Fix MCP config details, validate skills against API, move to .claude/skills/#2
Open
dym-ai wants to merge 3 commits intoJedIV:masterfrom
Open
Fix MCP config details, validate skills against API, move to .claude/skills/#2dym-ai wants to merge 3 commits intoJedIV:masterfrom
dym-ai wants to merge 3 commits intoJedIV:masterfrom
Conversation
- Fix ML training skill: use typed API (get_performance_metrics, set_algorithm_enabled, UPPERCASE algorithm names) instead of raw dicts - Fix dataset-management: autodetect_settings() called on DSSDataset, capture return value - Fix group-recipe: use set_column_aggregations() as primary approach - Fix data-collections: correct list_objects default (objects not dict) - Fix metadata: add japanese to supported AI description languages - Fix troubleshooting: autodetect_settings().save() pattern - Move skills/ to .claude/skills/ for native Claude Code discovery - Simplify CLAUDE.md now that skills are auto-discovered Co-Authored-By: Claude <noreply@anthropic.com>
dym-ai
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
dataikuapilibrary by inspecting method signatures and source code on a live instanceskills/to.claude/skills/so Claude Code auto-discovers them via native skill discovery instead of relying on manual CLAUDE.md instructionsSkill Fixes
ml-training
modeling['xgboost']) with typed API (settings.set_algorithm_enabled("XGBOOST_CLASSIFICATION", True),settings.disable_all_algorithms())raw['perf']['tiMetrics']withdetails.get_performance_metrics()(official accessor)details.get_modeling_settings()where applicabledataset-management
autodetect_settings()— was incorrectly called onDSSDatasetSettingsin one place; it only exists onDSSDatasetand returns a new settings object.save())recipe-patterns (group-recipe)
settings.set_column_aggregations()as primary approachfirst/last/concatDistinct(not in typed API)data-catalog
list_objects()defaultas_type— documented as"dict"but actual default is"objects"japaneseto supported AI description languagestroubleshooting
autodetect_settings()pattern to include.save()Verified as correct (no changes needed)
ml_task.train(),deploy_to_flow(train_dataset=...),create_prediction_ml_taskparamsTest plan
.claude/skills/🤖 Generated with Claude Code