Company Brain Company QA
topoteretes/cognee
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together.
企业年金/职业年金智能查询技能 v3.2。自动识别单位性质,精确判断年金类型,关键词分析优先,多重验证防错,查询年金开户银行,输出带来源链接和错误检查的标准化调查报告。支持事业单位、国企、民企、上市公司等各类单位。
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/company-pension-search .claude/skills/company-pension-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .claude/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/company-pension-search .agents/skills/company-pension-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .agents/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/company-pension-search .cursor/skills/company-pension-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .cursor/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/company-pension-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/company-pension-search .gemini/skills/company-pension-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .gemini/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/company-pension-search .github/skills/company-pension-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .github/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills company-pension-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/company-pension-search .opencode/skills/company-pension-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "company-pension-search" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/company-pension-search into .opencode/skills/company-pension-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "company-pension-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
company-pension-search企业年金/职业年金智能查询技能 v3.2。自动识别单位性质,精确判断年金类型,关键词分析优先,多重验证防错,查询年金开户银行,输出带来源链接和错误检查的标准化调查报告。支持事业单位、国企、民企、上市公司等各类单位。
Company Pension Search is an agent skill from LeoYeAI/openclaw-master-skills. 企业年金/职业年金智能查询技能 v3.2。自动识别单位性质,精确判断年金类型,关键词分析优先,多重验证防错,查询年金开户银行,输出带来源链接和错误检查的标准化调查报告。支持事业单位、国企、民企、上市公司等各类单位。
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `CHANGELOG_v3.0.md`, `CHANGELOG_v3.1.md` and `CHANGELOG_v3.2.md`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 3 files in scripts/ (Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
cninfo.com.cnsse.com.cnszse.cnfund.eastmoney.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
TAVILY_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Company Pension Search loads about 2.8k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 481 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 481 words, ~2,796 tokens.
.claude/skills/company-pension-search/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.关键改进:关键词分析优先、年金类型精确判断、多重验证防错、错误检查清单
一键调查任意企业/单位是否缴纳企业年金或职业年金,查询年金开户银行,通过上市公司年报、基金招募书、养老金产品报告等多渠道分析,所有结论附带来源链接。
"帮我查一下 [企业名称] 有没有企业年金"
"查询 [企业名称] 的职业年金情况"
"调查 [企业名称] 的福利待遇,包括年金""对 [企业名称] 进行全面年金调查,使用所有方法"
"查一下 [企业名称] 的年金、公积金、待遇情况,输出完整报告""帮我查一下这几家公司的年金:公司 A、公司 B、公司 C"| 功能 | 说明 | 版本 |
|---|---|---|
| 单位性质识别 | 自动识别企业/事业单位/国企/民企/上市公司 | ✅ v2.0 |
| 智能方法选择 | 根据单位类型自动选择最优调查方法 | ✅ v2.0 |
| 18 种调查方法 | 覆盖官方、商业、员工分享等多渠道 | ✅ v2.0 |
| 置信度评估 | 自动计算信息可靠性评分 | ✅ v2.0 |
| 标准化报告 | 输出结构化调查报告 | ✅ v2.0 |
| 批量查询 | 支持一次查询多家企业 | ✅ v2.0 |
| 年金开户银行查询 | 查询企业年金托管银行/受托银行 | ✅ v3.0 |
| 来源链接标注 | 所有结论附带来源链接 | ✅ v3.0 |
| 年报查询分析 | 通过上市公司年报查询应付职工薪酬、企业年金 | ✅ v3.1 |
| 基金/养老金产品查询 | 通过基金招募书、养老金产品报告查询投资管理人/托管人 | ✅ v3.1 |
| 官方机构名单比对 | 比对人社部/人社局官方受托机构/托管人名单 | ✅ v3.1 |
| 年金类型精确判断 | 关键词分析优先,防止类型判断错误 | ✅ v3.2 |
| 特殊情况识别 | 识别企业化管理事业单位等特殊情况 | ✅ v3.2 |
| 错误检查清单 | 输出前强制检查,防止先入为主错误 | ✅ v3.2 |
| 多重验证机制 | 关键词、单位性质、多渠道交叉验证 | ✅ v3.2 |
自动执行:
1. 搜索企业名称 + 官网
2. 分析工商注册信息
3. 识别单位类型标签判断逻辑:
┌─────────────────────────────────────┐
│ 输入企业名称 │
└─────────────┬───────────────────────┘
▼
┌─────────────────────────────────────┐
│ 搜索:单位性质/工商类型/上市状态 │
└─────────────┬───────────────────────┘
▼
┌─────────────────────────────────────┐
│ 类型判断 │
│ ┌─────────────────────────────┐ │
│ │ 财政供养? → 是 → 事业单位 │ │
│ │ 国资控股? → 是 → 国企 │ │
│ │ 上市代码? → 有 → 上市公司 │ │
│ │ 以上皆无? → 民企/其他 │ │
│ └─────────────────────────────┘ │
└─────────────┬───────────────────────┘
▼
┌─────────────────────────────────────┐
│ 输出:单位类型 + 置信度 │
└─────────────────────────────────────┘单位类型与年金类型映射:
| 单位类型 | 年金类型 | 是否强制 | 缴费比例 |
|---|---|---|---|
| 事业单位 | 职业年金 | ✅ 强制 | 单位 8% + 个人 4% |
| 公务员单位 | 职业年金 | ✅ 强制 | 单位 8% + 个人 4% |
| 国有企业 | 企业年金 | ❌ 自愿 | 单位 4-8% + 个人 1-4% |
| 上市公司 | 企业年金 | ❌ 自愿 | 单位 4-8% + 个人 1-4% |
| 民营企业 | 企业年金 | ❌ 自愿 | 单位 4-8% + 个人 1-4% |
| 外企 | 企业年金 | ❌ 自愿 | 单位 4-8% + 个人 1-4% |
根据单位类型自动选择最优调查方法组合:
| 优先级 | 方法 | 权重 | 预期可靠性 |
|---|---|---|---|
| 1 | 部门预算/决算公开 | 30% | ⭐⭐⭐⭐⭐ |
| 2 | 事业单位招聘公告 | 25% | ⭐⭐⭐⭐⭐ |
| 3 | 官网查询 | 20% | ⭐⭐⭐⭐ |
| 4 | 员工分享平台 | 15% | ⭐⭐⭐ |
| 5 | 直接咨询 | 10% | ⭐⭐⭐⭐⭐ |
| 优先级 | 方法 | 权重 | 预期可靠性 |
|---|---|---|---|
| 1 | 年报/ESG 报告 | 30% | ⭐⭐⭐⭐⭐ |
| 2 | 国资委官网 | 25% | ⭐⭐⭐⭐⭐ |
| 3 | 招聘公告 | 20% | ⭐⭐⭐⭐ |
| 4 | 商业查询平台 | 15% | ⭐⭐⭐⭐ |
| 5 | 员工分享 | 10% | ⭐⭐⭐ |
| 优先级 | 方法 | 权重 | 预期可靠性 |
|---|---|---|---|
| 1 | 年报查询(巨潮/港交所) | 40% | ⭐⭐⭐⭐⭐ |
| 2 | ESG 报告/社会责任报告 | 25% | ⭐⭐⭐⭐⭐ |
| 3 | 招聘平台 | 15% | ⭐⭐⭐⭐ |
| 4 | 员工分享平台 | 15% | ⭐⭐⭐ |
| 5 | 商业查询平台 | 5% | ⭐⭐⭐ |
| 优先级 | 方法 | 权重 | 预期可靠性 |
|---|---|---|---|
| 1 | 商业查询平台(天眼查/企查查) | 25% | ⭐⭐⭐⭐ |
| 2 | 招聘平台 | 25% | ⭐⭐⭐⭐ |
| 3 | 员工分享平台 | 20% | ⭐⭐⭐ |
| 4 | 直接咨询 HR | 20% | ⭐⭐⭐⭐⭐ |
| 5 | 官网查询 | 10% | ⭐⭐⭐ |
自动化脚本调用:
# 基础搜索
./scripts/search.sh "企业名称" all
# 按类型搜索
./scripts/search.sh "企业名称" official # 官方渠道
./scripts/search.sh "企业名称" recruitment # 招聘信息
./scripts/search.sh "企业名称" social # 员工分享
./scripts/search.sh "企业名称" financial # 财务/年报
# 深度调查(所有方法)
./scripts/search.sh "企业名称" deep搜索渠道:
置信度算法:
置信度 = Σ(信息来源可靠性 × 信息一致性 × 时效性权重)
信息来源可靠性:
- 官方文件/官网:1.0
- 政府公开信息:0.9
- 上市公司年报:0.95
- 招聘公告:0.8
- 员工分享:0.6
- 匿名爆料:0.4
信息一致性:
- 多个独立来源一致:1.0
- 部分来源一致:0.7
- 单一来源:0.5
- 来源冲突:0.3
时效性权重:
- 1 年内信息:1.0
- 1-2 年信息:0.8
- 2-3 年信息:0.6
- 3 年以上:0.4置信度等级:
| 分数 | 等级 | 显示 |
|---|---|---|
| 0.85-1.0 | 极高 | ⭐⭐⭐⭐⭐ |
| 0.70-0.84 | 高 | ⭐⭐⭐⭐ |
| 0.55-0.69 | 中 | ⭐⭐⭐ |
| 0.40-0.54 | 低 | ⭐⭐ |
| 0.00-0.39 | 极低 | ⭐ |
报告结构:
# [企业名称] - 企业年金/职业年金调查报告
## 核心结论(TL;DR)
| 项目 | 结论 | 置信度 | 来源 |
|------|------|--------|------|
| 企业年金/职业年金 | 有/无 | ⭐⭐⭐⭐ | [链接](url) |
| 年金开户银行 | XX 银行 | ⭐⭐⭐⭐ | [链接](url) |
| 单位性质 | XXX | ⭐⭐⭐⭐⭐ | [链接](url) |
## 单位性质分析
[详细说明] [来源](url)
## 年金信息
- 年金类型:企业年金/职业年金 [来源](url)
- 缴费比例:单位 X% + 个人 X% [来源](url)
- 开户银行:XX 银行(托管人/受托人) [来源](url)
## 调查结果汇总
| 方法 | 发现 | 可靠性 | 来源链接 |
|------|------|--------|----------|
| 年报查询 | ... | ⭐⭐⭐⭐⭐ | [链接](url) |
| 招聘平台 | ... | ⭐⭐⭐⭐ | [链接](url) |
## 待遇水平估算
[基于公开数据的估算]
## 信息来源(带链接)
1. [来源名称](url) - 内容描述
2. [来源名称](url) - 内容描述
## 建议进一步确认方式
[具体行动建议]v3.0 新增要求:
[来源名称](URL)核心原则:公告/文档标题关键词优先级 高于 单位性质推断
| 关键词 | 年金类型 | 优先级 |
|---|---|---|
| "企业年金" | 企业年金 | ⭐⭐⭐⭐⭐(最高) |
| "职业年金" | 职业年金 | ⭐⭐⭐⭐⭐(最高) |
| "五险二金(企业年金)" | 企业年金 | ⭐⭐⭐⭐⭐ |
| "五险二金(职业年金)" | 职业年金 | ⭐⭐⭐⭐⭐ |
| "五险二金" | 需进一步确认 | ⭐⭐⭐⭐ |
判断规则:
| 特殊情况 | 识别方法 | 处理方式 |
|---|---|---|
| 企业化管理事业单位 | 官网查询单位性质 | 查看公告关键词,不自动假设 |
| 编外/合同制人员 | 招聘公告区分 | 可能有独立企业年金 |
| 混合年金(既有企业又有职业) | 咨询 HR/查看合同 | 分别查询确认 |
| 历史遗留(2014 年前建立) | 查看建立时间 | 可能是企业年金延续 |
| 股权激励替代 | 上市公司年报查询 | 确认无企业年金 |
### 错误检查(v3.2 新增)
- [ ] 公告标题关键词是否与结论一致?
- [ ] 单位性质是否有特殊情况?
- [ ] 是否有多个信息来源交叉验证?
- [ ] 是否存在 2014 年前后时间差异?
- [ ] 是否考虑了编外/合同制人员情况?
- [ ] 置信度是否合理标注?
- [ ] 待确认项是否明确标注?| 错误类型 | 错误表现 | 预防措施 |
|---|---|---|
| 先入为主 | 看到"事业单位"就假设"职业年金" | ✅ 强制提取公告关键词 |
| 忽略特殊情况 | 不了解"企业化管理事业单位" | ✅ 维护特殊情况清单 |
| 单一来源 | 仅凭单位性质推断 | ✅ 强制多渠道交叉验证 |
| 时间差异忽略 | 不考虑 2014 年政策变化 | ✅ 查询年金建立时间 |
适用对象:上市公司
查询平台:
搜索关键词:
"[企业名称] 年报 应付职工薪酬 企业年金"
"[企业名称] 年报 离职后福利"可获取信息:
适用对象:所有单位(如有年金产品)
查询平台:
搜索关键词:
"[企业名称] 企业年金 养老金产品 投资管理人 托管人"
"[企业名称] 年金 受托人 托管银行"可获取信息:
适用对象:所有单位
查询平台:
全国企业年金管理机构(截至 2025 年):
可获取信息:
## 💰 年金开户银行(v3.1 增强)
| 角色 | 机构名称 | 信息来源 | 置信度 |
|------|----------|----------|--------|
| **受托人** | [机构名称] | [年报/产品报告/官方名单] | ⭐⭐⭐ |
| **托管人** | [银行名称] | [产品报告/官方名单] | ⭐⭐⭐ |
| **投资管理人** | [机构名称] | [产品报告] | ⭐⭐⭐ |
| **账户管理人** | [机构名称] | [产品报告] | ⭐⭐⭐ |
**查询方法**:
- [ ] 上市公司年报查询
- [ ] 年金产品报告查询
- [ ] 官方名单比对
- [ ] 招聘信息确认#!/bin/bash
# 用法:./search.sh "企业名称" [搜索类型] [输出格式]
# 搜索类型:all / official / recruitment / social / financial / deep
# 输出格式:text / json / markdown
COMPANY_NAME="$1"
SEARCH_TYPE="${2:-all}"
OUTPUT_FORMAT="${3:-text}"
# 自动检测可用的搜索工具
if [ -n "$TAVILY_API_KEY" ]; then
SEARCH_TOOL="tavily"
elif [ -n "$SEARXNG_URL" ]; then
SEARCH_TOOL="searxng"
else
SEARCH_TOOL="fallback"
fi
# 执行搜索
case "$SEARCH_TYPE" in
official)
search_official "$COMPANY_NAME"
;;
recruitment)
search_recruitment "$COMPANY_NAME"
;;
# ... 其他类型
esac#!/bin/bash
# 用法:./generate_report.sh [企业名称] [调查数据 JSON] [输出路径]
COMPANY_NAME="$1"
DATA_FILE="$2"
OUTPUT_PATH="${3:-./reports}"
# 生成 Markdown 报告
generate_markdown_report "$COMPANY_NAME" "$DATA_FILE" "$OUTPUT_PATH"
# 可选:生成 PDF
if command -v pandoc &> /dev/null; then
generate_pdf_report "$OUTPUT_PATH"
fi#!/bin/bash
# 用法:./batch_query.sh [公司列表文件] [输出目录]
COMPANY_LIST="$1"
OUTPUT_DIR="${2:-./batch_reports}"
# 读取公司列表
while IFS= read -r company; do
echo "调查:$company"
./search.sh "$company" deep
./generate_report.sh "$company"
done < "$COMPANY_LIST"
# 生成汇总报告
generate_summary_report "$OUTPUT_DIR"| 缴费方 | 比例 | 说明 |
|---|---|---|
| 单位缴纳 | 8% | 财政负担 |
| 个人缴纳 | 4% | 工资代扣 |
| 合计 | 12% | 强制 |
| 缴费方 | 比例范围 | 说明 |
|---|---|---|
| 单位缴纳 | 4%-8% | 不超过工资总额 8% |
| 个人缴纳 | 1%-4% | 自愿选择 |
| 合计 | 5%-12% | 自愿 |
详见 references/salary-reference.md
| 变量 | 用途 | 必需 | 默认值 |
|---|---|---|---|
TAVILY_API_KEY | Tavily 搜索 API | 否 | - |
SEARXNG_URL | SearXNG 实例 URL | 否 | http://localhost:8080 |
OUTPUT_DIR | 报告输出目录 | 否 | ./reports |
CACHE_ENABLED | 启用缓存 | 否 | true |
CACHE_TTL | 缓存过期时间(秒) | 否 | 86400 |
创建 ~/.openclaw/workspace/skills/company-pension-search/config.json:
{
"search": {
"preferred_tool": "tavily",
"fallback_tool": "searxng",
"max_results": 20,
"timeout_seconds": 30
},
"report": {
"format": "markdown",
"include_raw_data": true,
"auto_save": true
},
"cache": {
"enabled": true,
"ttl_seconds": 86400
}
}用户:帮我查一下深圳市大数据资源管理中心有没有企业年金
AI 执行流程:
1. 识别单位性质 → 事业单位(置信度 0.95)
2. 选择调查方案 → 事业单位方案
3. 执行调查:
- 搜索预算/决算公开 ✅ 找到
- 搜索招聘公告 ✅ 找到
- 搜索员工分享 ⚠️ 信息少
4. 计算置信度 → 0.88(高)
5. 输出结论 → ✅ 有职业年金(单位 8% + 个人 4%)用户:腾讯公司有没有企业年金?
AI 执行流程:
1. 识别单位性质 → 民营企业/上市公司(置信度 1.0)
2. 选择调查方案 → 上市公司方案
3. 执行调查:
- 搜索年报 ✅ 找到,无年金披露
- 搜索 ESG 报告 ✅ 找到,有股权激励
- 搜索员工分享 ✅ 找到,确认无年金
4. 计算置信度 → 0.92(极高)
5. 输出结论 → ❌ 无企业年金,有股权激励替代用户:帮我查一下这几家公司的年金:腾讯、阿里、字节、华为
AI 执行流程:
1. 分别识别各单位性质
2. 为每家公司选择合适方案
3. 并行执行调查
4. 生成对比报告
5. 输出汇总表格Q1: 搜索结果为空?
Q2: 置信度过低?
Q3: 报告生成失败?
references/pension-policy.md - 年金政策详解references/salary-reference.md - 各地待遇参考references/search-methods.md - 18 种调查方法详解scripts/search.sh - 搜索脚本scripts/generate_report.sh - 报告生成脚本scripts/batch_query.sh - 批量查询脚本版本:2.0.0
最后更新:2026-03-12
维护者:OpenClaw 社区
许可证:MIT
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 13 other files (scripts, references) in skills/company-pension-search of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Company Pension Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Company Pension Search this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Company Brain Company QAtopoteretes/cognee | 32k | — | ~750 | Automated safety check: Notes | Apache-2.0 | |
| Company Creatorpaperclipai/paperclip | 100k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Company Brainifygarrytan/gbrain | 31k | — | ~9k | Automated safety check: Pass | MIT | |
| Company Osalirezarezvani/claude-skills | 28k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Sop Company Wikisickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Pass | MIT |
topoteretes/cognee
Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together.
paperclipai/paperclip
Create agent company packages that conform to agentcompanies/v1.
garrytan/gbrain
Extract a sanitized shared team/company brain from a personal brain.
alirezarezvani/claude-skills
The meta-framework for how a company runs — the connective tissue between all C-suite roles.
sickn33/agentic-awesome-skills
SOP and company wiki register: title, category, department, owner, version, priority and review dates.
HKUDS/Vibe-Trading
Runs a six-lens research framework on pre-IPO and private companies, labels every data point by confidence, and produces a fair-value range, exit-path analysis and information-gap map.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
企业年金/职业年金智能查询技能 v3.2。自动识别单位性质,精确判断年金类型,关键词分析优先,多重验证防错,查询年金开户银行,输出带来源链接和错误检查的标准化调查报告。支持事业单位、国企、民企、上市公司等各类单位。. Company Pension Search is an agent skill from LeoYeAI/openclaw-master-skills.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a claude-code`. Or copy the skill folder (skills/company-pension-search in LeoYeAI/openclaw-master-skills) into .claude/skills/company-pension-search in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a codex`. Or copy the skill folder (skills/company-pension-search in LeoYeAI/openclaw-master-skills) into .agents/skills/company-pension-search in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill company-pension-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/company-pension-search, .gemini/skills/company-pension-search, .github/skills/company-pension-search and .opencode/skills/company-pension-search in your project.
Going by SKILL.md and its folder, Company Pension Search needs a shell for the scripts in its folder and credentials named TAVILY_API_KEY. Our summary lists: A Bash shell; A credential in TAVILY_API_KEY.
SKILL.md names 4 domains. As links in the text: cninfo.com.cn, sse.com.cn, szse.cn and fund.eastmoney.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Company Pension Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Company Pension Search: Company Brain Company QA (topoteretes/cognee, 32k stars), Company Creator (paperclipai/paperclip, 100k stars), Company Brainify (garrytan/gbrain, 31k stars) and Company Os (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.