What it does
This repo is a collection of 21 skills
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for MINIMAX_API_KEY (per the README)
- Category Automatisierung und Agenten
Maker’s original description
OpenJudge: A Unified Framework for Holistic Evaluation and Quality RewardsFür Anbieter: Badge ins README
Wenn du das gebaut hast, füge diesen Code in dein README ein. Das Badge verlinkt auf diese Seite.
[](https://mcp.popnx.com/en/skills/agentscope-ai-openjudge)Ähnliche Skills
Gleiche Art Arbeit, sortiert wie die Skill-Liste
21 Skills (Anweisungssammlungen) von agentscope-ai, die eine KI liest und befolgt · kein MCP-Server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
Install the whole set (21)
If you want every one, let the AI install them in one go. Know 2 things first
- Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
- Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Uploading to Claude on the web and apps: you need 21 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 12. Nov. 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
- 00-academic-router
Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review…
- 00-arena-router
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 are…
- 00-meta-eval
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, assessi…
- 01-auto-arena
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate ranking…
- 01-eval-design
Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a labeled evaluation set. Also use when the user mentions test data design, eval coverage, difficulty stratification, synthe…
- 01-graders-and-pipeline
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating grad…
- 01-paper-review
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_scien…
- 02-bib-verify
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…
- 02-metric-design
Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader se…
- 02-ref-hallucination-arena
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) m…
- 02-rl-reward
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win r…
- 03-align-human
Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TN…
- 03-ref-hallucination-arena
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) m…
- 04-eval-report
Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "ho…
- 05-rag-eval
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…
- 06-prompt-regression
Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change he…
- 07-redteam
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,…
- 08-bootstrap
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 nee…
- claude-authenticity
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 bel…
- find-skills-combo
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…
- mmx-cli
Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and w…
Was einen Skill von MCP unterscheidet
MCP = die Hände
Verbindet die KI mit einem externen Dienst oder Daten, etwa Notion lesen oder eine Rechnung erstellen. Ein Programm oder Server muss laufen.
Skill = das Handbuch
Eine Textdatei, die der KI zeigt, wie eine Aufgabe geht. Sie verbindet sich mit nichts.
Manches überschneidet sich: Einige Skills starten Skripte mit Werkzeugen, einige MCP-Server liefern nur Wissen. Geh von der Aufgabe aus.
Funktioniert mit
Vom Anbieter nicht angegeben · SKILL.md-Skills laufen in Apps mit Agent-Skills-Unterstützung wie Claude Code, Codex und Cursor
Installieren
Pick a skill first
This repo has 21 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Diskussion
Fragen, Tipps teilen oder melden, dass etwas nicht geht. Sortiert nach „hilfreich“.
Noch keine Beiträge. Stell die erste Frage oder teile einen Tipp.
Beiträge hier stammen von Nutzern, nicht vom PopNx-Team.
Von GitHub
- GitHub-Sterne
- 1.113
Stars are for the whole repo, not each skill - Anbieter
- agentscope-ai
- Lizenz
- Apache-2.0
- Letzte Codeänderung
- 18. Nov. 2026
- SKILL.md-Dateien im Repo (mit Übersetzungen und Vorlagen)
- 21
- Themen
- agent, agent-skills, ai-agent, alignment, evaluation, grader, llm, reward, reward-model, rlhf, skill-md, skills