Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap
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。
This skill should be used when the user asks to "write a comment for this LinkedIn post", "help me respond to this post", "what should I comment on this", "craft a LinkedIn comment", or when Genesis identifies high-value posts in the user's network worth engaging with. Also triggered by "how should I engage on LinkedIn" or "help me be more visible on LinkedIn".
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。
Write LinkedIn comments that build genuine professional visibility — not generic "Great post!" noise. Every comment should demonstrate expertise, add value to the conversation, or make the author want to respond. Comments are the highest-ROI LinkedIn activity for building network presence.
Before writing comments, load the user's voice via voice-master's overlay resolution:
../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).social. Select social-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.
Comments follow the same voice rules as posts but in compressed form.
Extend the post's point with additional insight, a related experience, or a nuance the author didn't cover.
When to use: The post makes a good point that you can genuinely build on. Length: 2-4 sentences. Example pattern: "[Specific agreement with a detail]. In my experience with [specific context], [additional insight]. [Optional: question or implication]."
Disagree with or complicate the post's thesis — with reasoning, not contrarianism.
When to use: The post oversimplifies something or misses a key angle. Length: 3-5 sentences. Example pattern: "[Acknowledge the valid part]. Where I'd push back is [specific point] because [evidence/experience]. [What this changes about the conclusion]."
Contribute a relevant personal experience that illustrates or complicates the post's point.
When to use: The post resonates with something you've lived through. Length: 3-6 sentences. Example pattern: "[Brief connection to the post]. When I was [specific situation], [what happened]. [What you learned or how it relates]."
Ask a genuine question that advances the discussion. Not a rhetorical question for engagement — a question you'd actually want answered.
When to use: The post raises something you're genuinely curious about. Length: 1-3 sentences. Example pattern: "[What specifically triggered the question]. How do you think about [specific aspect]?"
Read the post — The user pastes or describes the post content.
Identify the angle — What's the most natural type of comment given the user's expertise and relationship to the topic?
Check relevance — Is this a post worth commenting on? Criteria:
Draft — Write the comment in voice. Short, specific, adds value.
Anti-slop check — Verify no banned patterns. Verify it references something specific from the post.
When the user asks for a general commenting strategy (not a specific comment):
Target authors: People in the user's target audience or industry who post regularly and engage with comments. Commenting consistently on 5-10 key authors builds more visibility than scattered commenting.
Timing: Comment within the first hour of a post going live. Early comments get more visibility as engagement grows.
Frequency: 3-5 meaningful comments per day is more effective than 15 generic ones. Quality signals expertise; quantity signals desperation.
Reciprocity: When someone comments on the user's posts, prioritize engaging with their content. Builds genuine relationships.
post_summary: <brief summary of the post being commented on>
comment_type: <add-value | challenge | experience | question>
comment: |
<the comment text>
rationale: |
<why this type and angle were chosen>
../voice-master/SKILL.md — Voice authority; follow its User Calibration Overlay section to load social exemplars from the user overlay../voice-master/references/anti-slop.md — Universal + Professional/LinkedIn anti-slop rules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。
概要と使いどころ
Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap
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。
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
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。
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.
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。
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 stops at the merge gate for the user's per-PR approval. Do NOT load it for building a feature and opening its PR — that is a build session (`genesis-development`).
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。
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.
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。
End-to-end content creation and publishing. Takes a topic (or generates one), drafts in the user's voice, gets approval via Telegram, and publishes to Medium via browser automation. Invoke with "publish a post about X", "write and publish to Medium", "content-publish", or when an ego-dispatched session needs to create and distribute content.
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。