Loading...
Loading...
Found 7 Skills
Scaffold, clone, and deploy config-driven NextJS landing pages that use a shared UI components package. Use this skill when creating single or multiple startup landing pages with email capture, analytics, and modern design. Supports batch creation from templates or CSV/JSON files, and automatic Vercel deployment with custom domains. Each landing is a standalone NextJS app driven by an app.json config file.
Create and manage structured documentation — experiments, plans, findings, checkpoints, research, learnings. Config-driven, parallel-safe.
Before adding abstraction, asks "do we need this now?" Activates when proposing factories, abstract classes, config-driven behavior, or "for future extensibility." Resists over-engineering. Three similar lines are better than a premature abstraction.
Reference OpenCode docs when implementing skills, plugins, MCPs, or config-driven behavior.
Command-line interface for CloudAnalyzer — Agent-friendly harness for CloudAnalyzer, a QA platform for mapping, localization, and perception outputs. Supports 27 commands across 8 groups: point cloud evaluation, trajectory evaluation, ground segmentation QA, config-driven quality gates, baseline evolution, processing, visualization, and interactive REPL.
Score the PATH an agent took (tool choice, ordering, retries, repeatability, grounding) — not just its final answer — to catch "corrupt success" (right answer via a bad/unsafe path) and flakiness. Deterministic trace schema + pass^k repeatability + config-driven rule checks (forbidden tool, out-of-order, retry-storm, excessive steps, edited-without-read grounding). Parses canonical traces.json, hooklib.audit / code-logger events.jsonl, OR a full Claude Code session transcript (--transcript, richest source: recovers retrieval args + observation + per- step ok). Trigger when the user says "grade the trajectory", "score the path not the answer", "did it cheat / take a bad path", "did it look before it acted / grounding", "corrupt success", "is this flaky / does it repeat", "pass^k", "grade a session transcript", "trace grader", or invokes /trace-grader.
Use when the user is shaping how one model request or request family should be instructed or templated, including prompt slots, input/instruct/info layering, mappings, recursive placeholder injection, prompt config, YAML or config-file-driven prompt behavior, and reusable prompt structure.