Use when working with Turso/libSQL embedded databases, configuring encryption-at-rest, setting up sync replication, or building agent-friendly database patterns. Keywords: Turso, libSQL, embedded, SQLite, encryption, sync.

Auto-loaded at session start via SessionStart hook. Teaches skill invocation protocol, tool selection rules (look-at for media, skills for workflows), agent delegation patterns, and enforcement mechanisms. NOT user-triggered - provides foundational skill usage discipline for all sessions.

Draft CHANGELOG entries from git log via the pm-changelog-curator sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-skills:pm-changelog-curator); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads agents/pm-changelog-curator.md and executes the system prompt inline. Applies CLAUDE.md hygiene rules (no internal-notes references, no em-dashes, no Claude attribution trailers, public paths only). Returns a layered draft (full CHANGELOG draft + Status Summary prose + Status YAML envelope per master plan D26) with hidden justification comments for maintainer audit. Refuses on dirty working tree unless --committed-only is passed.

Implement QRSPI-planned OpenSpec changes with intelligent parallelization. Use when the user wants to apply a QRSPI change, implement tasks with parallelization, or says "apply this QRSPI change", "implement with parallelization", "run the parallel slices". This skill is specifically designed for changes created via accelint-qrspi that include "Parallelization Strategy" sections in tasks.md. It orchestrates parallel sub-agent execution for independent task slices using OpenSpec CLI workflows. Make sure to use this skill when the user mentions applying QRSPI changes, running parallel implementation, or working on changes with vertical slices.

Use when the user asks to create a persistent repo-local Codex agent, scaffold `.codex/agents/*.toml`, define a reusable specialist role, or match an agent to existing local skills and MCP servers.

Architecture patterns and best practices for giving AI agents email capabilities. Use when designing how agents send, receive, and manage email conversations, building two-way communication loops, implementing human-in-the-loop approval with drafts, choosing between WebSockets and webhooks, setting up multi-agent email topologies, handling OTP and verification flows, or securing agent email against prompt injection.

Agentic Platform Contract tables for AI agent applications - runs, events, artifacts, and tool calls tracking. Use when building AI agent backends that need structured run/event storage.

Audits and writes AGENTS.md files using execution-first standards. Checks commands, gotchas, and signal-to-noise ratio. Use when asked to audit, review, score, refactor, or improve agent instruction files, fix stale commands, reduce bloat, or asking "my AGENTS.md is bad", "help me write a CLAUDE.md", or "improve my agent instructions".

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls. Use when building, deploying, or hardening agentic AI systems that invoke tools, access data, or interact with production infrastructure.

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

Converts markdown plans into beads (tasks with dependencies) and polishes them until implementation-ready. The bridge between planning and agent swarm execution. Use when converting a plan to beads, polishing bead descriptions, adding test coverage beads, reviewing bead dependencies, or preparing tasks for agent swarm execution.

Generate AEO-optimized content (Answer Engine Optimization) for AI search visibility - ChatGPT, Claude, Gemini, AI Overviews. Use when optimizing websites for AI citations, creating FAQ schemas, evidence panels, or analyzing content for LLM extraction readiness.

Extended documentation skill for Claude Code installations. Complements built-in /team-onboarding with multi-mode research — internal setup analysis, external architecture docs, and web research from forums/GitHub/marketplaces.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Monitors competitor websites, pricing, content changes, hiring patterns, and product updates. Generates intelligence reports with strategic implications and trend analysis. Stores history for longitudinal tracking.

Create and edit checkpointflow workflow YAML files. Use this skill whenever the user wants to create a workflow, automate a process as a YAML pipeline, define steps that mix CLI commands with human or agent checkpoints, turn a conversation into a reusable runbook, or asks about writing cpf/checkpointflow workflows. Also use it when you see keywords like "workflow", "runbook", "approval flow", "pause and resume", or "await event" in the context of automation.

Patterns for Databricks Vector Search: create endpoints and indexes, query with filters, manage embeddings. Use when building RAG applications, semantic search, or similarity matching. Covers both storage-optimized and standard endpoints.

This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up unused code", "remove redundant code", "prune this codebase", "dead code sweep", "code cleanup", or when a codebase has gone through multiple agent-driven refactors and likely contains overlooked remnants. Systematically identifies cruft, categorizes findings, and removes confirmed dead code with user approval.

Conduct multi-agent deep research on a topic with parallel web searches and synthesis

Interactive planning at any scope — whole thesis, chapter, section, or subsection. Invoke with a prompt specifying the working level. Collaboratively builds writing plans from cold start through to statement-level outlines with verified Zotero citations.

Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a final Summarizer subagent with task tracking and failure recovery

DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers

End-to-end dataset curation for FiftyOne: inspect schema and quality, audit annotations, analyze class distributions, explore embeddings, find duplicates, create curated subsets, and build train/val/test splits. Works with any computer vision dataset type.

LangGraph framework for building stateful, multi-agent AI applications with cyclical workflows, human-in-the-loop patterns, and persistent checkpointing.

Use when implementing semantic / vector search in Laravel 13 with PostgreSQL + pgvector. Covers schema setup, embedding workflow, and the new query builder methods (`whereVectorSimilarTo`, `selectVectorDistance`, etc.).

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Development standards for the Nathan n8n-Jira agent automation system. Covers n8n workflows, Python patterns, and project conventions.

Provides migration guides, release notes, and error solutions for updating @lenne.tech/nest-server to a newer version. Covers version-specific breaking changes, stepwise upgrade strategies, and starter project comparisons. Activates for nest-server version updates, upgrades, migrations, breaking changes between versions, "pnpm run update", TypeScript errors after upgrading, or stepwise migration planning. Delegates execution to the lt-dev:nest-server-updater agent. NOT for writing NestJS code or building features (use generating-nest-servers). NOT for general npm package updates (use maintaining-npm-packages).

Debug failing Playwright E2E tests by analyzing error messages, stack traces, screenshots, and Playwright traces. Provides actionable solutions for common test failures including timeouts, selector issues, race conditions, and unexpected behaviors. Optionally uses Playwright MCP for live debugging.

Write enterprise-ready, agent-executable Product Requirements Documents (PRDs). Use this skill whenever the user wants to "write a PRD", "create a PRD", "draft product requirements", "create a product spec", "write requirements for a new feature", "create a product document", "write an agentic PRD", "create a requirements document", "draft a PRD for coding agents", "plan a new product or feature", or mentions "PRD", "product requirements document", or "product spec" in the context of writing or creating one. Also triggers when the user says "help me plan a feature", "scope out a project", or "define requirements for" something. This skill produces PRDs that coding agents can execute with low drift, low rework, and strong governance.

Configure and manage Claude Code sandboxing for secure code execution. Use when user mentions sandboxing, security isolation, untrusted code, network restrictions, filesystem permissions, or wants to configure Claude Code security settings. Helps enable/disable sandbox mode, configure permissions, troubleshoot compatibility issues, and provide scenario-based configurations.

Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).

Extract and analyze cash flow trends and working capital changes from SEC filings using Octagon MCP. Use when researching operating cash flow, investing activities, financing activities, free cash flow, liquidity, and working capital dynamics from 10-K and 10-Q filings.

Index and search Claude Code sessions using semantic embeddings (Gemini). Find past sessions by topic, relaunch the best match. Triggers on "find session", "which session did I", "relaunch the session where", "session about X".

Spawn a new Claude Code session in a separate terminal to work on a different task, optionally with context from the current session. Use when you need to work on something else without losing your current progress.

Read-only static security audit of Claude Code skills, commands, and plugins. Analyzes SKILL.md frontmatter, body content, supporting scripts, and hooks for security risks. Use this skill when the user asks to "audit a skill", "review skill security", "check SKILL.md for risks", "scan a plugin for dangerous patterns", "verify skill safety", "check skill permissions", "analyze skill hooks", "audit a skill from GitHub", "review a remote skill", "check a skill by URL", or needs a security assessment of any Claude Code skill, command, or plugin before enabling it.

Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.

Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack)

Use when creating specialized Claude Code subagents in .claude/agents/. Use when user says 'create agent', 'add reviewer', 'specialized agent', 'isolated context task'.

Spawnable research agent. Accepts research requests and uses the deep-zotero MCP server to search indexed PDFs. Callers spawn this via Task -- do not invoke directly.

Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.

Defines behavioral and cognitive standards for senior AI engineering agents. Use when configuring agent reasoning protocols, memory management, or context engineering strategies. Use for autonomous reasoning, tiered memory systems, verifiable goal execution, multi-agent orchestration, and token optimization.

Compatibility alias for the canonical `workflow-rig` front door. Use when older prompts mention `agent-workloads` or when you need the legacy workload-planning guidance; for new work, load `workflow-rig` first.

Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agents that do not read AGENTS.md natively (Claude Code, Gemini CLI, Qwen Code). Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve performance by ~4%. Use when the user says "generate CLAUDE.md", "create AGENTS.md", "generate context file", "agentmd", "create recommended CLAUDE.md", "generate agent instructions", "init context file", or any request to create/improve a coding agent context file for a repository. Replaces the default /init command which generates bloated, counterproductive context files.

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

Multi-agent orchestration — N AI agents with distinct personas debate sequentially in real-time. Each agent sees prior agents' output, creating adversarial pressure-testing. Use this skill when the user says "add multi-agent", "ai debate", "agent panel", "multi-agent chat", or "adversarial agents".

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.

Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure

Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]"

Guide for creating Claude Code output styles and reusable response-format contracts. Use when creating, shipping, or customizing an output style for a session; defining the response shape an agent, command, or team worker must produce; standardizing worker reports so a team lead can parse them; or deciding between an output style, a skill, and a CLAUDE.md entry.

OpenAI Codex CLI wrapper — three modes. (gstack)

Transform clarified user requests into structured delegation prompts optimized for specialist agents (cto-architect, strategic-cto-mentor, cv-ml-architect). Use after clarification is complete, before routing to specialist agents. Ensures agents receive complete context for effective work.

Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification

Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).

Imports datasets into FiftyOne with automatic format detection. Supports all media types (images, videos, point clouds), label formats (COCO, YOLO, VOC, KITTI), multimodal grouped datasets, and Hugging Face Hub datasets. Use when importing datasets from local files or Hugging Face, loading autonomous driving data, or creating grouped datasets.

Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on /flow-next:prime.