Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "write a LinkedIn message", "draft a connection request", "help me reach out to someone on LinkedIn", "write an InMail", "message this person", or when the prospect-researcher skill identifies a high-value contact worth reaching out to. Also triggered by "how should I approach [person/company]" in a LinkedIn context.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Write personalized LinkedIn messages — connection requests, InMails, and follow-up messages — that get responses instead of being ignored. Every message must demonstrate genuine relevance: why THIS person, why NOW, why the user is worth responding to.
Load the user's voice via voice-master's overlay resolution before drafting:
../voice-master/SKILL.md and follow its User Calibration
Overlay section to load exemplars and voice-dimensions from the
out-of-repo overlay (or template fallback with warning if no overlay).professional. Select professional-medium
exemplars from whatever voice-master loads.../voice-master/references/anti-slop.md — apply the Universal
and Professional / LinkedIn sections.If no overlay is present, voice-master falls back to generic voice guidance and warns — note this in your output.
DMs are the most personal LinkedIn format — sounding templated here is fatal. One bad outreach message can permanently close a door.
The hardest format. 300 characters to establish relevance and earn a click.
Rules:
Structure: "[Specific reference to them or their work]. [Why connecting makes sense for both sides — in one sentence]."
Sent after a connection request is accepted, or to an existing connection.
Rules:
Structure:
If the first message got no response after 5-7 days.
Rules:
Asking a mutual connection to introduce you to someone.
Rules:
Before drafting any outreach, gather intelligence on the recipient:
If the prospect-researcher skill has already run on this target, use
its findings. If not, perform lightweight research before writing.
Goal: Get a conversation about opportunities. Approach: Lead with what you can do for them, not what you want. Reference specific challenges their company/team faces. Ask about the team or the work, not about open positions directly.
Goal: Start a relationship that could lead to business. Approach: Never pitch in the first message. Offer genuine value first (insight, introduction, resource). Build rapport before discussing services. The goal is a conversation, not a sale.
Goal: Build a genuine professional relationship. Approach: Reference specific shared interests or complementary expertise. Suggest a concrete (low-commitment) next step — a specific article exchange, a brief call, a shared event.
Goal: Attract a candidate. Approach: Lead with why you noticed THEM specifically (not "we have an exciting opportunity"). Be transparent about the role and company. Respect that they may not be looking.
recipient: <name and context>
message_type: <connection_request | first_message | follow_up | intro_request>
scenario: <job_search | client_acquisition | networking | recruiting>
research_used: |
<key findings about the recipient that informed the message>
message: |
<the message text>
character_count: <for connection requests — must be under 300>
rationale: |
<why this approach and angle>
../voice-master/SKILL.md — Voice authority; follow its User Calibration Overlay section to load professional exemplars from the user overlay../voice-master/references/anti-slop.md — Universal + Professional/LinkedIn anti-slop rules../prospect-researcher/SKILL.md — Deep research on outreach targets还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap
中文简介正在准备中。当前显示原文说明。
Canonical guide to Genesis browser automation - layers (Camoufox, Chromium, the user's Chrome over CDP, TinyFish, desktop), per-tool timeouts, safety gates, verify-after-act, what a click checks (scroll, hit test, covered targets), overlays, iframes, tabs, and failure diagnosis
中文简介正在准备中。当前显示原文说明。
This skill should be used when a session BUILDS one Genesis item: implementing a change in a worktree through to opening its PR, including rework from a send-back spec. Load `genesis-development` (the shared core) first. Do NOT load it for driving open PRs to merge (`closing-session`), post-merge verification (`validating-merges`), or specifying a change before it is planned (`spec-session`).
中文简介正在准备中。当前显示原文说明。
Update Claude Code (the CC CLI / "clog code") to a new version, or bump the pinned CC version. Use when the user asks to update Claude Code, bump the CC pin, evaluate a new CC release, or says "clog code update". Routes to the canonical, standardized process in docs/reference/cc-compatibility.md — do NOT re-derive the update mechanism by grepping every time. Do NOT use for general "what changed in CC" trivia with no intent to update.
中文简介正在准备中。当前显示原文说明。
This skill should be used when a session's job is to DRIVE OPEN PRs TO MERGE rather than to write new code — "close out the open PRs", "review and fix the open PRs", "what's blocking our PRs", "which PRs are mergeable". It owns the In Review column: it reads each PR's gate status, verifies and fixes review findings on PRs OTHER sessions built, replies in-thread, and merges a PR only under the owner's authorization: a per-PR yes, or the owner's request for closing work covering a PR whose every gate passes. Do NOT load it for building a feature and opening its PR — that is a build session (`build-session`).
中文简介正在准备中。当前显示原文说明。
Code understanding tool selection. Use when exploring architecture, finding definitions, tracing call chains, assessing blast radius of changes, or debugging code paths in the Genesis codebase.
中文简介正在准备中。当前显示原文说明。