Delegate Git operations to a Manager when a worker lacks credentials. The skill explains how to prepare command requests, receive results, and synchronize shared files, covering repository downloads, branches, commits, pushes, and other Git tasks.
中文简介正在准备中。当前显示英语简介。
Change the language model used by a Worker Agent through the agt command-line tool. The controller resolves model settings, regenerates configuration, and recreates the container to apply the change without a manual restart.
中文简介正在准备中。当前显示英语简介。
Manage AI agent Workers by creating roles, selecting runtimes, starting or stopping Workers, and updating their skills. It also covers runtime migration, direct mentions between Workers, and access to the QwenPaw console.
中文简介正在准备中。当前显示英语简介。
Guides the creation, import, and composition of agent teams with one Team Leader and multiple Workers. It explains member changes, delegation through the Leader, and where to manage each Worker's runtime settings and lifecycle.
中文简介正在准备中。当前显示英语简介。
Coordinate changes to shared task folders with .processing marker files that indicate ongoing work. Managers and Workers check these markers before editing, synchronize files through MinIO, and remove markers after completing their changes.
中文简介正在准备中。当前显示英语简介。
Switch the Manager Agent's primary language model with a script that checks connectivity before saving configuration. You can also set how much context the model accepts and whether extended thinking is enabled.
中文简介正在准备中。当前显示英语简介。
Configure external APIs and existing MCP tool servers through Higress AI Gateway. The skill covers YAML-based setup, credential updates, Worker access permissions, and connection checks before making tools available to the Workers that need them.
中文简介正在准备中。当前显示英语简介。
Set up and operate ReMe through its command-line interface to retain context across conversations. Search saved history, record facts and decisions, ingest documents, and consolidate notes into long-term memory stored in a local workspace.
中文简介正在准备中。当前显示英语简介。
Turn financial research requests into Tushare data retrieval, cleaning, comparisons, and concise summaries. Study Chinese stocks, funds, financial statements, market flows, and economic indicators, or export structured files for further analysis.
中文简介正在准备中。当前显示英语简介。
Send notifications and documents through DingTalk using enterprise bots or Webhook bots, which receive messages through a dedicated URL. Manage multiple bots and choose text, Markdown, links, or cards for individual and group conversations, depending on bot type.
中文简介正在准备中。当前显示英语简介。
Search the public web through Serper for current information and sources unavailable in local files or project APIs. Refine queries, check important claims against linked pages, and summarize findings with source titles and links.
中文简介正在准备中。当前显示英语简介。
Retrieve past conversations, preferences, project history, and decisions stored in ReMe from Claude Code. Read relevant records with source paths, save explicitly requested facts, and investigate plugin or memory service connection problems.
中文简介正在准备中。当前显示英语简介。
Keep decisions, preferences, and project context in daily notes and curated memory files. Search those records before answering questions about past work, so useful information remains available across separate conversations.
中文简介正在准备中。当前显示英语简介。
Retrieve past facts, preferences, and decisions from ReMe with references to saved files. Check service health, pending memory writes, and consolidation schedules, or organize existing notes into long-term knowledge when requested.
中文简介正在准备中。当前显示英语简介。
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
中文简介正在准备中。当前显示原文说明。
Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X", or describes a task that likely requires multiple capabilities working together. Also use when the user mentions composing workflows, building pipelines, or needs help across several domains at once — even if they only say "find me a skill". This skill supersedes simple single-skill search by decomposing the task into subtasks and assembling an optimal skill portfolio.
中文简介正在准备中。当前显示原文说明。
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.
中文简介正在准备中。当前显示原文说明。
Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.
中文简介正在准备中。当前显示原文说明。
Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.
中文简介正在准备中。当前显示原文说明。
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
中文简介正在准备中。当前显示原文说明。
Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.
中文简介正在准备中。当前显示原文说明。
Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.
中文简介正在准备中。当前显示原文说明。