aiming-lab/autoresearchclaw/nlp-alignment

Claude Code and agent skill by aiming-lab/autoresearchclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Best practices for LLM alignment techniques including RLHF, DPO, and instruction tuning. Use when working on alignment or safety.

Install

npx vskill@latest install aiming-lab/autoresearchclaw/nlp-alignment

SKILL.md

LLM Alignment Best Practice

Methods:

  • RLHF: Train reward model → PPO fine-tuning (complex but powerful)
  • DPO: Direct preference optimization (simpler, no reward model needed)
  • GRPO: Group relative policy optimization
  • SFT: Supervised fine-tuning as alignment baseline

Training recipe:

  • Start with SFT on high-quality instruction data
  • DPO: lr=5e-7, beta=0.1, batch_size=64
  • PPO: lr=1e-6, clip=0.2, KL coeff=0.02
  • Use reference model for KL penalty
  • Evaluate on safety benchmarks (TruthfulQA, BBQ, etc.)

Common pitfalls:

  • Reward hacking: model finds shortcuts to high reward
  • Mode collapse: model generates repetitive outputs
  • Catastrophic forgetting: loses general capabilities

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
13,988
Repository forks
1,636
7-day trend score
48

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 10 Aug 2026, 3 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/aiming-lab/autoresearchclaw/nlp-alignment/badge)](https://verified-skill.com/skills/aiming-lab/autoresearchclaw/nlp-alignment)

Something wrong with this skill or its page? Tell us.