Super-Dev Full-Stack Self-Evolving Suite
Paste the following prompt into your AI chat to install this skill:
Please install @user_7f13f2c8/super-dev-skills according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
One-off agent skills often treat every task as stateless: ambiguous requirements are rushed into code, while testing, UX, supply-chain safety, and past mistakes remain fragmented. This skill turns full-stack delivery into an auditable workflow that binds requirements, architecture, tests, UX, security, memory, and evolution into one set of constraints.
How it works
The super-dev-orchestrator detects modes such as BOOTSTRAP, FEATURE, FIX, and REFACTOR, then delegates to focused skills:
- Requirements interviewing: forms hypotheses and acceptance criteria before implementation.
- TDD and review: enforces Red → Green → Refactor, testing pyramid, DAMP, and Stop-the-Line checks.
- Security gates: compares dependencies against malicious-package data before install, then uses SBOM, CVE, and static-analysis checks for supply-chain risk.
- UX audit and memory: flags AI-style aesthetic anti-patterns and stores project facts, preferences, and lessons in .memory/.
Boundaries
It fits multi-step full-stack work where engineering constraints, dependency safety, or UX quality matter. For disposable scripts or simple copy edits, the process overhead may outweigh the benefit. If a team already has fixed architecture and security workflows, treat it as a supplement rather than a replacement.
Use Cases
- Turn vague requests into assumptions, acceptance criteria, and shared terminology before coding.
- Run supply-chain gates before adding dependencies, including malicious-package scans and SBOM/CVE audits.
- Audit finished features for AI aesthetic anti-patterns, responsive issues, and accessibility regressions.
- Persist project facts, user preferences, and lessons learned into layered memory for later retrieval.
Best For
- Solo developers maintaining multi-round AI-generated code need durable requirements, testing, and security constraints.
- Technical leads shipping full-stack features want unified ADR, TDD, and dependency-review standards.
- Product engineers building AI-agent workflows need reusable project memory from past iterations.
- Architects reviewing agent or outsourced delivery need auditable requirements, tests, and security reports.
Related Skills
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.
A hybrid-evolution agent for OpenClaw developers that offers tiered-confirmation and rollback-safe capability optimization.