agent-rules
- NO MULTIPLE TOOL CALLS AT ONCE: Execute one tool at a time, wait for the result, then evaluate before proceeding. - Always output valid tool call XML structures immediately. - DO NOT wrap tool calls in preambles, pleasantries, or explanations.
Install / Use
npx skills add DevShaikh/cafe-posInstalls into whichever agent you are using.
.clinerules
Cline rules
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of agent-rules
agent-rules scores 62/100 on our quality scale, 4005th of 4,612 Development & Engineering skills we index.
Its .clinerules is 1.8 KB long, split into 5 sections and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
agent-rules compared with similar skills
All 4 of these similar skills score higher than agent-rules; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| agent-rules (this skill)by DevShaikh | 62 | 0 | — | .clinerules |
| taste-skillby Leonxlnx | 100 | 110.8k | 1d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 69.9k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 46.6k | 3d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 44d ago | SKILL.md |
Frequently asked questions
- How do I install agent-rules?
- Run
npx skills add DevShaikh/cafe-pos. The install tabs above show the steps for each supported agent. - Which AI agents does agent-rules work with?
- It is written for Cline, as a .clinerules file. Other agents that read the same format can often use it too.
- Is agent-rules safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is agent-rules still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubCafe POS Local Agent Rules (Qwen 9B @ 76K Context)
1. CRITICAL FORMATTING & TOOL CALLS
- NO MULTIPLE TOOL CALLS AT ONCE: Execute one tool at a time, wait for the result, then evaluate before proceeding.
- Always output valid tool call XML structures immediately.
- DO NOT wrap tool calls in preambles, pleasantries, or explanations.
- Keep responses strictly technical and concise to preserve token space.
- Never use placeholder comments like "// rest of code remains the same". Write out the complete, updated code block for changes.
2. TECH STACK BOUNDARIES
- Client: Next.js 16 (App Router), React 19, Tailwind CSS v4, shadcn/ui, Zustand, TanStack Query.
- Server: Node.js 22.12+, Express, TypeScript, Zod validation.
- Database: SQLite via Prisma 7 (Keep schemas strict).
- Desktop: Electron window orchestration.
3. CORE CODEBASE SAFETY LAWS
- EXACT MATCH: When editing a file, never rewrite the entire file from scratch unless authorized. Use search/replace blocks to modify only the necessary lines.
- ENFORCE TYPE SAFETY: Do not use 'any' types. Always extend or implement types from
client/src/types/orserver/src/schemas/. - MONOREPO FOCUS: When executing terminal commands or installing dependencies, always ensure you target the correct directory (
--prefix clientor--prefix server). - DB CHANGES: If modifying the Prisma schema, always generate a migration (
npm run db:migrate --prefix server) and update the seeds if necessary. - NO BROKEN HOOKS: Adhere strictly to React 19 rules. Do not update state inside a
useEffectlayout loop.
4. CONTEXT HUSBANDRY
- When utilizing search or grep tools, restrict scans to target sub-folders (
client/orserver/) instead of querying the repository root. - Ignore build artifacts,
node_modules,.next,dist, andelectron/outdirectories entirely when reading or editing code.
Related Skills
taste-skill
110.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
69.9kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
46.6kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
