Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add modu-ai/moai-cowork --skill ai-prompting-basicsgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modu-ai/moai-cowork/ai-prompting-basics)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/ai-prompting-basics"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/ai-prompting-basics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/ai-prompting-basics"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/ai-prompting-basics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.00915 |
| Opus 5 | $0.00037 | $0.00458 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
ai-prompting-basics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
ai-prompting-basics — 비개발자용 Claude 대화 가이드
cowork 플러그인 스킬 —
skills/카테고리만 사용 (commands/·agents/ 없음).
핵심 6원칙 (Claude 공식)
- 명확하고 직접적으로 — Claude를 '맥락 없는 똑똑한 새 동료'로 대해. 원하는 출력 형식·제약을 직접 명시. "도움말 만들어줘" (X) → "초보용 5단계 설치 도움말, 단계당 2문장, 이모지 1개" (O).
- 맥락·동기 추가 — 왜 중요한지 설명하면 Claude가 올바르게 일반화. "소리 내어 읽을 거니 줄임표 금지" > "줄임표 금지".
- 예시로 보여주기 (multishot) — 3–5개 잘 만든 예시가 형식·톤·구조를 가장 안정적으로 유도.
<example>태그로 감싸. 긍정 예시가 부정 지시보다 강하다. - XML 태그로 구조화 — 혼합 프롬프트는
<instructions>,<context>,<input>,<output_format>태그로 나누면 Claude가 헷갈리지 않음. - 역할 부여 — 시스템 프롬프트에 한 문장 역할("너는 10년 차 카피라이터야")로 톤·행동 집중.
- 긴 자료는 상단에 — 20k+ 토큰 입력은 데이터를 상단에, 질문·지시는 하단에 배치 (품질 ~30% 향상).
비개발자 실전 치트키
| 이런 요청은 | 이렇게 바꾸세요 |
|---|---|
| "글 써줘" | "50대 주부 대상 건강보험 블로그 글, 3문단, 핵심 혜택 1개" |
| "잘 만들어줘" (모호) | 원하는 형식의 예시 1개를 직접 보여주기 |
| "~하지 마" (부정) | "~하게 써" (긍정) — 부정 지시는 잘 안 지켜짐 |
| "더 좋게" (평가어) | 구체 기준("초등 5학년이 이해 가능하게, 문장당 25자 이내") |
자주 묻는 질문
Q: Claude가 너무 길게 써요 → 출력 형식 명시: "3문단, 문장당 25자 이내" 또는 "한 슬라이드당 핵심 1줄".
Q: 내 뉘앙스가 안 살아요 → 역할 + 예시 2–3개 제공. "이런 톤으로: [예시1] [예시2]".
Q: 거짓말(할루시네이션)해요 → "모르면 모른다고 해. 추측하지 마" + 확인 가능한 출처 요청.
참고
- Claude 공식 프롬프트 엔지니어링 가이드: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices
- 본 스킬은
/harness:plugin하네스(skill-builder)가 Claude 공식 문서 기반으로 생성한 cowork 플러그인 스킬입니다.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 50 lines · 75 tokens per session scan A e1cb712f7823
ai-prompting-basics is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 75 tokens to every session and 915 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
openrouter
OpenRouter API - Unified access to 400+ AI models through one API.
prompt-master
The one skill for prompting the Claude 5 models the way Anthropic says to. Starts by interviewing the user one question at a time, then writes a new prompt, rewrites an old one, or audits a whole CLAUDE.md, skill or project-instruction file, applying the rules from Anthropic's Opus 5 guide, Fable 5 guide, best…
revenantworks-foundation-promptwright
Builds, scores, hardens, and red-teams LLM prompts — from a rough idea to a copy-paste-ready artifact — and picks which model tier to run a prompt or task on. Trigger to write, fix, improve, debug, red-team, or rewrite a prompt, meta-prompt, template, or system prompt; to assemble parameters into a working prompt; for…
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.