02-rl-reward SKILL.md skillA
02-rl-reward from agentscope-ai/openjudge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agentscope-ai/openjudge/02-rl-reward@git:20260911.d1e0642Pins git:20260911.d1e0642 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agentscope-ai/openjudge
- Path
skills/openjudge-core/02-rl-reward/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260911.d1e0642, committed Sep 11, 2026
- Size
- 6,692 bytes
- Repository stars
- 1,054
- License
- Apache-2.0
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 rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# RL Reward Construction with OpenJudge Build reward signals for reinforcement learning from human feedback (RLHF) and reinforcement learning from AI feedback (RLAIF) using the `openjudge` library. ## When to Use This Skill - Building scalar rewards for GRPO / REINFORCE rollout scoring - Generating (chosen, rejected) preference pairs for DPO / IPO - Best-of-N candidate selection - Multi-dimensional reward shaping (correctness + safety + format) - Replacing or bootstrapping a reward model with LLM-as-judge ## Step 1 — Choose Your Reward Strategy Use this decision tree **before** writing any code: ``` RL Algorithm + Task type? │ ├── GRPO / REINFORCE — Verifiable task (math, code, structured output) │ └── → POINTWISE ✅ (FunctionGrader, exact score, zero LLM cost) │ ├── GRPO / REINFORCE — Subjective task (instruction following, dialogue, summarization) │ └── → PAIRWISE TOURNAMENT ✅ (compare each rollout vs all others in group, │ reward = net win rate within group) │ ├── DPO / IPO / SLiC — need (chosen, rejected) pairs │ └── → PAIRWISE ✅ (two-way comparison, return winner/loser) │ └── Best-of-N / reranking — rank N candidates …
Read the whole file at its exact version.
How to install
mdr add agentscope-ai/openjudge/02-rl-reward@sha256:8a452ea43509bdbaThe line at the top of this page pins the label git:20260911.d1e0642, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7j3dvtr4k77jix4u)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 11, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6692 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
agentscope-ai/openjudge · 1,054 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7j3dvtr4k77jix4u GET https://markdownregistry.com/api/v1/resolve?ref=agentscope-ai/openjudge/02-rl-reward GET https://markdownregistry.com/api/v1/blob/8a452ea43509bdba72f849f3583f1f9a411a316dcd11ad5d5c4f2dd5dd66b93b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.