[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737J7MA1AMEMW6TS3F3S4HB":3,"skill-same:01M737J7MA1AMEMW6TS3F3S4HB":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M737J7MA1AMEMW6TS3F3S4HB","sourcing-outreach",null,"When the user needs to write recruiting outreach messages to attract passive candidates or request referrals.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fstartup--sourcing-outreach\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: sourcing-outreach\ndescription: When the user needs to write recruiting outreach messages to attract passive candidates or request referrals.\nrelated: [job-description, interview-kit]\nreads: [startup-context]\norigin: \"startup\"\n---\n\n# Sourcing Outreach\n\n## When to Use\nActivate when the user asks to write cold outreach to potential candidates (LinkedIn InMails, cold emails), craft referral request messages, build a multi-touch follow-up sequence, or improve response rates on existing recruiting outreach. Also activate when the user is sourcing for a specific role and needs help personalizing messages at scale.\n\n## Context Required\n- **From startup-context:** Company name, one-line mission, stage\u002Ffunding, notable investors or customers, recent milestones, and team size.\n- **From user:** Role being hired for, the candidate's name and background (LinkedIn profile, blog posts, talks, open-source work), what specifically drew the user to this candidate, and the communication channel (LinkedIn, email, Twitter DM).\n\n## Workflow\n1. **Research the candidate** — Review the candidate details provided by the user. Identify 1-2 specific, genuine connection points: a project they shipped, a talk they gave, an open-source contribution, a blog post, or a career pattern that signals fit.\n2. **Choose the outreach template** — Select from: cold LinkedIn InMail, cold email, warm intro request, referral ask, or follow-up. Each has different length and tone constraints.\n3. **Draft the message** — Write a short, personalized message using the PRC framework (see below). Keep LinkedIn InMails under 300 characters for the preview. Keep cold emails under 150 words.\n4. **Add a clear, low-friction CTA** — The ask should be small: a 15-minute call, a reply with interest level, or permission to send more details. Never ask for a resume or formal application in cold outreach.\n5. **Build the follow-up sequence** — Draft 2-3 follow-ups spaced 4-7 days apart. Each follow-up adds new information (a company milestone, a team blog post, a relevant data point) rather than just \"bumping\" the thread.\n6. **Review for tone** — Ensure the message sounds human, not templated. Check that personalization is specific enough that it could only apply to this candidate.\n\n## Output Format\n- A primary outreach message (ready to send)\n- 2-3 follow-up messages with suggested send timing\n- Notes on personalization elements used and why they were chosen\n\n## Frameworks & Best Practices\n\n### The PRC Framework\nEvery outreach message should contain three elements in roughly this order:\n- **Personalization (P):** A specific, genuine observation about the candidate's work that shows you did your homework. Not \"I saw your impressive profile\" — something like \"Your talk on event sourcing at StrangeLoop changed how I think about our own data pipeline.\"\n- **Relevance (R):** Why this role connects to their career trajectory. Bridge from what they've done to what they'd do at your company.\n- **Call-to-action (C):** A single, low-commitment ask. \"Would you be open to a 15-minute call this week?\" is better than \"Apply at our careers page.\"\n\n### Channel-Specific Guidelines\n\n**LinkedIn InMail:**\n- Subject line matters more than body — keep it intriguing and specific (e.g., \"Your Kafka work + our real-time pipeline\" not \"Exciting opportunity\").\n- InMail preview shows ~300 characters. Front-load the personalization.\n- Do not connect-and-pitch simultaneously. Either send an InMail or send a connection request with a note — not both at once.\n\n**Cold Email:**\n- Subject: Short, specific, no clickbait. \"Quick question about [their project]\" or \"[Mutual connection] suggested I reach out.\"\n- Keep body under 150 words. Three short paragraphs max.\n- Plain text outperforms HTML templates. No logos, no signatures with 10 links.\n- Send from a real person's email (founder@, not recruiting@).\n\n**Warm Intro \u002F Referral Request:**\n- Make it easy for the connector: provide a forwardable blurb they can send with zero editing.\n- Include context on why you think the candidate is a fit so the connector can vouch meaningfully.\n- Always give the connector an out: \"No pressure at all if this doesn't feel right.\"\n\n### Personalization Research Checklist\nBefore writing, look for:\n- [ ] Recent talks, podcast appearances, or conference presentations\n- [ ] Blog posts or technical writing\n- [ ] Open-source contributions (GitHub, GitLab)\n- [ ] Career trajectory patterns (e.g., \"you've gone deep on infrastructure at two companies in a row\")\n- [ ] Mutual connections or shared communities\n- [ ] Company or product they built that you genuinely admire\n\n### Follow-Up Sequence Design\n- **Follow-up 1 (Day 4-5):** Add a new piece of information — a recent company milestone, a blog post from the team, or a specific project they'd work on. Keep it to 2-3 sentences.\n- **Follow-up 2 (Day 9-11):** Try a different angle. If the first message was about the role, this one could be about the team or a technical challenge. Ask a question rather than making a pitch.\n- **Follow-up 3 (Day 16-20):** A graceful close. \"I don't want to crowd your inbox — just wanted to leave the door open. If timing is ever better, I'd love to chat.\" This gets surprisingly high response rates.\n- **Never send more than 3 follow-ups** to a candidate who hasn't responded.\n\n### Anti-Patterns to Avoid\n- **Spray and pray:** Sending identical messages to 200 people. Response rates plummet below 5%. Batch personalization into tiers instead.\n- **The humble brag opener:** \"We just raised $50M from Sequoia\" as your first sentence. Lead with the candidate, not yourself.\n- **Fake personalization:** \"I was really impressed by your background\" is worse than no personalization because it signals a template.\n- **Overselling:** Don't describe the role as \"once in a lifetime.\" Be honest and specific about what makes it compelling.\n- **Asking for too much:** \"Please send your resume and three references\" in a cold message guarantees no reply.\n\n## Related Skills\n- `job-description` — The JD provides the source material for what makes the role compelling in outreach.\n- `interview-kit` — Mention the candidate-friendly interview process in outreach to reduce friction.\n\n## Examples\n\n**Prompt:** \"Write a cold LinkedIn InMail for a senior ML engineer. She gave a talk at NeurIPS on efficient fine-tuning and currently works at Stripe.\"\n\n**Good output snippet:**\n```\nSubject: Your NeurIPS talk on efficient fine-tuning\n\nHi [Name],\n\nYour NeurIPS presentation on LoRA variants for production models stuck\nwith me — especially the bit about keeping inference costs flat while\nscaling model complexity. We're solving a similar problem at [Company]:\nbuilding real-time ML models for [use case] and need someone who thinks\nabout efficiency as a first-class constraint.\n\nWe're 18 people, Series A, and this would be our second ML hire. You'd\nown the model architecture end to end.\n\nWould you be open to a 15-minute call to see if there's a fit?\n\n— [Your name]\n```\n\n**Prompt:** \"Write a referral request email I can send to a mutual connection.\"\n\n**Good output snippet:**\n```\nSubject: Quick ask — know anyone strong in product design?\n\nHi [Connector],\n\nWe're hiring our first product designer at [Company] and I thought of\nyou since you work with strong designers regularly. Here's what we're\nlooking for: [1-2 sentences on the role].\n\nIf anyone comes to mind, I'd be grateful for an intro. Here's a\nforwardable blurb:\n\n---\n\"[Your name] is the CEO of [Company] ([one-liner]). They're hiring a\nfounding product designer to own the end-to-end user experience. The\nteam is 14 people, Series A, remote-first. Here's the JD: [link]\"\n---\n\nNo pressure at all — and thanks either way.\n\n[Your name]\n```\n","# Sourcing Outreach\n\n## When to Use\nActivate when the user asks to write cold outreach to potential candidates (LinkedIn InMails, cold emails), craft referral request messages, build a multi-touch follow-up sequence, or improve response rates on existing recruiting outreach. Also activate when the user is sourcing for a specific role and needs help personalizing messages at scale.\n\n## Context Required\n- **From startup-context:** Company name, one-line mission, stage\u002Ffunding, notable investors or customers, recent milestones, and team size.\n- **From user:** Role being hired for, the candidate's name and background (LinkedIn profile, blog posts, talks, open-source work), what specifically drew the user to this candidate, and the communication channel (LinkedIn, email, Twitter DM).\n\n## Workflow\n1. **Research the candidate** — Review the candidate details provided by the user. Identify 1-2 specific, genuine connection points: a project they shipped, a talk they gave, an open-source contribution, a blog post, or a career pattern that signals fit.\n2. **Choose the outreach template** — Select from: cold LinkedIn InMail, cold email, warm intro request, referral ask, or follow-up. Each has different length and tone constraints.\n3. **Draft the message** — Write a short, personalized message using the PRC framework (see below). Keep LinkedIn InMails under 300 characters for the preview. Keep cold emails under 150 words.\n4. **Add a clear, low-friction CTA** — The ask should be small: a 15-minute call, a reply with interest level, or permission to send more details. Never ask for a resume or formal application in cold outreach.\n5. **Build the follow-up sequence** — Draft 2-3 follow-ups spaced 4-7 days apart. Each follow-up adds new information (a company milestone, a team blog post, a relevant data point) rather than just \"bumping\" the thread.\n6. **Review for tone** — Ensure the message sounds human, not templated. Check that personalization is specific enough that it could only apply to this candidate.\n\n## Output Format\n- A primary outreach message (ready to send)\n- 2-3 follow-up messages with suggested send timing\n- Notes on personalization elements used and why they were chosen\n\n## Frameworks & Best Practices\n\n### The PRC Framework\nEvery outreach message should contain three elements in roughly this order:\n- **Personalization (P):** A specific, genuine observation about the candidate's work that shows you did your homework. Not \"I saw your impressive profile\" — something like \"Your talk on event sourcing at StrangeLoop changed how I think about our own data pipeline.\"\n- **Relevance (R):** Why this role connects to their career trajectory. Bridge from what they've done to what they'd do at your company.\n- **Call-to-action (C):** A single, low-commitment ask. \"Would you be open to a 15-minute call this week?\" is better than \"Apply at our careers page.\"\n\n### Channel-Specific Guidelines\n\n**LinkedIn InMail:**\n- Subject line matters more than body — keep it intriguing and specific (e.g., \"Your Kafka work + our real-time pipeline\" not \"Exciting opportunity\").\n- InMail preview shows ~300 characters. Front-load the personalization.\n- Do not connect-and-pitch simultaneously. Either send an InMail or send a connection request with a note — not both at once.\n\n**Cold Email:**\n- Subject: Short, specific, no clickbait. \"Quick question about [their project]\" or \"[Mutual connection] suggested I reach out.\"\n- Keep body under 150 words. Three short paragraphs max.\n- Plain text outperforms HTML templates. No logos, no signatures with 10 links.\n- Send from a real person's email (founder@, not recruiting@).\n\n**Warm Intro \u002F Referral Request:**\n- Make it easy for the connector: provide a forwardable blurb they can send with zero editing.\n- Include context on why you think the candidate is a fit so the connector can vouch meaningfully.\n- Always give the connector an out: \"No pressure at all if this doesn't feel right.\"\n\n### Personalization Research Checklist\nBefore writing, look for:\n- [ ] Recent talks, podcast appearances, or conference presentations\n- [ ] Blog posts or technical writing\n- [ ] Open-source contributions (GitHub, GitLab)\n- [ ] Career trajectory patterns (e.g., \"you've gone deep on infrastructure at two companies in a row\")\n- [ ] Mutual connections or shared communities\n- [ ] Company or product they built that you genuinely admire\n\n### Follow-Up Sequence Design\n- **Follow-up 1 (Day 4-5):** Add a new piece of information — a recent company milestone, a blog post from the team, or a specific project they'd work on. Keep it to 2-3 sentences.\n- **Follow-up 2 (Day 9-11):** Try a different angle. If the first message was about the role, this one could be about the team or a technical challenge. Ask a question rather than making a pitch.\n- **Follow-up 3 (Day 16-20):** A graceful close. \"I don't want to crowd your inbox — just wanted to leave the door open. If timing is ever better, I'd love to chat.\" This gets surprisingly high response rates.\n- **Never send more than 3 follow-ups** to a candidate who hasn't responded.\n\n### Anti-Patterns to Avoid\n- **Spray and pray:** Sending identical messages to 200 people. Response rates plummet below 5%. Batch personalization into tiers instead.\n- **The humble brag opener:** \"We just raised $50M from Sequoia\" as your first sentence. Lead with the candidate, not yourself.\n- **Fake personalization:** \"I was really impressed by your background\" is worse than no personalization because it signals a template.\n- **Overselling:** Don't describe the role as \"once in a lifetime.\" Be honest and specific about what makes it compelling.\n- **Asking for too much:** \"Please send your resume and three references\" in a cold message guarantees no reply.\n\n## Related Skills\n- `job-description` — The JD provides the source material for what makes the role compelling in outreach.\n- `interview-kit` — Mention the candidate-friendly interview process in outreach to reduce friction.\n\n## Examples\n\n**Prompt:** \"Write a cold LinkedIn InMail for a senior ML engineer. She gave a talk at NeurIPS on efficient fine-tuning and currently works at Stripe.\"\n\n**Good output snippet:**\n```\nSubject: Your NeurIPS talk on efficient fine-tuning\n\nHi [Name],\n\nYour NeurIPS presentation on LoRA variants for production models stuck\nwith me — especially the bit about keeping inference costs flat while\nscaling model complexity. We're solving a similar problem at [Company]:\nbuilding real-time ML models for [use case] and need someone who thinks\nabout efficiency as a first-class constraint.\n\nWe're 18 people, Series A, and this would be our second ML hire. You'd\nown the model architecture end to end.\n\nWould you be open to a 15-minute call to see if there's a fit?\n\n— [Your name]\n```\n\n**Prompt:** \"Write a referral request email I can send to a mutual connection.\"\n\n**Good output snippet:**\n```\nSubject: Quick ask — know anyone strong in product design?\n\nHi [Connector],\n\nWe're hiring our first product designer at [Company] and I thought of\nyou since you work with strong designers regularly. Here's what we're\nlooking for: [1-2 sentences on the role].\n\nIf anyone comes to mind, I'd be grateful for an intro. Here's a\nforwardable blurb:\n\n---\n\"[Your name] is the CEO of [Company] ([one-liner]). They're hiring a\nfounding product designer to own the end-to-end user experience. The\nteam is 14 people, Series A, remote-first. Here's the JD: [link]\"\n---\n\nNo pressure at all — and thanks either way.\n\n[Your name]\n```\n",{"name":5,"reads":24,"origin":26,"related":27,"description":7},[25],"startup-context","startup",[28,29],"job-description","interview-kit","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fstartup--sourcing-outreach",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill sourcing-outreach",{"tool":46,"command":47},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill sourcing-outreach",{"tool":49,"command":50},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill sourcing-outreach","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fstartup--sourcing-outreach\u002FSKILL.md",true,[],[55,63,70,78,86,94],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]