发现 Skills

Autonomous application of specification-compliance automatic checks. How to use the spec-compliance-check command, how to reference requirement documents, procedures to maintain a 95% specification-compliance rate, and methods to identify specification-deviation risks. Intended for use when implementing new features from Phase C onward.

Decompose time series into trend, seasonal, and residual components. Use for forecasting, pattern analysis, and seasonality detection.

Generate styled word clouds from text with custom shapes, colors, fonts, and stopword filtering. Supports PNG/SVG export and frequency dictionaries.

Kimi K2.6 runtime policy for thinking mode, no-thinking research mode, tool use, context budget, and long-horizon coding tasks.

Git worktree based multi-agent team workflow for isolated parallel coding, review, QA, and integration.

This skill creates or updates a README.md file in the GitHub home directory of the current project. The README.md file it generates will conform to GitHub best practices, including badges, project overview, site metrics, getting started instructions, and comprehensive documentation.

Global environment variable management skill. Manages a direnv-based hierarchical environment variable system. Keywords: env, environment variables, environment, .env, direnv, env-check, configuration

Complete feature development lifecycle from research to deployment. Uses Gemini Search for best practices, architecture design, Codex prototyping, comprehensive testing, and documentation generation. Full 12-stage workflow.

Automate internationalization and localization workflows for web applications with translation, key generation, and library setup

Comprehensive pre-deployment validation ensuring code is production-ready. Runs complete audit pipeline, performance benchmarks, security scan, documentation check, and generates deployment checklist.

Comprehensive security auditing across static analysis, dynamic testing, dependency vulnerabilities, secrets detection, and OWASP compliance

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management. Coordinates cicd-engineer, workflow-automation, tester, and security-auditor agents through mesh topology to create, optimize, and maintain GitHub Actions workflows. Handles workflow generation, performance optimization, security hardening, matrix testing strategies, and workflow debugging. Use when building CI/CD pipelines, optimizing existing workflows, or establishing automation standards.

Complex multi-agent swarm orchestration with task decomposition, distributed execution, and result synthesis

Use when conducting a comprehensive code review of a pull request across multiple quality dimensions. Orchestrates 12–15 specialized reviewer agents across four phases using a star-topology coordination pattern. Covers automated gates, parallel expert reviews (quality, security, performance, architecture, documentation), integration analysis, and a final merge recommendation within a four-hour timebox.

Advanced database performance tuning including query optimization, indexing strategies, partitioning, and scaling patterns

ML deployment paradigms including batch vs real-time inference, online vs offline serving, edge deployment, and serverless ML.

Orchestrates AI-native sprint management with autonomous agent coordination and continuous delivery. Use when running development sprints with AI agent teams or coordinating parallel task execution.

AI agent structures complex reasoning through numbered thought sequences with explicit dependencies. Use when facing multi-step problems, complex debugging, or architectural decisions.

A skill for tracking and managing task progress. It checks for unfinished tasks when a conversation starts, suggests starting a task when a new task is requested, and suggests reporting completion when work is finished. Integrates with a checkpoint system.

An integrated skill for fact-checking and reference verification of texts. It performs claim extraction, verification against external sources, and organization of references in a single workflow. Used for document review, article proofreading, report checks, and academic paper inspections.

name: freelance-search description: ALWAYS invoke when the user wants to find freelance gigs, contracts, or consulting engagements matched to a CV from vetted/niche/regional boards (not Upwork/Fiverr).

Use for React integration patterns and best practices in dojo.js. Triggers: dojo react, react hooks, effect atoms, Result.match, infinite scroll dojo, DojoSdkProvider, useDojoSDK, react patterns

Use when managing game state with Zustand in dojo.js. Triggers: dojo state, zustand dojo, game state, createDojoStore, optimistic update, getEntity, mergeEntities, state management, revert transaction

Leverage shell_agent for autonomous file creation and modification with automatic tool selection and error recovery