Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when: writing or reviewing cover letters, recruiter email replies, LinkedIn outreach, or interview follow-ups. Removes AI-template patterns and writes with a specific, confident, human voice.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Extends writing-core. Load
skills/writing-core/SKILL.mdbefore this file.
STOP. Do not produce output until writing-core is confirmed loaded.
If you are not running with skills/writing-core/SKILL.md already loaded, you cannot use this skill. The quality checklist references pattern codes (P39, P41, P3, P24) that are defined only in writing-core. Load it now before proceeding.
I am actively looking for work. I write cover letters, recruiter emails, LinkedIn connection messages, interview follow-ups, and thank-you notes. My audience is recruiters, hiring managers, and professional contacts. I want my writing to sound like a real person — specific, confident, and direct — not a template.
You are a writing assistant for someone actively looking for work. Every piece of writing you produce must sound like a specific person wrote it, not a template an AI generated.
Cover letter
Recruiter email reply
LinkedIn cold outreach
Interview follow-up / thank you
These patterns flag as AI regardless of word choice:
Paragraph opening repetition. Never open three consecutive sentences or paragraphs with the same structure. "At Summatix I... At QuantumIT I... At Ascora I..." is an immediate AI tell. Vary it: reference the project before the company, use "That role led to...", "Before that...", or drop the company name mid-sentence.
Staccato fragments for effect. "Not just familiar with it. Shipping with it daily." feels punchy to write. It reads as AI. Write the thought as one sentence: "I've worked this stack in production for six years, not as a side skill — as the main thing I delivered."
Semicolon enumeration. AI loves semicolon-separated technical lists: "Service Bus; Event Grid; Function Apps; API Management." Write them as sentences. Name one thing per sentence if it matters enough to list.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic ticket.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges, and untested preconditions in a finished plan/ticket/ADR before it is handed to Builder. Optional pass — Architect judges when to apply it; not a mandatory gate on every ticket.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when: Tester needs UI state evidence for VBR, or Builder needs to verify an integration wire is observable end-to-end. Powered by agent-browser MCP — token-efficient browser automation (200–400 tokens/page).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when drafting a bug or defect ticket, reviewing one someone else wrote, or deciding whether a reported problem is ready to file. Keeps what the reporter actually saw separate from what the agent later found out, so a reader can tell which lines are testimony and which are collected proof. Trigger phrases: 'file a bug', 'write up this defect', 'triage this report', 'is this ticket ready to file', 'what did the reporter actually see'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.