원클릭으로 Manus에서 모든 스킬 실행

setup

스타2

포크0

업데이트2026년 5월 1일 11:18

First-time setup for this kit. Setup is an interactive bash script (setup.sh) that runs in the user's terminal -- not a conversational skill. Use this skill when the user asks "/setup", says they just cloned the kit, asks how to get connected, or wants to set up MCP / statusline. Tell them to exit Claude Code and run `bash setup.sh` from the kit root.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

RelevanceAI

RelevanceAI/relevance-builder-kit

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

What to do when this skill is invoked

Setup is now a self-contained interactive bash script -- not a conversational walkthrough. It handles prerequisites, MCP config, folder + server suffix, statusline toggles, the optional ccd alias, an optional first build folder, and verification, all in one terminal session.

Tell the user (verbatim or close to it):

Setup runs as a single interactive bash script in your terminal. Exit Claude Code, then from the kit root run:
bash setup.sh
It walks through prerequisites, folder + MCP server naming, the statusline, an optional ccd alias, an optional first build folder, and a verification pass. Idempotent -- safe to re-run any time.

When it finishes, it tells you to start Claude Code in the (possibly renamed) folder and run /mcp to authenticate via OAuth.

That's it. Do not try to walk the user through setup conversationally inside Claude Code -- the bash script is the single source of truth so the flow stays synced and the user doesn't context-switch between terminal and chat.

Why bash, not a conversational skill

Earlier versions of /setup ran each step as a back-and-forth in chat, which (a) forced the user to bounce between terminal and Claude Code (closing/reopening for the folder rename, sourcing rc files), and (b) drifted out of sync with setup.sh. The bash flow keeps everything in one terminal session and survives the folder rename without tearing down the Claude Code session.

What setup.sh does

Prerequisites -- python3, git, claude CLI checks
MCP config -- verifies .mcp.json points to mcp.relevanceai.com (restores from git if missing)
Folder + server suffix -- prompts for a suffix (e.g. dev, prod, team), renames folder to relevance-builder-kit-{suffix} and MCP server to relevance-ai-kit-{suffix}
Statusline -- offers [a]ll on / [n]one / [c]ustomise mode; writes .claude/statusline.conf
ccd alias -- optional, appends to ~/.zshrc or ~/.bashrc
First build folder -- optional scaffold of builds/{name}/ with starter agent.md + system-prompt.md
Verification -- runs scripts/verify-setup.sh

After it finishes, the user runs /mcp inside Claude Code to do the OAuth login.

Edge cases

Folder rename: the script renames the folder mid-run. The shell that invoked the script keeps running fine (script cds into the new path), but the user's outer shell prompt is stale -- the final message tells them to cd to the new path. Any other terminals open in the old path should be closed.
OAuth re-auth: if MCP tools stop working later, run /mcp again. Not a setup concern.
Recovering the statusline settings.json entry: if someone hand-edits .claude/settings.json and removes the statusLine block, run bash scripts/setup-statusline.sh to re-wire just that entry. The conf toggles still come from setup.sh.

이 저장소의 다른 Skills

같은 저장소

eval

RelevanceAI/relevance-builder-kit

Auto-generate test cases and run platform evals on a Relevance AI agent. Covers golden sets, quick smoke tests, publish gates, and ongoing performance monitoring of production conversations. Use when the user says "test this agent", "evaluate this agent", "set up evals", "run an eval", "create test cases", "set a publish gate", "add a golden set", "monitor production quality", or asks how to validate before going live. Quick mode (3 cases, auto-fix loop) for after-change smoke tests; Full mode (5-8 cases, user-reviewed) before launch or major redesign.

2026-05-042

template-agent

RelevanceAI/relevance-builder-kit

Design and build a clean starter agent for any new use case. Use this skill when starting a new build, when someone asks "how should I build my first agent for X?", "what goes in a v1 agent?", "how do I avoid ending up with a generic stock-template-looking agent?", or when sanity-checking before shipping. Covers the 12-point design rubric, architecture layers (variables vs knowledge tables vs tools vs placeholders), the v0 to vN roadmap pattern, build-fresh-not-fork principle, system prompt anti-patterns, tool selection rules, smoke test via async pattern. Pairs with `/agent-build-patterns` for general design philosophy.

2026-05-042

agent-optimiser

RelevanceAI/relevance-builder-kit

Diagnose a Relevance AI agent or workforce for config, prompt, tool, and credit-spend issues, then recommend ranked optimizations with concrete prompt rewrites and credit-saving estimates. Use when the user says "optimise this agent", "audit this workforce", "review this agent's prompt", "find waste in this build", "why is my agent slow / expensive / unreliable?", "the agent is using too many credits", or asks for a health check on an existing build. Reads platform state via native MCP tools (no writes without permission); works on any connected project.

2026-05-042

agent-build-patterns

RelevanceAI/relevance-builder-kit

Design philosophy, architecture patterns, and decision guides for production-grade Relevance AI builds. Use this skill when designing a new agent or tool, reviewing existing architecture, debugging production failures, deciding where logic should live (code vs LLM vs knowledge table), structuring multi-agent workforces, eliminating duplicated tools, adding audit trails, or when someone asks "is this the right pattern?" or "why is my agent doing X wrong?". Covers Unit of Action, Note Step, Centralize Rules, Code Over LLM, Parameterize, Compute at Right Level, Data Over Routing, and Audit Enrichment patterns.

2026-05-042

capture-learning

RelevanceAI/relevance-builder-kit

Review a build or debug session, extract reusable learnings, and update the knowledge base or share with the wider community via PR. Use this skill at end of session, when the user says "what did I learn", "save this pattern", "document this discovery", "let's do a retro", "capture this before I forget", "update the knowledge base", or "share this back". Also use when someone wants to graduate a discovery into BUILD_PRACTICES.md, PLATFORM_MECHANICS.md, or agent-build-patterns.

2026-05-042

improve

RelevanceAI/relevance-builder-kit

Capture a single mid-flow insight as a well-scoped repo PR. Highly opinionated - refuses ~half of invocations on a substance bar (actually happened, non-obvious, clear canonical home, no contradictions, in scope, reusable). Use when the user says `/improve`, says `go` immediately after Claude surfaced an "Improvement spotted" line, or says "capture this and PR", "raise this improvement", "PR this learning", "improve the kit with this". Do NOT use for end-of-session retros (use /capture-learning) or build-specific docs (edit builds/{build-name}/...).

2026-05-042

name	setup
description	First-time setup for this kit. Setup is an interactive bash script (setup.sh) that runs in the user's terminal -- not a conversational skill. Use this skill when the user asks "/setup", says they just cloned the kit, asks how to get connected, or wants to set up MCP / statusline. Tell them to exit Claude Code and run `bash setup.sh` from the kit root.

What to do when this skill is invoked

Tell the user (verbatim or close to it):

Setup runs as a single interactive bash script in your terminal. Exit Claude Code, then from the kit root run:
bash setup.sh
It walks through prerequisites, folder + MCP server naming, the statusline, an optional ccd alias, an optional first build folder, and a verification pass. Idempotent -- safe to re-run any time.

When it finishes, it tells you to start Claude Code in the (possibly renamed) folder and run /mcp to authenticate via OAuth.

Why bash, not a conversational skill

What setup.sh does

Prerequisites -- python3, git, claude CLI checks
MCP config -- verifies .mcp.json points to mcp.relevanceai.com (restores from git if missing)
Folder + server suffix -- prompts for a suffix (e.g. dev, prod, team), renames folder to relevance-builder-kit-{suffix} and MCP server to relevance-ai-kit-{suffix}
Statusline -- offers [a]ll on / [n]one / [c]ustomise mode; writes .claude/statusline.conf
ccd alias -- optional, appends to ~/.zshrc or ~/.bashrc
First build folder -- optional scaffold of builds/{name}/ with starter agent.md + system-prompt.md
Verification -- runs scripts/verify-setup.sh

After it finishes, the user runs /mcp inside Claude Code to do the OAuth login.

Edge cases

Folder rename: the script renames the folder mid-run. The shell that invoked the script keeps running fine (script cds into the new path), but the user's outer shell prompt is stale -- the final message tells them to cd to the new path. Any other terminals open in the old path should be closed.
OAuth re-auth: if MCP tools stop working later, run /mcp again. Not a setup concern.
Recovering the statusline settings.json entry: if someone hand-edits .claude/settings.json and removes the statusLine block, run bash scripts/setup-statusline.sh to re-wire just that entry. The conf toggles still come from setup.sh.