kwongfuk/codex-skills/repro-record-workflow
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Run research/paper/code reproduction tasks with strict execution logging. Use when requests involve reproducing results, debugging training/evaluation pipelines, Slurm/HPC experiments, dataset/model setup, or iterative small-task execution where every subtask must be written to a repository-level CODEX_RECORD.md.
Install
npx vskill@latest install kwongfuk/codex-skills/repro-record-workflowSKILL.md
Repro Record Workflow
Keep reproduction work and record-keeping coupled:
- Execute a concrete subtask.
- Validate outcome quickly (logs, test, job status, artifact path).
- Append one concise record entry to
CODEX_RECORD.md.
Workflow
- Locate record file:
- Use repository root
CODEX_RECORD.md. - If missing, create it from record-template.md.
- Split request into small subtasks:
- Keep each subtask independently verifiable.
- Prefer one observable output per subtask (job id, file diff, command result).
- Apply storage policy before execution:
- keep repository files under
/homefocused on code, configs,CODEX_RECORD.md, and standard lightweight experiment results - keep datasets, caches, model weights, checkpoints, raw intermediates, and other large artifacts under
/scratch - if a result directory is large, store the primary artifact on scratch and record the absolute scratch path in
Evidence
- Execute subtask:
- Apply environment/config/code changes.
- For training launchers or checkpoint logic, also apply
exact-training-resume-guard. - Run minimal verification.
- Update record immediately:
- Use
scripts/update_codex_record.py. - One entry per completed/failed subtask.
- Include blockers and next action if failed.
- Repeat:
- Never batch many subtasks into one record entry.
Record Rules
- Use timestamped entries (script default).
- Include these fields:
TaskStatusSummaryEvidenceNext
- Keep entries short and factual.
- Use absolute paths/job ids in
Evidence. - If a training run is only restartable from model weights rather than exactly resumable, record that limitation explicitly instead of calling it a resume checkpoint.
Commands
Create or append entry:
Create record file if missing:
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingglobal/repro-record-workflow/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
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
[](https://verified-skill.com/skills/kwongfuk/codex-skills/repro-record-workflow)