Build resumable state-machine workflows with checkpoint patterns, progress preservation, and automatic recovery for complex multi-phase operations that need to survive interruptions, timeouts, and failures.
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 →Build resumable state-machine workflows with checkpoint patterns, progress preservation, and automatic recovery for complex multi-phase operations that need to survive interruptions, timeouts, and failures.
Use when saving current iteration progress mid-conversation, before context compaction, or at interim pause points
Checkpoint reference guide for GSD
Standard Operating Procedure for /fix-ci phase. Fix CI/deployment blockers after PR creation.
---name: chemcrow-drug-discovery
Guide for analyzing chess positions from images and determining optimal moves. This skill should be used when asked to find the best move, checkmate, or tactical solution from a chess board image. It provides structured approaches for image-based chess analysis, piece detection calibration, position validation, and move verification.
Dotfile backup and sync with chezmoi. TRIGGERS - chezmoi, dotfiles, sync dotfiles, backup configs, cross-machine sync.
Chezmoi dotfile management expertise
---name: chic-ml-framework-agent
Chilisin Electronics inductor MPN encoding patterns, value decoding, and handler guidance. Use when working with Chilisin inductors or ChilisinHandler.
Analyze China macroeconomic data, PBOC monetary policy, fiscal policy, and their impact on A-share and HK stock markets. Track GDP, CPI, PPI, PMI, social financing, and interpret policy signals. Use when user asks about 中国宏观经济, 央行政策, economic data impact on markets, or needs to understand policy implications for investment.
---name: chip-clonal-hematopoiesis-agent
Chipone Technology MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Chipone LED driver components or ChiponeHandler.
Use when deciding which pgdbm pattern to use (standalone, dual-mode library, or shared pool) - provides decision tree based on deployment context without requiring doc exploration
chrome-auth-recorder
Run and manage a single-instance Chrome DevTools MCP server on this machine, including start/stop/status/dedupe workflows and safe cleanup to prevent multiple chrome-devtools-mcp processes from running concurrently. Use when you need a singleton MCP server for Chrome DevTools or when EMFILE/process-spawn issues require enforcing exactly one chrome-devtools-mcp instance.
Build modern, cross-browser extensions using WXT - the next-generation framework that supports Chrome, Firefox, Edge, Safari, and all Chromium browsers with a single codebase.
---name: chromosomal-instability-agent
Search and retrieve context from past development sessions using Chronicle data. Works with MCP (fast, structured) or CLI commands (portable). Use when user asks about previous work, wants to recall past decisions, needs to understand codebase history, or wants to avoid repeating past approaches.
Automate cross-system summarization workflow for Chronicle sessions. Export sessions from remote systems (like FreeBSD) and import/summarize on local machine with Gemini API. Use when you have sessions on a system without Gemini API access and need to summarize them on another machine.
Complete workflow for tracking development work with Chronicle - session recording, git tracking, AI summarization, and Obsidian documentation. Works with CLI commands (portable) or MCP tools (faster). Use when starting a new development session, setting up project tracking, or when user wants comprehensive session management.
Apply when making API calls to ChurchTools, using churchtoolsClient methods, handling API responses, or working with Tags API. Covers correct HTTP method names, parameter structure, and response handling patterns.
Predict customer churn risk using behavioral signals, engagement data, and predictive analytics
A lightweight checklist for CI, toolchain bumps, and version/release hygiene for the ComputationalPaths Lean 4 project (Lake + lean-action CI).
'Checks GitHub CI status and guides fixing failures. Use when asked to check CI, verify PR checks, or diagnose CI failures after PR creation.'
ci-doctor
CIBA(Client Initiated Backchannel Authentication)機能の開発・修正を行う際に使用。Poll/Push/Pingモード、Login Hint解決、FCM通知実装時に役立つ。
Cinder Usage Rules
cinema-voice-architect
Automatic decryption/decoding tool that uses AI to detect and crack encryption.
Implement circuit breaker patterns for fault tolerance, automatic failure detection, and fallback mechanisms. Use when calling external services, handling cascading failures, or implementing resilience patterns.
Implement the circuit breaker pattern to prevent cascade failures in distributed systems. Use when adding resilience to API clients, external service calls, or any operation that can fail and should fail fast.
Comprehensive Citrix environment health assessment and diagnostics. Use when analyzing Citrix site health, checking VDA registration status, verifying Delivery Controller services, assessing StoreFront availability, or performing environment audits. Covers infrastructure health, database connectivity, resource utilization, and component status verification.
Citrix infrastructure architecture and capacity planning. Use when designing Citrix environments, planning capacity, sizing components, configuring high availability, designing multi-site deployments, or planning disaster recovery. Covers architecture patterns, component sizing, redundancy design, and best practices.
StoreFront deployment planning, configuration, and security hardening. Use when planning StoreFront infrastructure, configuring stores and authentication, setting up server groups, implementing SSL/TLS, or troubleshooting StoreFront connectivity issues. Covers architecture patterns, high availability, and operational procedures.
condition/restartパターンを適用。エラーハンドリング実装時に使用
Document construction claims for disputes and recovery. Compile evidence, calculate damages, track notice requirements, and prepare claim packages.
Deep learning-based variant calling from long reads using Clair3 for SNPs and small indels. Use when calling germline variants from ONT or PacBio alignments, particularly when high accuracy is needed for clinical or research applications.
Common Clap patterns and idioms for argument parsing, validation, and CLI design. Use when implementing CLI arguments with Clap v4+.
Detect and analyze geometric clashes between BIM elements. Identify hard clashes, soft clashes, and workflow conflicts using spatial analysis and rule-based detection.
Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.
Apply the multi-proxy discrimination framework to classify geochemical anomalies as SEISMIC, CLIMATIC, VOLCANIC, or COMPOUND (CVSE). This is the core methodology for distinguishing earthquake signals
Build coding agents with the Claude Agent SDK. Use when creating agentic workflows, implementing todo tracking, monitoring agent progress, building multi-turn conversations, streaming responses, or integrating custom tools with Claude Code.
claude-agent-sdk
Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.
claude-api
Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.
Analyze repo's .claude/** for overlap with bluera-base and suggest cleanup
Diagnose slow Claude Code startup and guide cleanup. Use /bluera-base:claude-code-clean to run.
Executes tasks using the Claude Code CLI (`claude`). Automatically determines the safest permission mode (plan, acceptEdits, or bypassPermissions) based on the task type.