Agent Skills
› opensquilla/opensquilla
› meta-sales-lead-researcher
meta-sales-lead-researcher
GitHub用于销售线索研究,通过协调网络搜索、浏览器审查、CRM笔记及邮件起草等多技能,生成基于证据的客户简报和 outreach 草稿。
Trigger Scenarios
客户背景调查
销售外联准备
Install
npx skills add opensquilla/opensquilla --skill meta-sales-lead-researcher -g -y
SKILL.md
Frontmatter
{
"kind": "meta",
"name": "meta-sales-lead-researcher",
"always": false,
"metadata": {
"opensquilla": {
"risk": "medium",
"capabilities": [
"network",
"filesystem-write"
]
}
},
"triggers": [
"sales lead research",
"account brief",
"客户调研",
"销售线索",
"拜访前调研",
"outreach prep",
"company brief"
],
"provenance": {
"origin": "opensquilla-original",
"license": "Apache-2.0"
},
"composition": {
"steps": [
{
"id": "intake",
"kind": "llm_chat",
"with": {
"task": "Parse the lead research contract.\n\nRequest:\n{{ inputs.user_message | xml_escape | truncate(2500) }}\n\nReturn exactly:\nTARGETS:\n - <company\/person\/domain>\nSALES_GOAL: <meeting|proposal|partnership|renewal|unknown>\nPRODUCT_CONTEXT: <brief or unknown>\nREGION: <region or unknown>\nNEEDS_CLARIFICATION: <yes|no>\nMISSING_FIELDS:\n - <target|sales_goal|none>\n",
"system": "You parse lead research requests and avoid inventing private contact data."
}
},
{
"id": "clarify",
"kind": "user_input",
"when": "'NEEDS_CLARIFICATION: yes' in outputs.intake",
"clarify": {
"mode": "form",
"intro": "销售调研需要目标公司\/联系人和拜访目的。",
"fields": [
{
"name": "target",
"type": "string",
"prompt": "目标公司\/联系人 \/ Target",
"required": true,
"max_chars": 240
},
{
"name": "sales_goal",
"type": "string",
"prompt": "销售目标 \/ Sales goal",
"max_chars": 240
}
],
"nl_extract": true,
"timeout_hours": 24,
"cancel_keywords": [
"取消",
"算了",
"cancel",
"stop"
]
},
"depends_on": [
"intake"
]
},
{
"id": "web_search",
"kind": "skill_exec",
"with": {
"query": "{{ outputs.intake | truncate(320) }} company news hiring funding product leadership competitors",
"engines": [
"duckduckgo",
"brave"
],
"max_results": 20
},
"skill": "multi-search-engine",
"depends_on": [
"intake",
"clarify"
]
},
{
"id": "source_review",
"kind": "agent",
"with": {
"task": "Review the public-source lead evidence. Do not scrape login-gated\nsites or infer private personal data. Summarize official site,\nnews, hiring signals, product clues, pain hypotheses, and weak data.\n\nIntake:\n{{ outputs.intake | truncate(1000) }}\nSearch:\n{{ outputs.web_search | truncate(8000) }}\n"
},
"skill": "sub-agent",
"depends_on": [
"web_search"
]
},
{
"id": "outreach_drafts",
"kind": "llm_chat",
"with": {
"task": "Draft:\n- 3 personalized email options\n- 1 LinkedIn\/message variant\n- discovery-call questions\n- objections and responses\n- CRM notes\n\nSource review:\n{{ outputs.source_review | truncate(7000) }}\n",
"system": "You write respectful, source-grounded B2B outreach drafts."
},
"depends_on": [
"source_review"
]
},
{
"id": "lead_brief",
"kind": "llm_chat",
"with": {
"task": "Return:\n- account snapshot\n- trigger events\n- pain hypotheses\n- stakeholder map if public evidence supports it\n- outreach drafts\n- discovery questions\n- do-not-claim list\n- source links\n\nReview:\n{{ outputs.source_review | truncate(6000) }}\nDrafts:\n{{ outputs.outreach_drafts | truncate(5000) }}",
"system": "You assemble sales account briefs with evidence and caveats."
},
"depends_on": [
"source_review",
"outreach_drafts"
]
}
]
},
"description": "Use this meta-skill instead of answering directly when the user wants account research, lead qualification, company\/person briefing, outreach prep, or a sales call brief that benefits from multi-skill orchestration across web research, browser\/source review, CRM-style notes, and email drafting.",
"meta_priority": 59,
"final_text_mode": "step:lead_brief"
}
Sales Lead Researcher
Creates evidence-grounded account briefs and outreach drafts from public data.
Version History
- 7f72a32 Current 2026-07-05 18:41


