本文へ移動
cccskills
無料GitHub で公開

job-seeker

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.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md5.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Job Seeker — Voice Skill

Extends writing-core. Load skills/writing-core/SKILL.md before this file.


REQUIRED GATE: Load writing-core First

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.


Profile

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.


Instructions

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.

Voice

  • Confident without arrogance. State what you did and why it matters — do not hedge.
  • Warm but professional. You are talking to a person, not addressing a selection panel.
  • Specific always. Name the company, the role, the technology, the outcome. Vague claims lose.
  • Direct. Lead with the most relevant thing. Do not warm up the reader before making your point.
  • Active voice. Name who does what. "I built X" not "X was built" or "the role involved building X".

Document rules

Cover letter

  • Salutation: use first name when you have a direct contact ("Dear Neeta,"), formal surname when you don't ("Dear Ms. Sharma,"). Never full name — "Dear Neeta J Sharma," is an AI tell. "Dear Hiring Manager," only when no name is available.
  • First sentence: the most relevant thing about you for this role. Not "I am writing to apply for..."
  • Second paragraph: one specific achievement with a real outcome ("reduced deployment time from 3 days to 4 hours", not "improved efficiency")
  • Third paragraph: why this company, this role — something specific you researched, not "I admire your values"
  • Close: one clear sentence. Not "I look forward to hearing from you at your earliest convenience"
  • Length: 3–4 paragraphs maximum

Recruiter email reply

  • Match their energy — brief if they were brief
  • Answer what they asked, then add one specific detail about your background relevant to the role
  • No throat-clearing ("Thank you so much for reaching out, I really appreciate...")
  • End with a clear next step or question

LinkedIn cold outreach

  • Three sentences maximum
  • Sentence 1: specific reason you're reaching out (not "I came across your profile")
  • Sentence 2: one relevant thing about yourself
  • Sentence 3: a low-friction ask ("Would you be open to a brief chat?" not "I would love to pick your brain")

Interview follow-up / thank you

  • Reference something specific from the conversation — a problem discussed, a question they asked
  • One sentence on why you're more interested after the conversation, not less
  • No generic closing ("I remain enthusiastic about the opportunity")

Structural tells

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.

Banned phrases

  • "I am passionate about..."
  • "I am excited to apply for..."
  • "I would love the opportunity to..."
  • "Thank you so much for your time"
  • "I look forward to hearing from you at your earliest convenience"
  • "Results-driven professional"
  • "Strong communication skills"
  • "Team player"
  • "Leveraging my experience in..."
  • "I am a perfect fit for this role"
  • "Please find attached my resume"
  • "Do not hesitate to contact me"

Quality check before output

  • Does the first sentence earn the reader's attention?
  • Is there at least one specific, verifiable achievement or detail?
  • Does it sound like this person, or like any applicant?
  • Is it the right length for the document type?
  • Are all banned phrases removed?
  • Do any three consecutive sentences or paragraphs open with the same structure?
  • Are there any staccato dramatic fragments ("Not just X. Y.")?
  • Are there semicolon-enumerated technical lists?
  • Does any paragraph end with a "whether X or Y" summary sentence? (P39)
  • Are there any infomercial hooks as solo paragraphs ("The catch?", "Here's the thing:")? (P41)
  • Are there any -ing phrase tails on sentences ("...ensuring reliability, fostering growth")? (P3)
  • Does the piece end on a generic positive conclusion? (P24)

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

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).

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

Writing skill for freelancers and independent consultants. Covers project proposals, bids, client emails, and scope summaries. Leads with the client's problem, not the consultant's background.

日本語の概要は準備中です。原文の説明を表示しています。

Agistra/agistra.dev52026年10月7日 更新

Agistra のスキルをすべて見る

このスキルの問題を報告する