无状态迭代开发循环工作流，支持开发 (develop)、调试 (debug)、验证 (validate) 三个阶段，每个阶段都有独立的文件记录进展。

无状态工作流协调器，根据任务意图自动选择最优工作流。

Implement change data capture and event-driven sync.

Context Driven Development pipeline for release workflows

CDK8s for type-safe Kubernetes manifests using Python. Use when building complex K8s applications programmatically, generating manifests from code, creating reusable infrastructure patterns, or managing multi-environment deployments.

Expert Celery distributed task queue engineer specializing in async task processing, workflow orchestration, broker configuration (Redis/RabbitMQ), Celery Beat scheduling, and production monitoring. Deep expertise in task patterns (chains, groups, chords), retries, rate limiting, Flower monitoring, and security best practices. Use when designing distributed task systems, implementing background job processing, building workflow orchestration, or optimizing task queue performance.

Cell Ranger skill for 10X Genomics single-cell data processing

Build a **reflection system**, not a task manager. This is a private, single-user operating system for executives that combines thoughtful frameworks with coaching-style prompts.

Automate TLS certificates, rotation, and mTLS configuration.

Two-phase compilation error fixer for Rust and TypeScript using Cerebras LLM bulk processing + dedicated agent cleanup. Use when you have 20+ compilation errors that need fast bulk reduction, or when errors are mostly mechanical (type mismatches, missing imports, syntax issues).

Task mode heap limiter for memory-constrained environments

Agent interaction capture, logging, and analysis with memory tracking and security (Rust implementation). Use when you need to capture and analyze agent interactions, track tool usage and performance metrics, query execution history, or export audit trails for compliance.

Small business finance, tax strategy, and wealth management. Auto-activates for Augusta Rule, home office deduction, Solo 401k, R&D credits, tax optimization, Mercury/Ramp operations, Bitcoin treasury, IRS notices, audit defense, and bootstrapped founder CFO work.

Build and execute multi-step prompt chains for complex tasks

- [Purpose](#purpose)

Expert guidance for building conversational AI applications with Chainlit framework in Python. Use when (1) creating chat interfaces for LLM applications, (2) building apps with OpenAI, LangChain, LlamaIndex, or Mistral AI, (3) implementing streaming responses, (4) adding UI elements like images, files, charts, (5) handling user file uploads, (6) implementing authentication (OAuth, password), (7) creating multi-step workflows with visible steps, (8) building RAG applications with document upload, or (9) deploying chat apps to web, Slack, Discord, or Teams.

Analyze LinkedIn profiles in target accounts to identify potential internal champions. Evaluates role, career path, mutual connections, interests, and suggests personalization approach. Use when you need to find who will champion your solution internally.

change-impact-analyzer

A practical framework to map change dependencies and blast radius, including who/what is affected, what to test, rollout/rollback strategies, and stakeholder ownership

Perform post-merge integration tasks after a code PR is successfully merged. This skill completes the development cycle by moving approved specs from `docs/changes/` to `docs/specs/`, updating the ret

Specifies bugs, upgrades, refactors, and behavioral changes as explicit deltas against existing feature specifications, preserving original intent while defining what changes, what remains unchanged, and how correctness is verified.

Analyze and predict construction change orders using ML. Classify change order types, predict costs and schedule impacts, identify patterns, and optimize approval workflows.

Manage construction change orders from request to approval. Track costs, schedule impacts, and maintain audit trail for dispute prevention.

Classify a change set as behavior vs structure, then recommend the correct PR label (change:behavior or change:structure) and the appropriate local/CI checks. Use when the user asks whether a change is a behavior change or a structure change, what label to apply, or how CI/testing should differ based on change type.

Auto-generate changelogs from commit history

Generate beautiful infographic PNG images from Claude Code changelog summaries. Use this skill after changelog-interpreter has generated a user-friendly summary, to create a visual representation that can be saved and shared.

Documenting changes to software over time using structured changelog formats, semantic versioning, and clear categorization to help users and developers understand what has changed.

Transform technical changelog entries into user-friendly newsletter content for email, blog posts, and release notes. Use when converting CHANGELOG.md files, git commit logs, or release notes into customer-facing communications.

>

Maintain CHANGELOG.md with properly categorized entries. Use after implementing features, fixing bugs, or making any notable changes. Follows Keep a Changelog format.

Expert in resilience testing, fault injection, and building anti-fragile systems using controlled experiments.

Plan fault injection and resilience tests.

Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use for resilience testing, game days, failure injection experiments, and building confidence in system stability.

The skill that makes senior developers nervous but can't quite articulate why.

Plan and architect a single chapter at beat-level granularity. Use when you have a chapter from the Architecture Document and need to create a detailed outline before drafting. Produces a Chapter Outline Document for use by draft-coach or ghostwriter.

This skill generates comprehensive chapter content for intelligent textbooks after the book-chapter-generator skill has created the chapter structure. Use this skill when a chapter index.md file exists with title, summary, and concept list, and detailed educational content needs to be generated at the appropriate reading level with rich non-text elements including diagrams, infographics, and MicroSims. (project, gitignored)

Autonomously draft and polish chapters through multi-skill editorial passes. Use when you have a complete outline and want to produce a polished first draft with iterative refinement.

Evaluate educational chapters from dual student and teacher perspectives. This skill should be used when analyzing chapter quality, identifying content gaps, or planning chapter improvements. Reads all lessons in a chapter directory and provides structured analysis with ratings, gap identification, and prioritized recommendations.

An intelligent skill that creates production-ready elizaOS character configurations with comprehensive personality traits, knowledge bases, and plugin integrations.

Ensure character consistency across scenes and episodes by maintaining canonical character files and validating usage.

This skill generates interactive Chart.js visualizations for use in iframes using any chart type supported by the library (line, bar, pie, doughnut, radar, polar area, bubble, scatter). Use this skill when users need to create data visualizations for educational content, reports, or dashboards. The skill creates complete MicroSim packages with HTML, CSS, and documentation.

Create and manage Mermaid architecture diagrams with automatic SVG generation

Generate quick, effective responses for chat and messaging platforms

Design conversational AI chatbots with optimal flows and user experience

Implements interactive widget actions and bidirectional communication patterns for ChatKit. This skill should be used when building AI-driven interactive UIs with buttons, forms, entity tagging (@mentions), composer tools, and server-handled widget actions. Covers the full widget lifecycle from creation to replacement.

This skill generates two essential marketing/documentation assets for Chat Memo version releases:

Find concurrency issues including race conditions, deadlocks, unsafe shared state, and improper synchronization