Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

autodl-remote-run-snippet

Étoiles2

Forks0

Mis à jour2 juillet 2026 à 11:06

Generate a copy-paste remote (AutoDL/tmux) run snippet (git fetch/checkout/pull + scripts/train_eval_shutdown_autodl.sh). Use when you need a remote train→eval command block and must manually choose train/eval scripts from scripts/.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

Zhou1317fe5

Zhou1317fe5/research-harness-workflow

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	autodl-remote-run-snippet
description	Generate a copy-paste remote (AutoDL/tmux) run snippet (git fetch/checkout/pull + scripts/train_eval_shutdown_autodl.sh). Use when you need a remote train→eval command block and must manually choose train/eval scripts from scripts/.

AutoDL Remote Run Snippet

This is a mirror of the Codex skill at .codex/skills/autodl-remote-run-snippet/SKILL.md.

Usage

# List candidate scripts (manual selection required)
python3 .codex/skills/autodl-remote-run-snippet/scripts/generate_snippet.py

# Generate the snippet after choosing scripts
python3 .codex/skills/autodl-remote-run-snippet/scripts/generate_snippet.py \
  --branch "<branch>" \
  --train-script "scripts/<train_*.sh>" \
  --eval-script "scripts/<eval_*.sh>"

References

docs/SKILLs/agent-skills-standard.md

Plus depuis ce dépôt

même dépôt

autodl-remote-pull-manifest

Zhou1317fe5/research-harness-workflow

Generate a minimal remote artifact pull manifest (results.json + train/logs + eval logs/metrics/vis) and place files under research_workspace/experiments/<ExpID>/remote_artifacts.

2026-07-022

brainstorming

Zhou1317fe5/research-harness-workflow

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

2026-07-022

exp-analysis-hen

Zhou1317fe5/research-harness-workflow

Analyze experiment results pulled by autodl-remote-pull-manifest (remote_artifacts) and generate a Hypothesis→Evidence→Next-Experiment (H→E→N) report. Use when you want evidence-first analysis from logs/metrics/vis and an actionable next-step plan to improve <主指标>.

2026-07-022

exp-results-ingest-local

Zhou1317fe5/research-harness-workflow

Ingest pulled remote artifacts under research_workspace/experiments/<ExpID>/remote_artifacts, summarize latest eval (summary.json), and update research_workspace/00-实验记录.md (index row + detailed section). Use when you want to record <主指标>/<辅助指标> into 00-实验记录.md after pulling remote artifacts.

2026-07-022

mission-approved-doc

Zhou1317fe5/research-harness-workflow

Use when the input is a user-approved design doc or implementation plan and the agent needs to turn it into an executable issues CSV before handing off to CSV execution.

2026-07-022

mission-csv-execute

Zhou1317fe5/research-harness-workflow

Use when executing an existing task CSV and the agent needs to push all actionable rows to closed-loop completion without stopping between issues.

2026-07-022

Exécutez n'importe quel Skill en un clic