FreeSkills
Knowledge wiki setup
- 418418 downloads
- 129129 likes
- 161161 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Adaptive epoch selection for walk-forward v1.0.0
Use this resource to choose training epochs per fold in walk-forward optimization
New
- 383 downloads
- 102 likes
- 108 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install walk-forward-epoch-selectionWith 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 generates epoch candidates from search bounds, sweeps epochs for each fold and keeps the one that maximizes walk-forward efficiency (WFE). It reminds you of the guardrails against look-ahead bias.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Wiki health check
- 552552 downloads
- 202202 likes
- 127127 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Ask your wiki
- 374374 downloads
- 131131 likes
- 214214 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki source ingestion
- 315315 downloads
- 230230 likes
- 246246 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki auditor agent
- 556556 downloads
- 205205 likes
- 192192 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
UX research assistant
- 598598 downloads
- 142142 likes
- 236236 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki ingestion agent
- 437437 downloads
- 162162 likes
- 191191 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki librarian agent
- 304304 downloads
- 120120 likes
- 217217 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: method, WFE formula and quick start
- references/epoch-selection-decision-tree.md: decision tree
- references/guardrails.md: guardrails against look-ahead bias
Good fit for
- You train an ML model with walk-forward validation and are unsure how many epochs to use
- You want to avoid an overfitted model looking good
Not for
Tags
- wfo
- epochs
- overfitting
About
You say
“Choose the optimal epoch count for each fold of my WFO, with bounds from 100 to 2000.”
Skill published by terrylica under the MIT 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 choose training epochs per fold in walk-forward optimization
- Review and adjust the result
Content preview
Files
- LICENSE1 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/academic-foundations.md9.8 KB
- references/anti-patterns.md17.7 KB
- references/configuration-framework.md7.8 KB
- references/efficient-frontier.md3.9 KB
- references/epoch-selection-decision-tree.md24.1 KB
- references/epoch-smoothing-methods.md4.1 KB
- references/epoch-smoothing.md15 KB
- references/evolution-log.md0.7 KB
- references/feature-sets.md8.4 KB
- references/guardrails.md5.4 KB
- references/look-ahead-bias-v3.md5.5 KB
- references/look-ahead-bias.md15.4 KB
- references/mathematical-formulation.md7.7 KB
- references/oos-application.md16.4 KB
- references/oos-metrics-implementation.md6.5 KB
- references/oos-metrics.md11.9 KB
- references/oos-workflow.md9.5 KB
- references/range-bar-metrics.md8.1 KB
- references/troubleshooting.md1.2 KB
- references/wfe-aggregation.md2.9 KB
- references/xlstm-implementation.md7.8 KB
- SKILL.md17.4 KB
Origin and licence
Listed unmodified
- Author
- terrylica
- Source
- github.com/terrylica/cc-skills/tree/0ca36f7260a3eb5de13a1b684509c4ecd5fe819b/plugins/quant-research/skills/adaptive-wfo-epoch
- Licence
- MIT
Notice
« adaptive-wfo-epoch » (terrylica, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…