Clone
1
Skills Reference
wmj2024 edited this page 2026-07-07 15:02:54 +08:00
Skills Reference
This page documents all AI coding agent skills installed in the project's pi agent environment. Skills are on-demand capability packages that the agent loads automatically when relevant tasks arise.
📦 Installed Skills
| # | Skill | Source | Sub-Skills |
|---|---|---|---|
| 1 | 🎨 ui-ux-pro-max | nextlevelbuilder | Design intelligence — 50+ styles, 161 color palettes, 57 font pairings |
| 2 | 🧪 skills-testing-qa | qajonatasmartins | 19 QA/testing sub-skills |
| 3 | 🔒 security-audit | cloudflare | 6-phase security audit pipeline |
| 4 | 🖌️ design-auditor | Ashutos1997 | Design QA scoring across 19 categories |
| 5 | ⚙️ cc-devops-skills | akin-ozer | 31 DevOps generator & validator skills |
1. 🎨 ui-ux-pro-max
Source: github.com/nextlevelbuilder/ui-ux-pro-max-skill
Purpose: Full-stack UI/UX design intelligence for web and mobile applications across 10 technology stacks.
Capabilities
- 50+ design styles — glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design
- 161 color palettes organized by product type
- 57 font pairings with Google Fonts integration
- 161 product types with reasoning rules
- 99 UX guidelines across 10 priority categories
- 25 chart types with recommendations
- 10 tech stacks — React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, HTML/CSS
Design Sub-Skills
| Sub-Skill | Purpose |
|---|---|
| brand | Brand identity, voice, assets |
| design-system | Token architecture, specs |
| ui-styling | Component implementation |
| logo-design | AI logo generation (55 styles, 30 palettes) |
| cip-design | Corporate Identity Program (50 deliverables) |
| slides | HTML presentations with Chart.js |
| banner-design | Banners for social, ads, web, print (22 styles) |
| icon-design | SVG icon generation (15 styles) |
Priority Rule Categories
| Priority | Category | Impact |
|---|---|---|
| 1 | Accessibility | CRITICAL |
| 2 | Touch & Interaction | CRITICAL |
| 3 | Performance | HIGH |
| 4 | Style Selection | HIGH |
| 5 | Layout & Responsive | HIGH |
| 6 | Typography & Color | MEDIUM |
| 7 | Animation | MEDIUM |
| 8 | Forms & Feedback | MEDIUM |
| 9 | Navigation Patterns | HIGH |
| 10 | Charts & Data | LOW |
Search Engine
# Design system (full recommendations)
python3 skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system -p "Project Name"
# Domain-specific search
python3 skills/ui-ux-pro-max/scripts/search.py "<keyword>" --domain <domain>
# Stack best practices
python3 skills/ui-ux-pro-max/scripts/search.py "<keyword>" --stack <stack>
Available Domains
product, style, typography, color, landing, chart, ux, gsap, google-fonts, react, web, prompt
Available Stacks
react, nextjs, vue, nuxtjs, nuxt-ui, svelte, astro, shadcn, html-tailwind, angular, laravel, swiftui, flutter, jetpack-compose, react-native, threejs
2. 🧪 skills-testing-qa
Source: github.com/qajonatasmartins/skills-testing-qa
Purpose: Comprehensive QA and testing skill pack with 19 sub-skills covering the full testing lifecycle.
Sub-Skills
| Sub-Skill | Purpose |
|---|---|
| bug-traking | Bug tracking workflows and best practices |
| clickup-task-context | ClickUp integration for QA tasks |
| design-pattner | Design pattern verification |
| domain-storytelling-plantuml | Domain storytelling with PlantUML |
| figma-context | Figma design context for QA |
| framework-context | Framework-specific testing context |
| jira-task-context | Jira integration for QA tasks |
| owasp-context | OWASP security testing context |
| prisma-risk-testing | PRISMA risk-based testing methodology |
| prompt-craft | Test prompt engineering |
| refinament | Test refinement techniques |
| setup | Test environment setup |
| slack-context | Slack integration for QA workflows |
| strategy-testing-context | Test strategy development |
| teams-context | Microsoft Teams integration |
| test-design | Test design techniques and patterns |
| test-heuristic | Heuristic testing approaches |
| test-verifier | Test verification and validation |
| write-test-case | Test case writing standards |
3. 🔒 security-audit
Source: github.com/cloudflare/security-audit-skill
Purpose: Multi-phase security audit skill that turns the agent into a security auditor. Orchestrates parallel agents through a structured pipeline to find exploitable vulnerabilities.
Six-Phase Pipeline
| Phase | Name | Description |
|---|---|---|
| 1 | Recon | Parallel research agents map application architecture, trust boundaries, and input surfaces. Produces architecture.md. |
| 2 | Hunt | Parallel general agents attack the codebase from different angles (injection, access control, business logic, cryptography, feature abuse, chained attacks, wildcard). Each can spawn sub-agents. |
| 3 | Validate | Separate agents try to disprove each finding. Adversarial review kills false positives. |
| 4 | Report | Produces REPORT.md (human-readable) and FINDINGS-DETAIL.md (detailed traces for MEDIUM+ findings). |
| 5 | Structured Output | Writes findings.json conforming to report-schema.json, validated by validate-findings.cjs. |
| 6 | Independent Verification | Fresh agents verify every factual claim in the structured output against actual source code. |
Key Files
| File | Purpose |
|---|---|
SKILL.md |
Setup, core principles, workflow overview, audit anti-patterns |
RECONNAISSANCE.md |
Phase 1 reconnaissance prompts and synthesis instructions |
HUNTING.md |
Phase 2 orchestration, hunting methodology, validation rules |
ATTACK-CLASSES.md |
Core, wildcard, and obvious-things attack prompts |
MEMORY-SAFETY-AND-BINARY.md |
Memory-safety, binary, and kernel hunting for native targets |
AI-AND-LLM.md |
Prompt-injection, agent/tool, output-handling hunting for LLM-backed targets |
WEB-PROTOCOL-AND-AUTH.md |
HTTP request-framing, cache, and auth-protocol hunting classes |
Features
- Multiple runs are additive — each run explores different code paths
- Reads prior
findings.jsonfiles to skip known issues and target gaps - Independent verification ensures claim accuracy
4. 🖌️ design-auditor
Source: github.com/Ashutos1997/claude-design-auditor-skill
Purpose: Audits designs against 19 professional design categories. Works with Figma files, code (HTML/CSS/React/Vue), screenshots, wireframes, and written descriptions.
Scoring System
| Score | Description |
|---|---|
| Overall Score | /100 with per-category breakdown (mini bar chart per row) |
| Accessibility Score | WCAG coverage across categories 2, 6, 7, 15, 16 |
| Ethics Score | Dark patterns and manipulative design (Category 18) |
| Usability Score | Nielsen heuristics cross-reference (Categories 1, 2, 3, 6, 7, 10) |
Severity Levels
| Level | Label |
|---|---|
| 🚫 | Blocker — legal/compliance violations (WCAG AA, GDPR, PECR) |
| 🔴 | Critical |
| 🟡 | Warning |
| 🟢 | Tip |
Special Features
- Color blindness context — every failing color pair annotated with affected blindness type
- SVG accessibility checks — decorative vs. meaningful SVG patterns, aria-hidden, role="img"
- Design System detection — MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap (system-specific fixes)
- Supports English and Korean
- Compatible with Claude, Manus, and other SKILL.md-compatible agents
5. ⚙️ cc-devops-skills
Source: github.com/akin-ozer/cc-devops-skills
Purpose: Practical DevOps skill pack with 31 skills — 16 generators for scaffolding production-ready configs, 14 validators for linting/security/dry-run validation, and 1 debugger for cluster troubleshooting.
Generator Skills (16)
| Skill | Generates |
|---|---|
| ansible-generator | Ansible playbooks and configurations |
| azure-pipelines-generator | Azure DevOps pipeline YAML |
| bash-script-generator | Shell scripts with best practices |
| dockerfile-generator | Dockerfiles with multi-stage builds |
| fluentbit-generator | Fluent Bit configurations |
| github-actions-generator | GitHub Actions workflow YAML |
| gitlab-ci-generator | GitLab CI pipeline configuration |
| helm-generator | Helm charts for Kubernetes |
| jenkinsfile-generator | Jenkins pipeline scripts |
| k8s-yaml-generator | Kubernetes manifests |
| logql-generator | LogQL queries for Loki |
| loki-config-generator | Loki configuration |
| makefile-generator | Makefiles with targets |
| promql-generator | PromQL queries |
| terraform-generator | Terraform configurations |
| terragrunt-generator | Terragrunt configurations |
Validator Skills (14)
| Skill | Validates |
|---|---|
| ansible-validator | Ansible playbook syntax and structure |
| azure-pipelines-validator | Azure DevOps pipeline correctness |
| bash-script-validator | Shell script linting and best practices |
| dockerfile-validator | Dockerfile best practices and security |
| fluentbit-validator | Fluent Bit configuration correctness |
| github-actions-validator | GitHub Actions workflow validity |
| gitlab-ci-validator | GitLab CI configuration correctness |
| helm-validator | Helm chart linting and structure |
| jenkinsfile-validator | Jenkins pipeline syntax |
| k8s-yaml-validator | Kubernetes manifest validation |
| makefile-validator | Makefile syntax and structure |
| promql-validator | PromQL query correctness |
| terraform-validator | Terraform configuration and security |
| terragrunt-validator | Terragrunt configuration validation |
Debugger Skill (1)
| Skill | Purpose |
|---|---|
| k8s-debug | Kubernetes cluster troubleshooting and diagnosis |
📋 Quick Reference
When to Use Each Skill
| Task | Use Skill |
|---|---|
| Design a new page/component | 🎨 ui-ux-pro-max |
| Review UI quality | 🖌️ design-auditor |
| Write/run tests | 🧪 skills-testing-qa |
| Security audit codebase | 🔒 security-audit |
| Generate infra configs | ⚙️ cc-devops-skills (generators) |
| Validate infra configs | ⚙️ cc-devops-skills (validators) |
| Debug K8s cluster | ⚙️ cc-devops-skills (k8s-debug) |
Installation Sources
git:github.com/nextlevelbuilder/ui-ux-pro-max-skill
git:github.com/qajonatasmartins/skills-testing-qa
git:github.com/cloudflare/security-audit-skill
git:github.com/Ashutos1997/claude-design-auditor-skill
git:github.com/akin-ozer/cc-devops-skills