modelscope/map-verl-config
ajet/copilot/map-verl-config/SKILL.md
Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters to AgentJetJob.
$ install --global
skillsauthnpx skillsauth add modelscope/agentjet map-verl-configInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 27, 2026, 7:12 AM160.7s1 file scanned
SKILL.md
- name:
- map-verl-config
- description:
- Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters to AgentJetJob.
- license:
- Complete terms in LICENSE.txt
-
find user requested verl config in codebase/agentjet/ajet/default_config/verl/verl_default.yaml
-
check
codebase/agentjet/ajet/default_config/verl/config_auto_convertion_verl.jsonc, whether a mapping to this config already exists. -
if not, add a config under
ajetfield incodebase/agentjet/ajet/default_config/ajet_default.yaml, and add a mapping incodebase/agentjet/ajet/default_config/verl/config_auto_convertion_verl.jsonc -
double check, confirm that default value in
ajet_default.yamlis the same as verl config inverl_default.yaml, and the mapping is correct inconfig_auto_convertion_verl.jsonc -
ask user whether to add to AgentJetJob (ajet/copilot/job.py), if the user confirms:
- learn how other config is added in ajet/copilot/job.py
- add to init signature (with type hint and default None)
- update docstring with parameter description
- add instance attribute assignment with cast()
- add mapping to
overridesdict
- CRITICAL: update
ajet/default_config/ajet_config_schema.py
- the schema must have a dataclass for EVERY nested level in the config path
- e.g., for
ajet.trainer_common.optim.lr, need:AjetOptimdataclass withlr: float = 1e-6AjetTrainerCommonmust haveoptim: AjetOptim = field(default_factory=AjetOptim)
- if parent dataclass is missing the nested field, config loading will store it as a raw dict instead of a typed dataclass, causing
getattr()to fail at runtime
Related Skills
modelscope/swarm-configuration
data-ai
VerifiedTrustedCommunity
How `max_env_worker` caps the "Running Episodes" gauge, and how `AgentJetJob` relates to the YAML config.
209SKILL.mdUpdated May 27, 2026
modelscope/skill-normalizer
tools
VerifiedTrustedCommunity
Convert skills in non-standard formats to the standard Agent Skills `SKILL.md` format. Validates YAML frontmatter (name, description, license, compatibility, metadata, allowed-tools), directory structure (SKILL.md, scripts/, references/, assets/), and best practices. Use when the user asks to normalize, validate, or fix a skill.
209SKILL.mdUpdated May 27, 2026
modelscope/download-from-swanlab-url
devops
VerifiedTrustedCommunity
Download per-step time-series metric data (reward, entropy, response length, etc.) from a SwanLab cloud run URL as a pandas.DataFrame. Use when the user provides a SwanLab URL and wants to fetch or analyze training curves.
209SKILL.mdUpdated May 27, 2026
modelscope/ajet/copilot/create-keep-think-model-chat-template
development
VerifiedTrustedCommunity
Your task is to investigate the chat template of given model, go to its tokenizer config and check whether the following behavior exists: > > Remove history <think> block from the input when apply chat template when converting messages. > This behavior will make RL training slower, if this behavior exists, please change the chat template to forbid such behavior. You must not do this in-place, instead, please create another model. E.g., "/mnt/data_cpfs/xielipeng.xlp/models/Qwen3-8B" -> "/mnt
209SKILL.mdUpdated May 27, 2026