shike-huashu-perspectiveHuashu perspective - AI Native Coder mindset. Harness Engineering methodology, zero-code development, knowledge assets construction. Use when: AI coding meth...
Install via ClawdBot CLI:
clawdbot install sjj2026/shike-huashu-perspectiveGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 8, 2026
A business or product person with no coding background uses the Harness Engineering framework to guide an AI coding tool like Cursor through building a working prototype in under an hour. The perspective helps them structure instructions, constraints, and feedback loops so the AI produces usable results instead of random output.
An indie developer stuck with unpredictable AI output applies the three-stage evolution model (Vibe → Spec → SDD Coding) to move from chaotic experimentation to production-grade delivery. They learn to write design docs first and persist specs into CLAUDE.md files for repeatable results.
A small product team uses the knowledge-asset moat concept to convert individual prompt tricks into shared CLAUDE.md files, rules directories, and code templates. This makes AI-assisted development a team capability rather than a personal skill that walks out the door.
A creator who built a useful tool uses the 'open-source influence > closed-source revenue' heuristic to weigh whether to release under MIT. The framework prompts them to ask whether their core value lies in the code itself or in the methodology and community influence.
An educator or thought leader distills their working process into a downloadable framework (like a 'perspective' skill) and distributes it free to build audience and credibility. They use the Zero-Code and knowledge-asset layers to package their expertise as a repeatable system rather than one-off advice.
Release core methodology or tooling under a permissive license (e.g., MIT) to maximize stars, community contributions, and personal brand reach. The free distribution creates inbound opportunities that are worth more than direct licensing revenue.
Publish free 'orange book' style PDFs and open skills to build trust and audience, then monetize through high-touch access. The free tier acts as a lead magnet for premium advisory or community memberships.
Package the Harness Engineering and knowledge-asset frameworks as an internal enablement engagement for product teams adopting AI coding. Deliverables include CLAUDE.md templates, rules directories, and workflow training.
💬 Integration Tip
Adopt the framework incrementally by starting with the three-stage code evolution (Vibe → Spec → SDD) and a single CLAUDE.md file before layering on the full Harness Engineering components. Treat the perspective as a decision lens for methodology and go-to-market questions, and route pure technical implementation or financial questions to other specialized perspectives.
Scored Oct 8, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.