GitHub
train-model
Execute model training with optimization algorithms. Use when running training loops on datasets.
☆ 13Voir le skill
Skills IA Recherche
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Catégories: Recherche
Recherche Effacer les filtres
Explorer
GitHub
check-memory-safety
Check Mojo code for memory safety issues (ownership violations, use-after-free, etc.). Use to catch memory bugs.
☆ 13Voir le skill
GitHub
detect-code-smells
Identify code quality issues and anti-patterns. Use when reviewing code for maintainability problems.
☆ 13Voir le skill
GitHub
quality-security-scan
Scan code for security vulnerabilities and unsafe patterns. Use before committing sensitive code or in security reviews.
☆ 13Voir le skill
GitHub
check-dependencies
Validate and verify dependencies are available and compatible. Use when setting up environments.
☆ 13Voir le skill
GitHub
evaluate-model
Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.
☆ 13Voir le skill
GitHub
validate-workflow
Validate GitHub Actions workflow files for syntax, best practices, and correctness. Use before committing workflow changes or when workflows fail.
☆ 13Voir le skill
GitHub
worktree-create
Create isolated git worktrees for parallel development. Use when working on multiple issues simultaneously.
☆ 13Voir le skill
GitHub
refactor-code
Restructure code for improved clarity and maintainability. Use when addressing code smells or technical debt.
☆ 13Voir le skill
GitHub
create-review-checklist
Generate review checklists for different change types. Use to customize review focus based on what was changed.
☆ 13Voir le skill
GitHub
gh-batch-merge-by-labels
Batch merge multiple PRs by label (e.g., all 'ready-to-merge' PRs). Use when you have multiple approved PRs to merge.
☆ 13Voir le skill
GitHub
install-workflow
Create GitHub Actions workflows for automated package building and distribution. Use in package phase to automate .mojopkg building and release creation.
☆ 13Voir le skill
GitHub
gh-read-issue-context
Read context from GitHub issue including body and comments. Use before starting implementation work or when prior context is needed.
☆ 13Voir le skill
GitHub
test-diff-analyzer
Analyze test differences between runs to identify flaky tests and consistency issues. Use to find tests that fail intermittently.
☆ 13Voir le skill
GitHub
run-precommit
Run pre-commit hooks locally or in CI to validate code quality before committing. Use to ensure commits meet quality standards and CI will pass.
☆ 13Voir le skill
GitHub
profile-code
Measure execution time and memory usage of code. Use when analyzing performance characteristics.
☆ 13Voir le skill
GitHub
mojo-simd-optimize
Apply SIMD optimizations to Mojo code for parallel computation. Use when optimizing performance-critical tensor and array operations.
☆ 13Voir le skill
GitHub
worktree-cleanup
Remove merged or stale git worktrees. Use after PRs are merged, work is done, or when worktrees are no longer needed.
☆ 13Voir le skill
GitHub
generate-tests
Create test cases for functions and modules. Use when implementing TDD or improving coverage.
☆ 13Voir le skill
GitHub
plan-validate-structure
DEPRECATED: The notes/plan/ directory has been removed. Planning is now done directly through GitHub issues. See gh-read-issue-context and gh-post-issue-update skills instead.
☆ 13Voir le skill
GitHub
analyze-equations
Parse and interpret mathematical equations from research papers. Use when extracting formulas for implementation.
☆ 13Voir le skill
GitHub
worktree-switch
Switch between git worktrees for parallel development. Use when working on multiple issues simultaneously.
☆ 13Voir le skill
GitHub
generate-docstrings
Create docstrings for functions and classes. Use when documenting code APIs.
☆ 13Voir le skill
GitHub
track-implementation-progress
Track implementation progress against plan. Use to monitor component delivery and identify blockers.
☆ 13Voir le skill
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.