发现 Skills

Disaster Recovery for IoT provides comprehensive strategies and implementations for recovering IoT infrastructure from catastrophic failures, including data loss, service outages, and regional disaste

Use this skill when a change affects user-visible behavior and needs public documentation at `docs.chronote.gg`.

Expert knowledge for Data Model Layer modeling in Documentation Robotics

Drift Detection and Retraining is practice of continuously monitoring ML models in production for performance degradation and data distribution changes, automatically triggering retraining pipelines w

Error Handling is a critical component of backend development that enables applications to operate reliably, maintainably, and debuggably. It encompasses patterns and best practices for handling, logg

EDA toolkit. Analyze CSV/Excel/JSON/Parquet files, statistical summaries, distributions, correlations, outliers, missing data, visualizations, markdown reports, for data profiling and insights.

Language learning expert with proven methods for acquiring multiple languages efficiently and effectively

Full validation workflow for QA agent. Runs automated checks (type-check, lint, test, build) and code quality review with enforced checkpoints. Use when validating implementation after code review.

Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and dependency injection updates. Use when upgrading AngularJS applications, planning framework migrations, or ...

Use when working with tdd workflows tdd refactor

Use this skill when you need to orchestrate specialized Claude agents in separate sessions. Perfect for long-running tasks, specialized agents with MCP tools, and resumable workflows.

Use this skill when you need to invoke another Claude Code session via the cli-agent-runner.sh script to perform specialized, potentially long-running tasks in a simplified way. This wrapper handles session management, result extraction, and can be run in background with polling support.

Patterns for designing command-line tools that agents can use effectively. Use when designing new CLIs, reviewing existing CLIs for agent compatibility, or adding agent-friendly features. Covers minimal ceremony, JSON output, context injection, batch operations, and error handling.

Transform ambiguous specs into implementable work items through adversarial refinement. Use when receiving specs, claiming epics, or starting complex (l/xl) tasks. Use /breakdown for spec→tasks decomposition, /refine for sharpening individual items.

Use when implementing features or fixing bugs — write the test first, watch it fail, write minimal code to pass. Ensures tests verify behavior by requiring failure first.

Create Claude Code hooks following correct patterns, security best practices, and configuration. Use this skill when building PreToolUse, PostToolUse, SessionStart, or other hook types for plugins.

Guidelines for writing effective Clojure docstrings with Markdown formatting, Wikilinks, code examples, and tables. Always use this skill when writing or reviewing docstrings in Clojure code, or when asked about docstring formatting and style. Triggers on (1) writing new functions/vars/namespaces with docstrings, (2) updating existing docstrings, (3) questions about docstring best practices, (4) reviewing code with docstrings.

Operate the current Logseq command-line interface to inspect or modify graphs, pages, blocks, tags, and properties; run Datascript queries; show page/block trees; manage graphs; and manage db-worker-node servers. Use when a request involves running `logseq` commands or interpreting CLI output.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Magisk Manager automation - app launching, module installation, Zygisk configuration

Copilot preferred path fixture.

Implement @data-client Managers for global side effects - websocket, SSE, polling, subscriptions, logging, middleware, Controller actions, redux pattern

A comprehensive multi-tool for reStructuredText (RST) and Sphinx documentation. This skill provides expert guidance for processing RST files, building and managing Sphinx projects, handling various output formats, extending functionality, and ensuring high-quality, accurate, and up-to-date documentation.

Reverse-engineers copy into reusable templates. Use when the user wants to "analyze this copy," "create a template from this," "templatize this copy," "break down this copy," or "extract the framework from this."