본문으로 건너뛰기
cccskills
무료GitHub에 공개

proposal-drafter

Draft freelance proposals and profile bios using real job briefs, skills, and past projects. Connect relevant experience to a client’s needs, include supporting examples, and suggest a clear next step without inventing credentials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Draft a tailored freelance proposal or platform profile bio from a real job posting/brief and the freelancer's actual background. Use when responding to a listing on Contra/Upwork/etc, or writing/updating a freelance profile. Never invents experience, clients, or credentials that weren't provided.

설치 방법 보기

이럴 때 유용합니다

  • Draft a proposal for an Upwork or Contra listing
  • Update a freelance profile bio
  • Connect real project experience to a client brief
  • Tailor a profile to a target client type

포함된 파일(1)

  • SKILL.md2.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Proposal Drafter

Turns a job posting (or "write my profile bio") plus the freelancer's real background into a proposal or bio that sounds like it was written for this one client, not copy-pasted.

Required inputs before drafting

Ask for these if not already provided — never fabricate them:

  • The job posting or brief (or, for a profile bio, the platform and target client type)
  • The freelancer's real skills, tools, and years of relevant experience
  • 1-3 real past projects or outcomes (even informal ones — side projects count if true)
  • Any real portfolio links

If any of this is missing, ask before writing. A confident-sounding proposal built on invented credentials is a liability, not an asset.

Structure for a proposal (platform message, ~100-150 words)

  1. Opening line — restate the client's actual problem in your own words, proving you read the brief. Never open with "I am a passionate developer with X years of experience."
  2. 2-3 concrete connections — specific ways the freelancer's real background maps to this ask, not a resume dump.
  3. One relevant proof point — a real past project/outcome that's the closest match, in one sentence.
  4. Clear next step — propose a concrete first action (a question, a quick call, a scoped first milestone), not "let me know if interested."

Structure for a profile bio (longer, ~150-300 words)

  1. First line = the outcome you deliver, not a job title. ("I build automation that saves technical teams hours a week" beats "Full-stack developer.")
  2. Skill areas grouped by client-recognizable outcome, not tech jargon dumps.
  3. 1-2 real project highlights with a concrete result if known (time saved, bug fixed, feature shipped) — omit the metric if it isn't real, don't estimate one.
  4. Close with working style — availability, communication style, what kind of projects are the best fit.

Tone rules

  • Specific beats clever. Cut any sentence that could apply to any freelancer.
  • No unverifiable superlatives ("best-in-class", "world-class") — let the proof points carry the claim.
  • Active voice, short sentences. This is being read by someone deciding in under 30 seconds.

Part of a larger workflow

This skill is one piece of a 5-skill freelance workflow (proposal → scope-of-work → client update → invoice summary → project handoff), all built around the same rule: if the input doesn't have it, the output doesn't claim it. The other 4 are available as a paid bundle: Freelance Toolkit for Claude Code.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Finding or registering contacts
  • Adding or removing contact tags
  • Subscribing contacts to lists or unsubscribing them
davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Find angles for new ad copy
  • Plan creative tests using competitor ads
  • Choose a landing page message
davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding page-view and key-action tracking
  • Reviewing traffic and referral sources across projects
  • Finding where visitors drop out before signup or purchase
davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 20일 업데이트

davepoon의 스킬 모두 보기

이 스킬의 문제 신고