bkinsey808/ai-system
skills/ai-system/SKILL.md
Explain, update, or audit the repository's cross-tool AI system. Use when the user asks how Copilot, Claude, Codex, Antigravity, Cursor, Gemini, skills, custom agents, or tool adapters are organized. Do not use for ordinary code changes that only need domain-specific implementation guidance.
$ install --global
skillsauthnpx skillsauth add bkinsey808/songshare-effect ai-systemInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 11:41 PM22.8s1 file scanned
SKILL.md
- name:
- ai-system
- description:
- >
- user-invocable:
- true
AI System
Use When
- Explaining how the repo's AI guidance is organized.
- Deciding whether something belongs in
skills/,agents/,docs/ai/, or a tool-specific adapter. - Updating adapter files such as
.github/copilot-instructions.md,CLAUDE.md,GEMINI.md,.cursor/rules/*.mdc, or.agent/workflows/*.md. - Auditing whether multiple AI tools still point to the same shared source of truth.
- Clarifying which tools use shared
skills/or sharedagents/.
Execution Workflow
- Read
docs/ai/ai-system.mdfirst. - Check
AGENTS.mdanddocs/ai/rules.mdfor shared entry-point and rule changes. - Read only the tool-specific adapter files relevant to the request.
- Prefer updating shared layers before updating tool-specific adapters.
- When changing paths or AI-system docs, run the relevant AI-system validation commands.
Key Patterns
docs/ai/rules.mdis the canonical coding-rules reference.skills/*/SKILL.mdare shared cross-tool task guides.agents/*.agent.mdare shared cross-tool focused agent prompts and hooks..github/,.cursor/,CLAUDE.md,GEMINI.md, and.agent/workflows/are adapter or tool-specific layers, not the canonical rules layer.- Keep adapters thin: they should point back to shared files rather than duplicating large rule lists.
- Use
.agent/workflows/for Antigravity execution playbooks, not for general shared coding rules.
References
- Primary reference: docs/ai/ai-system.md
- Canonical rules: docs/ai/rules.md
- Repo entry point: AGENTS.md
- Skill authoring: skills/write-skill/SKILL.md
- Skill reference: docs/skill-best-practices.md
Do Not
- Do not duplicate the full AI-system document in the skill.
- Do not put long per-tool historical notes in the skill body; keep them in
docs/ai/ai-system.md. - Do not move shared coding rules into tool-specific adapter files.
- Do not assume every tool consumes
skills/andagents/in the same way; confirm against the current adapter files and AI-system doc.
Related Skills
bkinsey808/zustand-best-practices
tools
VerifiedTrustedCommunity
Zustand state management patterns for this project — store creation, selectors, Immer middleware, async actions with loading states, devtools, persist, and testing. Use when authoring or editing Zustand stores (use*Store files) or components that subscribe to stores. Do NOT use for React component structure or TypeScript-only utilities.
2SKILL.mdUpdated Apr 15, 2026
bkinsey808/write-skill
testing
VerifiedTrustedCommunity
How to write, update, or split skill files in this repo. Use when creating a new SKILL.md, updating an existing one, or deciding whether to put content in a skill vs. docs/.
2SKILL.mdUpdated Apr 15, 2026
bkinsey808/unit-test-hook-best-practices
development
VerifiedTrustedCommunity
Complete guide for testing React hooks — renderHook, Documentation by Harness, installStore, fixtures, subscription patterns, lint/compiler traps, and pre-completion checklist. Read docs/testing/unit-test-hook-best-practices.md for the full reference.
2SKILL.mdUpdated Apr 15, 2026
bkinsey808/unit-test-best-practices
development
VerifiedTrustedCommunity
Vitest unit test authoring for this repo — setup, mocking, API handler testing, and common pitfalls for non-hook code. Use when the user asks to add, update, fix, or review unit tests for utilities, components, API handlers, or scripts. Do NOT use for React hook tests — load unit-test-hook-best-practices instead.
2SKILL.mdUpdated Apr 15, 2026