Create or update an audit of recent decisions for quality
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Create or update an audit of recent decisions for quality
Create or update a structured decision record
Facilitate data-driven technical decisions using embedded decision matrices and trade-off analysis. Use when relevant to the task.
Git-powered state awareness - track file changes, session context, decisions, and work history. Query what happened in previous sessions and during current session. Auto-activates for state queries and before duplicating work.
Strategic decision-making for CFN Loop progression with robust parsing. Use when evaluating validator consensus and determining PROCEED/ITERATE/ABORT outcomes.
Use when starting plan execution to decompose implementation plans into Claude Code Task tool tasks at H2 (Task) granularity - creates one task per plan task with citation-manager directives, keeping plan as source of truth
Use after writing-plans to decompose monolithic plan into individual task files and identify tasks that can run in parallel (up to 2 subagents simultaneously)
Investiga documentación oficial y valida soluciones en internet antes de implementar.
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data. Use when calling variants with DeepVariant deep learning caller.
Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
Delete files from knowledge base with directory governance. Use when user wants to remove or delete content. Reads RULE.md to check deletion permissions and handles dependencies.
container-use環境(コンテナ、ファイル、メタデータ)を完全に削除する手順
Use when investigating inbox placement, reputation, and compliance signals
Delta Sharing configuration, monitoring, and recipient management for secure cross-organization data sharing.
Analyze project dependencies for security vulnerabilities, outdated
Analyze project dependencies for vulnerabilities, updates, and optimization opportunities. Use when auditing dependencies or managing package versions.
Automated dependency management with security scanning, update orchestration, and compatibility validation
Add new services to DIContainer, create protocol-based implementations, set up singletons or factories for Leavn app dependency injection
>
Manage Python dependencies using uv package manager. Use when installing, adding, removing, or updating packages. Always prefer uv over pip.
Map, track, and manage project dependencies across teams, systems, and organizations. Identify critical path items and prevent blocking issues through proactive dependency management.
Health checks, metrics, alerting ve rollback stratejileri.
deploy-service
Deployment workflow for company repos (pre/pro) using CI, ECR, and Helm.
Set up progressive canary deployments on GCP Cloud Run with traffic splitting, monitoring alerts, and automated rollback.
Production deployment configurations for elizaOS agents with Docker, monitoring, and scaling.
Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.
Azure Deployment Stacks GA 2025 features for unified resource management, deny settings, and lifecycle management
Deployment Strategy Agent. Feature Flag, Canary/Blue-Green 배포, 롤백 전략을 담당합니다. 안전한 배포와 점진적 롤아웃을 관리합니다.
**Purpose**: Systematically validate the application is ready for production deployment, catching common "works locally, fails on Render" issues BEFORE they happen.
deployment-verification
Inline orchestration workflow for dependency audit and updates. Provides step-by-step phases for dependency-auditor detection, priority-based updates with dependency-updater, and verification cycles.
多方案評估決策框架. Use for: (1) 面臨 3+ 技術方案時的結構化評估, (2) 架構決策時的系統化分析, (3) 防止衝動決策和技術債務累積
Deep knowledge of legendary designers and their enduring contributions. Learn from Saul Bass, Massimo Vignelli, Dieter Rams, Paula Scher, and others whose work defines excellence. Use when seeking inspiration, understanding design history, or applying proven approaches.
Auto-activates when synthesizing outputs from multiple parallel sub-agents
Selects the appropriate quasi-experimental method (DiD, ITS, SC) based on data structure and research questions. Use when the user is unsure which method to apply.
Detect empty catch blocks and exception swallowing anti-patterns. Finds catch blocks that silently ignore errors without logging or rethrowing. Works across all languages. Use when user asks about error handling issues.
檢查聯準會持有證券的未攤銷折價(Unamortized Discounts)是否出現與特定歷史危機期間相似的走勢模板,並用多指標交叉驗證是否真的屬於「金融壓力升高」而非單純會計/利率效果。
Analyze git changes to determine release scope (marketplace/plugin/variants)
Utilities and patterns for detecting execution environment (CI/CD vs local, network access, available ports, timeouts). Use when you need to adapt scripts or workflows based on where the agent is running, or when creating helper scripts that need environment-aware behavior.
Detects OS command injection vulnerabilities by identifying unsafe system/popen/exec calls with user-controlled input. Use when analyzing command execution, shell operations, or investigating potential command injection points.
Detects logic bypass vulnerabilities including authentication bypass, authorization bypass, and business logic flaws. Use when analyzing authentication mechanisms, access controls, or investigating security control bypasses.
Detects null pointer dereference vulnerabilities by identifying unchecked pointer usage and missing validation. Use when analyzing pointer operations, input validation, or investigating crash vulnerabilities.
Detects race condition vulnerabilities including TOCTOU, double-checked locking issues, and shared state problems. Use when analyzing concurrent operations, file access patterns, or investigating timing-related vulnerabilities.
Detects unsafe signed/unsigned integer conversions that can lead to integer overflow and security check bypasses. Use when analyzing integer operations, comparisons, or investigating conversion-related vulnerabilities.
detection
Browser automation that maintains page state across script executions. Write small, focused scripts to accomplish tasks incrementally. Once you've proven out part of a workflow and there is repeated w
Package and dependency management patterns across ecosystems (npm, pip, cargo, maven). Covers lockfiles, semantic versioning, dependency security scanning, update strategies, monorepo workspaces, transitive dependencies, and avoiding dependency hell.
Run isolated mux desktop (Electron) instances (temp MUX_ROOT + free ports)