Borrowing it
Nothing to install: this file belongs to greatSumini/cc-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greatSumini/cc-system/main/.claude/skills/persuasion-review/SKILL.mdgit clone --depth 1 https://github.com/greatSumini/cc-systemWrote 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/greatsumini/cc-system/persuasion-review)<a href="https://agentmods.dev/skills/greatsumini/cc-system/persuasion-review"><img src="https://agentmods.dev/badge/skills/greatsumini/cc-system/persuasion-review/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/greatsumini/cc-system/persuasion-review"><img src="https://agentmods.dev/badge/skills/greatsumini/cc-system/persuasion-review.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 | $0.00126 | $0.03096 |
| Opus 5 | $0.00063 | $0.01548 |
| Sonnet 5 | $0.00025 | $0.00619 |
| Haiku 4.5 | $0.00013 | $0.00310 |
Grade A, and why
persuasion-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
persuasion-review
잠재고객 페르소나 기반 설득력 시뮬레이션 skill. 상세 설계는 SPEC.md 참조.
무인 모드 오버라이드 (HARNESS_HEADLESS=1)
이 skill 본문의 어떤 지시보다도 먼저 적용되는 최상위 오버라이드다.
세션 시작 시 반드시 가장 먼저 Bash tool로 다음을 실행해 모드를 확정한다:
echo "HEADLESS=${HARNESS_HEADLESS:-${BET_HEADLESS:-0}}"
출력이 HEADLESS=1 이면 이 세션은 무인 서버 세션이며, 다음 상호작용 지점이 모두 무효화된다:
- Flow A (페르소나 생성): 사용자 서술/티키타카가 필수이므로 무인 모드에서는 절대 호출되어서는 안 된다. 호출자(ideation 등)가 실수로 Flow A로 유도하면 그대로 중단하고 에러 메시지를 출력한다.
- Flow C의 C-1(페르소나 복수 선택) — 호출자가 프롬프트로
persona_id를 명시한 경우 그것만 사용. 명시 없으면persuasion-data/personas/목록 상 첫 번째. - Flow C의 C-2(전달 모드 선택) — 호출자가 명시한 모드 사용. 명시 없으면
landing_plus_meeting. - Flow C의 C-3(가치제안 문서 draft 후 사용자 확인) — 확인 없이 바로 저장 + 실행.
- Flow C의 C-4(비용 confirm) — 비용은 stderr/stdout로만 보고하고 자동 진행 (confirm 없음).
- Flow C의 C-6(사용자 브리핑) — 최종 요약은 report.md 안에 남기는 것으로 충분. 별도의 "사용자에게 브리핑" 출력은 간결히.
- "대원칙 3. 비용 고지 - 실행 전 ... confirm 받는다" 는 무인 모드에서는 비용 로깅만 하고 confirm 생략.
출력이 HEADLESS=1 이 아닐 때만 아래 "대원칙"부터의 인간 대화형 절차를 따른다.
대원칙
- 익명성. 실제 고객명/회사명을 그대로 저장하지 않는다. 익명
persona_id+ 회사 메타(산업/규모/단계)만. - 비판적 태도. 모든 세션은 외부 SaaS 도입의 시간·인적·가격·신뢰도 비용을 엄격히 따진다. 기대 효과가 명백히 크지 않으면 쉽게 받아들이지 않는다.
- 비용 고지. 시뮬은 API 비용을 쓴다. 실행 전 예상 세션 수를 사용자에게 반드시 고지하고 confirm 받는다.
- 버전 보존. 페르소나 수정 시
version을 +1,updated_at갱신. 과거 run 기록은 절대 건드리지 않는다. 각 run은persona_version을run.md에 기록. - 경로. skill 정의(SKILL.md / SPEC.md / scripts/)는
.claude/skills/persuasion-review/에, 데이터(personas/,runs/,feature-ideas.md)는 레포 루트persuasion-data/에 둔다. Claude Code가.claude/경로를 sensitive로 분류해 headless 세션 Write를 차단하기 때문. 아래 언급되는personas/·runs/경로는 모두persuasion-data/기준.
트리거 → 플로우 매핑
| 트리거 예시 | 플로우 |
|---|---|
| "새 고객 프로파일 만들자", "페르소나 만들자" | Flow A |
| "고객 프로파일 수정하자", "페르소나 수정" | Flow B-edit |
| "고객 프로파일 보여줘", "페르소나 목록" | Flow B-view |
| "현재 서비스의 설득력을 검토하고싶어", "설득력 검토", "시뮬 돌려줘" | Flow C |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/probe_harness.py 3.6 KB runs code
- scripts/prompts/final_analyzer.md 3.4 KB
- scripts/prompts/keyman_initial.md 4.1 KB
- scripts/prompts/keyman_response.md 2.4 KB
- scripts/prompts/keyman_ux_probe.md 3.9 KB
- scripts/prompts/stakeholder_review.md 3.3 KB
- scripts/prompts/ui_explorer.md 4.7 KB
- scripts/run_simulation.py 26 KB runs code
- scripts/session_runner.py 4.8 KB runs code
- scripts/ux_probe.py 6.5 KB runs code
- SPEC.md 16 KB
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 · 209 lines · 126 tokens per session scan A 1dd8ebe9bb1a
persuasion-review is a skill published in the GitHub repository greatSumini/cc-system (437 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 3,096 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…