Skip to content

Add slime skills for rollout, reward, filter, eval config, and CI#1646

Open
yitianlian wants to merge 6 commits intoTHUDM:mainfrom
yitianlian:codex/slime-skills-alignment
Open

Add slime skills for rollout, reward, filter, eval config, and CI#1646
yitianlian wants to merge 6 commits intoTHUDM:mainfrom
yitianlian:codex/slime-skills-alignment

Conversation

@yitianlian
Copy link
Collaborator

@yitianlian yitianlian commented Feb 28, 2026

Add skills

@yitianlian yitianlian marked this pull request as ready for review February 28, 2026 18:42
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e5c2fa5442

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

```bash
rg --files tests | rg 'reward|rollout|quick_start'
pytest "$(rg --files tests | rg 'reward|rollout|quick_start' | head -n 1)" -vv
python -m slime.utils.debug_utils.replay_reward_fn --help

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Replace missing replay_reward_fn validation command

The skill asks users to run python -m slime.utils.debug_utils.replay_reward_fn --help, but that module does not exist in this repository (checked with rg --files slime | rg replay_reward_fn), so this validation step fails with ModuleNotFoundError and blocks the documented reward-function workflow. Please update this to an existing utility or remove the step.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant