Research & Learning skills

Reasoning data lost across agent steps and missing low-confidence fallback Keywords: sqlite, triangulation, escalation, confidence

The English summary is being prepared. Showing the original description.

High concurrent SQLite access causing lock contention and missing indexes Keywords: sqlite, wal, indexes, performance

The English summary is being prepared. Showing the original description.

Perform triangulated cognitive research combining SQLite memory, GitHub 10k+ stars patterns, and ToT DAG benchmarking before critical architectural decisions. Automatically triggers subagent research escalation when confidence is low (<0.70). Keywords: research, benchmark, github, memory, triangulation, grounding, best-practices, escalation

The English summary is being prepared. Showing the original description.

Delegate implementation (or, when explicitly requested, research) to GPT-6.1 Sol (high reasoning; xhigh on request) via Codex CLI. Claude plans, orchestrates, and reviews; Sol writes the code.

The English summary is being prepared. Showing the original description.

Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.

The English summary is being prepared. Showing the original description.

Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md.

The English summary is being prepared. Showing the original description.

Timeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull them, and pairwise judges rank the survivors on a tournament ladder instead of 1-10 scores, evolving the leaders until the clock runs out. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking about X", "what features should we build", "explore options for X". Not for executing a task over time (timeboxed-iterating) or optimizing a measurable metric (autoresearch).

The English summary is being prepared. Showing the original description.

Build a timeframe-bounded research dossier by decomposing a topic into year orchestrators and month-level research passes that each write one condensed paragraph plus sources directly into a target file. Use when the user asks for a dossier, timeline, chronology, release history, or month-by-month research bounded by specific years or months. Not for timeless explainers or single-document summaries with no temporal scope.

The English summary is being prepared. Showing the original description.

Orchestrate work as a cyclic directed graph of subagent-executed nodes with transition criteria on edges, budgeted cycles, and per-node gates (runtime verification, metric, or artifact). Use when the user says "workgraph", "run this as a graph", "graph this work", or when a goal has parallel branches, feedback loops, or mixed gate types that a linear loop cannot express. Every node is sized to a 64k context budget, so small goals run as a two-node do/verify graph and large goals scale out without caps. For clock-driven or metric-driven single loops, timeboxed-iterating and autoresearch remain lighter.

The English summary is being prepared. Showing the original description.

Open the warm channel for a role the pipeline already assessed. Finds who the user already knows at the company, researches named targets from public professional presence when they know nobody, grades each path honestly, drafts the ask through the voice agent, and writes the contacts into the Referrals table in job_search.md.

The English summary is being prepared. Showing the original description.

Guide a first-time Forge builder through building Forge Guru, a Rovo Agent that answers Forge questions. Use for Forge onboarding, a first Forge or Rovo app, or resuming this tutorial. Route unrelated existing-app changes, debugging, reviews, and connector work to the specialist skills.

The English summary is being prepared. Showing the original description.

Use when the user wants a complete SPSS or SPSS-MCP empirical research workflow: organize source data, prepare datasets, design variables and models, run SPSS analyses, export Chinese result paragraphs and tables, write a Chinese LaTeX paper, and compile the final PDF.

The English summary is being prepared. Showing the original description.

X/Twitter public sentiment research. Searches X for real-time perspectives, market sentiment, expert opinions, breaking news, and community discourse. Use when: user asks "what are people saying about", "X/Twitter sentiment", "check X for", "search twitter for", "what's CT saying about", or wants public opinion on a stock, sector, company, or market event.

The English summary is being prepared. Showing the original description.

Use when the user wants to add source identity from PDF, URL, arXiv, DOI, note, experiment result, manual reference, or Zotero item into a Research Pilot project.

The English summary is being prepared. Showing the original description.

Use when a Research Pilot project needs read-only gap detection or Evidence Need extraction from the Project Understanding Graph.

The English summary is being prepared. Showing the original description.

Use when the user wants a related-work survey, technical lineage, task timeline, or paper-map around a baseline paper, research task, benchmark, or project direction.

The English summary is being prepared. Showing the original description.

Use when the user wants an agent to create or update a project-local source/paper note from a PDF, URL, arXiv, DOI, manual source, or Zotero item.

The English summary is being prepared. Showing the original description.

Use when a graph gap or Evidence Need should become a targeted paper-search contract or candidate lead list.

The English summary is being prepared. Showing the original description.

Use when a project-local paper dossier should produce graph delta JSON proposals and run through the human-gated delta loop.

The English summary is being prepared. Showing the original description.

Use when the user wants an agent to track, inspect, or operate Research Pilot project memory through natural chat.

The English summary is being prepared. Showing the original description.

Use when a new user wants an agent to start Research Pilot from scratch, create or inspect a local workspace, create the first project, or begin project tracking.

The English summary is being prepared. Showing the original description.

Use when the user wants papers to consider for a graph gap or missing evidence need.

The English summary is being prepared. Showing the original description.

Use when a research project needs normal project memory updated from human intent, sources, evidence pressure, experiment results, or direction changes; strict graph review is optional advanced mode.

The English summary is being prepared. Showing the original description.

Use when a Research Pilot project needs a read-only recommendation for the next workflow action.

The English summary is being prepared. Showing the original description.