GitHub
release
Create versioned releases - bump version via PR, tag, create GitHub release. CI publishes to npm.
Skills IA Bases de données
Découvrez les skills Bases de données, comparez leurs dépôts et consultez leurs instructions.
Catégories: Bases de données
Bases de données Effacer les filtres
Explorer
GitHub
memento
Manages mementos for session persistence - save and restore context across /clear and /compact
GitHub
corregir-graficos
Ejecuta 📚 SUBFASE 3A para errores gráficos - Corrección basada en ejemplos funcionales.
GitHub
internal-db
Persist data across ticket executions using MotherDuck/DuckDB. Use when tasks require: (1) Storing workflow state that persists between tickets, (2) Caching expensive computations or API results, (3) Maintainin...
GitHub
x-ranking-engine
Use this skill when you need to reason about the machine learning models that determine the final order of the "For You" timeline. It is essential for tasks involving model feature engineering, tuning engagemen...
GitHub
search-model
Search OpenRouter API for AI models and get pricing/capability details for model-reference.md
GitHub
x-experimental-ops
Use this skill when reasoning about how the algorithm is tuned, why different users see different behaviors, or how "Success" is defined by X's engineering team.
GitHub
review
Code review using multiple AI models concurrently
GitHub
m3-theria
FEP Octave M3: 理論モジュール (I-E-S)。因果モデルを構築・更新し、世界観を形成する。 Use when: 「なぜ？」質問時、予測と結果が乖離した時、パターン検出が必要な時、根本原因分析時。 Use when NOT: 単純な事実確認のみ...
GitHub
ml-experiment-runner
Run ML/deep learning experiments on Modal with robust error handling, W&B logging, and thorough documentation. Use when asked to: (1) Run an experiment, (2) Implement experiment handlers, (3) Fix and re-run fai...
GitHub
reward-function-v330
Use when tuning RL reward function weights, fixing reward hacking, or addressing P&L gradient issues
GitHub
ai-adaptive-uxui-design
支援 AI 彈性化調整的 UX/UI 設計指南 - 自適應介面、串流回應、載入狀態、對話式 UI
GitHub
requirements-framework-builder
This skill should be used when the user asks to "extend requirements framework", "add new requirement type", "create custom strategy", "add custom calculator", "modify framework architecture", "create requireme...
GitHub
x-safety-filtering
Use this skill when analyzing why content is not appearing, checking for "shadowban" conditions, or understanding the safety compliance layer. This skill covers the `VisibilityLib` logic that runs *after* candi...
GitHub
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
GitHub
app-development-flow
App 開発の標準フロースキル。 1.基盤做成 → 2.式様読取 → 3.設計 → 4.実装 → 5.テスト → 不足→循環 の反復開発プロセスを定義。
GitHub
pentest-checklist
This skill should be used when the user asks to "plan a penetration test", "create a security assessment checklist", "prepare for penetration testing", "define pentest scope", "follow security testing best prac...
GitHub
yukyu-ui-ux-master
Maestro de UI/UX para YuKyuDATA - Diseño de interfaces, experiencia de usuario, accesibilidad WCAG, patrones de interacción japoneses, dark/light mode, glassmorphism, responsive design, micro-interacciones y an...
GitHub
spec
Specification management - creating, organizing, and maintaining spec items with acceptance criteria and traits.
GitHub
p4-energeia
純粋定理 P4: 純粋行為 (A-P)。Flow×Value のみの最も抽象的な行為機能。 Use when: 実行、行動、「何をするか」を問う時。 Triggers: M6 Praxis（具体化）, M8 Anamnēsis（記録化） Keywords: pure-action, doing, execution,...
GitHub
scenario-thinking
Scenario-driven solution design that focuses on future use cases, dimensional analysis, and explicit trade-offs
GitHub
product-planning
Facilitate product thinking and structure work in Linear.
GitHub
ralph
This skill should be used when the user asks to "write a spec", "create a spec", "define requirements", "use ralph", "ralph methodology", "autonomous development", "sync specs to code", "run the planning loop",...
GitHub
api-integration
법제처 OPEN API를 MCP 프로젝트에 통합할 때 사용. lawSearch.do와 lawService.do 엔드포인트, target 파라미터로 기능 구분. 새로운 API 엔드포인트 통합 시 참조.
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.