FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Three-phase AutoML and DEFT training pipeline v1.0.0
Use this resource to run a three-phase AutoML, DEFT and AutoML training workflow
New
- 527 downloads
- 132 likes
- 196 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install automl-deft-three-phase-pipelineWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent checks the shared prerequisites, runs the baseline hyperparameter search, passes the settings to the DEFT loop (root-cause analysis, data generation, hard-example mining, retraining), then reruns AutoML on the augmented dataset. It does not reimplement AutoML or DEFT. You get a final model and the phase history.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- references/consolidated-preflight.md: shared preflight checks
- references/phase-handoffs.md: handoffs between phases
- references/pitfalls-and-quality-checks.md: pitfalls and quality checks
Good fit for
- You want to improve an AOI inspection model end to end
- You have an annotated dataset and want a hyperparameter search followed by a DEFT loop
Not for
Tags
- AutoML
- DEFT
- training
- AOI
About
You say
“Run the full three-phase AOI workflow on my PCB board dataset.”
Skill published by nvidia under the Apache-2.0 license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to run a three-phase AutoML, DEFT and AutoML training workflow
- Review and adjust the result
Content preview
Files
- BENCHMARK.md7.2 KB
- config/skillspector-baseline.yaml0.8 KB
- evals/evals.json0.8 KB
- LICENSE11.3 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/consolidated-preflight.md6.6 KB
- references/phase-handoffs.md8.8 KB
- references/pitfalls-and-quality-checks.md2.6 KB
- references/quick-start-example.md2.9 KB
- skill-card.md4.8 KB
- SKILL.md17.3 KB
- skill.oms.sig5.7 KB
Origin and licence
Listed unmodified
- Author
- nvidia
- Source
- github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-run-automl-deft-pipeline
- Licence
- Apache-2.0
Notice
« tao-run-automl-deft-pipeline » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…