claude-skills

Review any piece of content through a strict corporate HR lens, flagging offensive language, cultural insensitivity, stereotypes, exclusionary framing, cancel-risk phrasing, and other blindspots. Use this skill whenever the user asks to "HR check", "screen", "review for sensitivity", "check before I post", "is this okay to say", or pastes content and wants to know if it's safe. Also trigger when the user submits emails, social posts, blog drafts, scripts, or any written content and asks for feedback, a review, or a safety check — even if they don't use the words "HR" or "offensive". Err on the side of using this skill for any content review request.

Help the user brainstorm a topic in a structured, conversational way — like a really smart, honest friend. Use this skill whenever the user wants to think something through, explore an idea, work through a decision, or just talk something out. Trigger on phrases like "help me brainstorm", "I want to think through", "let's explore", "I'm trying to figure out", "help me think about", "I have an idea I want to explore", "can we brainstorm", or any time the user brings up a topic they seem to want to reason through together rather than just get a quick answer on. Prefer this skill even if the request is casual or vague — the skill is designed to handle ambiguity.

Turn any content into 3-4 finished LinkedIn posts ready to publish. Use this skill whenever the user shares something and wants LinkedIn posts from it — a PDF, an email, a newsletter, a URL, pasted text, a report, or anything else. Trigger on phrases like "turn this into posts", "what can I post about this", "LinkedIn content from this", "post ideas", "what should I post", or any time the user shares a piece of content and seems to want to repurpose it for LinkedIn.

Draft emails in the user's voice — direct, human, not generic — based on a voice profile and real samples they fill in below. Use this skill whenever the user asks to write, draft, reply to, or respond to an email; whenever they paste an email and ask how to handle it; and whenever they're working on outbound messages to clients, collaborators, or contacts. Use it even when they don't say "in my voice" — if they're drafting an email, this skill applies.

Fact-check any piece of written content — LinkedIn posts, emails, YouTube scripts, newsletters, or any draft text — by identifying factual claims and verifying them via web search. Returns a clear ✅/❌ claim-by-claim report with sources, suggested fixes, and a publishability rating. Trigger this skill whenever the user types /factcheck, pastes content and asks to fact-check it, asks to "verify", "check the facts", or "make sure this is accurate". Always present a clickable tier selector unless the user already specified a tier.

Search curated, trusted sources for installable agent skills that match what the user is trying to do, and return a short list of candidates with a one-line summary and link to each. Use this skill whenever the user asks to find, discover, look for, browse, or install skills — including phrasings like "is there a skill for X", "find me a skill that does Y", "what skills exist for Z", "I need a skill to handle W", or any time the user describes a repetitive task and wonders aloud whether a packaged skill exists. Also use when the user mentions a tool/workflow gap and is open to extending Claude. This skill only points at candidates — it does not install anything.

Instantly trim and tighten any content — emails, social posts, bullet points, paragraphs, or any text — while preserving the original meaning. Trigger immediately whenever the user types /hatchet, asks to "cut this down", "make this shorter", "trim this", "tighten this up", or pastes content with a request to reduce length. Don't ask clarifying questions — just cut and return the result.

Prepare a comprehensive pre-meeting briefing by pulling together everything you need to walk in ready. Use this skill whenever the user asks to "prep me for my meeting", "what do I have coming up", "brief me before my call", "meeting prep", "get me ready for [meeting name]", or any similar phrasing. Also trigger automatically when the user opens Claude and there is a meeting starting within the next 20–30 minutes — proactively offer the briefing without waiting to be asked. Covers upcoming calendar events, attendee email history, open action items, agenda/notes from the invite, and optional web context about attendees or their company.

Write LinkedIn posts in the user's voice — based on a voice profile they fill in below. Use this skill whenever the user asks to write, draft, or brainstorm a LinkedIn post, social post, or caption. Also use when they describe something that happened, share an observation, want to promote content, or say "help me post about this." Even if they don't say "LinkedIn" — if they're sharing something publicly, this skill applies.

Run the full publish-ready pipeline on source content — generate LinkedIn posts, fact-check them, tighten them, and HR-screen them — all in one shot, end-to-end. Trigger this skill whenever the user types /postready, says "make this publish-ready", "run the full pipeline", "give me final posts from this", or shares source material (PDF, email, newsletter, URL, pasted text) and signals they want finished, ready-to-publish posts rather than rough drafts.

Build a great prompt through a conversational interview. Use this skill whenever the user wants help writing, improving, or crafting a prompt — including phrases like "help me write a prompt", "I need a prompt for", "how do I prompt Claude to", "make me a prompt that", "I want to prompt an AI to", "create a prompt for", or any time the user describes a task they want an AI to do and seems to want help framing it. Even if they just describe a task vaguely and seem unsure how to ask for it — this skill applies. Trigger it early and often.

Search YouTube intelligently for the best video on any topic. Use this skill whenever the user wants to find YouTube videos, search for tutorials, watch something, or discover content on a topic — even if they just say "find me a video about X" or "look up X on YouTube." Runs multiple searches, interprets the user's intent, and returns one clear recommendation plus a few alternatives.