Skill-RM

In the author's own words, from each skill's SKILL.md.

• instruction_following

  Use this skill when judging instruction following for IF-RewardBench-style samples. It is especially useful when the sample contains exact constraints, a visible checklist, format requirements, word/count limits, language restrictions, or multiple sub-instructions that should be decomposed before the final benchmark judgment.

  skills/instruction_following/SKILL.md on GitHub (opens in a new tab)

• reward_judge_fair

  Use this Skill-RM reward judge to compare candidate responses for a visible user request with generic rubric, principles, bias controls, output contract, and Python sandbox checks over visible text.

  skills/reward_judge_fair/SKILL.md on GitHub (opens in a new tab)

• reward_judge_operational

  Use this Skill-RM reward judge when response judging may benefit from resource-rich evidence: benchmark/task metadata, visible references or ground truth, checklists, verifier signals, code/math/factuality tool protocols, same-backbone judging pipeline signals, or bias-control resources. Load it when these resources can materially change the verdict; do not load it merely to be thorough.

  skills/reward_judge_operational/SKILL.md on GitHub (opens in a new tab)

• instruction_following_pointwise

  Use this skill when judging a single candidate response for instruction following and a scalar score is needed. It is especially useful when the sample contains exact constraints, a visible checklist, verifier resources, format requirements, word/count limits, language restrictions, or multiple sub-instructions that should be decomposed before scoring.

  integrations/verl/recipe/skill_rm_if_pointwise/skills/instruction_following_pointwise/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 431k stars · 5 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 313k stars · 30 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 312k stars · 15 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 297k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 187k stars · 19 skills