MagicKidd/Rokid-agentic-workflow

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Use when starting or resuming a non-trivial Codex/Cursor/Claude task, especially long-running design, coding, testing, handoff, or multi-agent work. Performs a lightweight new-session continuity check, finds or creates a task ledger, and prevents stale-file assumptions without forcing per-action checks.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Brainstorming design process. Must be used before any creative work - creating features, building components, adding functionality, or modifying behavior. Transforms ideas into complete designs and specifications through collaborative dialogue. Trigger words: brainstorm, design discussion, requirement analysis…

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Methodology-grade community and technology research tool. Use when you need to find existing solutions, architecture references, or best practices from the web, OSS communities, or technical forums. Trigger words: community research, best practices research, competitor research, "how are others doing it".

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

The Design-vs-Implementation Audit Copilot. A universal skill for any project, any language, any design document. Before work starts, it reminds engineers what must be delivered; after code lands, it checks what was actually delivered, what drifted, and what silently went beyond the design. Feed it a design doc plus a…

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Real-time scribe for design discussions. During multi-turn design sessions, create and continuously maintain a structured decision document; after every turn, incrementally update core conclusions, eliminate conflicts and stale content; at end of session, output a clean final record and run a missing-items check.…

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Install and refresh dynamic learned context in any repo (.agent-context, AGENTS.md, learned-conventions.mdc). Use for coding, architecture code design, tests, refactors, code review, and bug fixes.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Translate technical terms into plain, business-friendly language for non-engineers. Use when users ask "explain in plain language", "in human terms", "I'm not an engineer", or similar. Trigger words: plain language, layman explanation, translate jargon.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Launch expert collaboration mode, dividing complex tasks among multiple roles. Use when a task requires coordination of experts from multiple domains, each contributing specialized knowledge. Trigger words: expert collaboration, collaborate, multi-role cooperation.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Launch expert debate mode, letting two experts debate over disagreements for three rounds to unify a strategy. Use when there's a split in approaches, unclear paths, or blurred model boundaries. Trigger words: expert debate, debate, disagreement analysis.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Discover, install, and security-audit skills. Use when you need to find local skills, search for new ones, add third-party skills, or audit skill safety. Trigger words: find skills, search skills, install skill, add skill, skill security audit.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

MagicKidd/Rokid-agentic-workflow

Skill Claude Code

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Batch-screenshot HTML interactive prototype pages. Uses Playwright to open an HTML file, walk through pages, and save full-viewport screenshots. Fits Pencil design exports, HTML prototype documentation, UI page archival. Trigger words: screenshot HTML, prototype screenshots, batch capture pages.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Enter internalized cognition mode to gain deep first-person insights by "becoming" the system/product/concept/process being analyzed. Use when you need to understand the essence and inner logic beyond external analysis. Trigger words: internalized cognition, internalize, become the system, first-person analysis.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

For new-module development or cross-module refactors, enforce separation of scaffolding from deliverables so that "locally standalone runnable" and "low-cost mergeable into the trunk" hold simultaneously. Trigger words: mergeable, low-cost handoff, standalone run, scaffolding, deliverable layer, refactor merge.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Create structured developer documentation for a project. Use when starting a new project, taking over an existing one, or generating README / CLAUDE.md / developer guides. Trigger words: project documentation, dev guide, CLAUDE.md, project conventions, architecture docs.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

Prompt engineering techniques and patterns. Use when writing agent commands, hooks, skills, subagent prompts, or any LLM interaction: optimizing prompts, improving output reliability, and designing production-grade prompt templates. Trigger words: prompt engineering, prompt, prompt optimization, LLM interaction.

MagicKidd/Rokid-agentic-workflow

Skill Claude CodeCodex

A standard workflow for creating Git commits, which are saved snapshots of code changes. It checks the branch baseline, requires commit messages in Chinese, and excludes non-business planning files.