GitHub
project-context-sync
Maintains synchronized project context for long-running work across sessions. Use when: starting a session (read context), completing significant work (update context), making architectural decisions (document...
Skills IA Tests et sécurité
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Catégories: Tests et sécurité
Tests et sécurité Effacer les filtres
Explorer
GitHub
dependency-analyzer
ライブラリのEOL状況と互換性要件を確認する。endoflife.dateやnpmからバージョン互換性情報を取得する
GitHub
package-updater
npm/yarn/pnpm/bunに対応したパッケージ更新を実行する。Node.jsバージョン管理ツール（mise/nvm/asdf）にも対応
GitHub
library-release-checker
GitHubや公式ドキュメントからライブラリのリリース情報を取得し、破壊的変更・非推奨化・ビルトイン化を特定する
GitHub
test-runner
lint、test、buildコマンドを実行し、結果を解析する。エラー時は原因分析と修正提案を行う
GitHub
code-impact-checker
破壊的変更に基づいてプロジェクト内のコードを検索し、影響を受けるファイルと行を特定する。テストカバレッジも確認する
GitHub
code-migrator
破壊的変更に対応したコード修正を行う。import文の変更、API呼び出しの修正、設定ファイルの更新を実行
GitHub
reward-shaping-engineering
Master reward function design - potential-based shaping, hacking patterns, validation
GitHub
prioritizing-improvements
Use when stakeholders pressure you to change technical priorities and you're tempted to compromise on security-first or call it synthesis - enforces risk-based prioritization over stakeholder preferences
GitHub
exploration-strategies
Master ε-greedy, UCB, curiosity-driven, RND, intrinsic motivation exploration
GitHub
identifying-technical-debt
Use when cataloging technical debt under time pressure and tempted to explain choices instead of delivering document - enforces execution discipline with scoped delivery patterns for partial catalogs
GitHub
rl-debugging
Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees
GitHub
offline-rl
Master CQL, IQL, BCQ - offline RL from fixed datasets without environment interaction
GitHub
value-based-methods
Master DQN, Double DQN, Dueling DQN, Rainbow - value-based methods for discrete actions
GitHub
policy-gradient-methods
Master REINFORCE, PPO, TRPO - direct policy optimization with trust regions
GitHub
model-based-rl
Master Dyna-Q, MBPO, Dreamer - model-based RL with world models and planning
GitHub
validating-architecture-analysis
Validate architecture artifacts against contracts and consistency requirements - codifies systematic validation practices with professional reporting
GitHub
generating-architecture-diagrams
Generate C4 architecture diagrams from subsystem catalogs - codifies abstraction strategies, notation conventions, and selection criteria
GitHub
using-system-archaeologist
Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows
GitHub
rl-environments
Gym/gymnasium API - custom environments, spaces, wrappers, vectorization, debugging
GitHub
actor-critic-methods
Master A2C, A3C, SAC, TD3 - actor-critic methods for continuous control
GitHub
using-deep-rl
Routes to appropriate deep-RL skills based on problem type and algorithm family
GitHub
assessing-architecture-quality
Use when assessing codebase architecture and you feel pressure to soften critique, lead with strengths, or frame problems diplomatically - provides evidence-based critical assessment resisting relationship and...
GitHub
multi-agent-rl
Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment
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.