据 AlphaMoat 统计,截至 2026-09,Lobster 累计下载 4,899 次、获 3 个星标,在全部 5,078 个 AI 技能中排名第 1,905 位,在「AI 智能体」分类(969 个)中排名第 356 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 159 | 4,899 | 2 | 2 |
| SkillHub ↗ | 157 | 4,726 | 3 | — |
各平台的计数口径不同,统计时间不一致。
可编排多步骤自动化、监控、类型化 JSON 处理和批量操作,并在产生副作用前暂停等待审批。宽泛的 shell 执行可能影响当前工作区;应限制凭据范围和状态目录,并在执行前审阅工作流。 需要Node.js和实际本地路径下审核固定的Lobster;审批只在已配置位置暂停,须核实每个副作用步骤均有关卡。设置项目专属LOBSTER_STATE_DIR,CLAWD_URL/CLAWD_TOKEN仅可选Clawdbot分支需用,保护token与恢复状态。
资料发布于 2026-10-27
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 4,899 | — | 3 |
| 2026-08 | 4,740 | +5.5% | 3 |
| 2026-07 | 4,493 | +10.3% | 3 |
| 2026-06 | 4,074 | +5.4% | 2 |
| 2026-05 | 3,864 | — | 2 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: lobster description: > Lobster workflow runtime for deterministic pipelines with approval gates. Use when: (1) Running multi-step automations that need human approval before side effects, (2) Monitoring PRs/issues for changes, (3) Processing data through typed JSON pipelines, (4) Email triage or batch operations, (5) Any workflow that should halt and ask before acting. Lobster saves tokens by running deterministic pipelines instead of re-planning each step. ---
# Lobster
> **Contribute:** Source code & PRs welcome at [github.com/guwidoe/lobster-skill](https://github.com/guwidoe/lobster-skill)
Workflow runtime for AI agents — typed pipelines with approval gates.
## CLI Location
```bash
# Set alias (adjust path to your install location)
LOBSTER="node /home/molt/clawd/tools/lobster/bin/lobster.js"
# Or install globally: npm install -g @clawdbot/lobster
# Then use: lobster '<pipeline>'
```
## Quick Reference
```bash
# Run pipeline (human mode - pretty output)
$LOBSTER '<pipeline>'
# Run pipeline (tool mode - JSON envelope for integration)
$LOBSTER run --mode tool '<pipeline>'
# Run workflow file
$LOBSTER run path/to/workflow.lobster
# Resume after approval
$LOBSTER resume --token "<token>" --approve yes|no
# List commands/workflows
$LOBSTER commands.list
$LOBSTER workflows.list
```
## Core Commands
| Command | Purpose |
|---------|---------|
| `exec --json --shell "cmd"` | Run shell, parse stdout as JSON |
| `where 'field=value'` | Filter objects |
| `pick field1,field2` | Project fields |
| `head --n 5` | Take first N items |
| `sort --key field --desc` | Sort items |
| `groupBy --key field` | Group by key |
| `dedupe --key field` | Remove duplicates |
| `map --wrap key` | Transform items |
| `template --text "{{field}}"` | Render templates |
| `approve --prompt "ok?"` | **Halt for approval** |
| `diff.last --key "mykey"` | Compare to last run (stateful) |
| `state.get key` / `state.set key` | Read/write persistent state |
| `json` / `table` | Render output |
## Built-in Workflows
```bash
# Monitor PR for changes (stateful - remembers last state)
$LOBSTER "workflows.run --name github.pr.monitor --args-json '{\"repo\":\"owner/repo\",\"pr\":123}'"
# Monitor PR and emit message only on change
$LOBSTER "workflows.run --name github.pr.monitor.notify --args-json '{\"repo\":\"owner/repo\",\"pr\":123}'"
```
## Approval Flow (Tool Mode)
When a pipeline hits `approve`, it returns:
```json
{
"status": "needs_approval",
"requiresApproval": {
"prompt": "Send 3 emails?",
"items": [...],
"resumeToken": "eyJ..."
}
}
```
To continue:
```bash
$LOBSTER resume --token "eyJ..." --approve yes
```
## Example Pipelines
```bash
# List recent PRs, filter merged, show as table
$LOBSTER 'exec --json --shell "gh pr list --repo owner/repo --json number,title,state --limit 20" | where "state=MERGED" | table'
# Get data, require approval, then process
$LOBSTER run --mode tool 'exec --json --shell "echo [{\"id\":1},{\"id\":2}]" | approve --prompt "Process these?" | pick id | json'
# Diff against last run (only emit on change)
$LOBSTER 'exec --json --shell "gh pr view 123 --repo o/r --json state,title" | diff.last --key "pr:o/r#123" | json'
```
## Workflow Files (.lobster)
YAML/JSON files with steps, conditions, and approval gates:
```yaml
name: pr-review-reminder
steps:
- id: fetch
command: gh pr list --repo ${repo} --json number,title,reviewDecision
- id: filter
command: jq '[.[] | select(.reviewDecision == "")]'
stdin: $fetch.stdout
- id: notify
command: echo "PRs needing review:" && cat
stdin: $filter.stdout
approval: required
```
Run: `$LOBSTER run workflow.lobster --args-json '{"repo":"owner/repo"}'`
## Clawdbot Integration
Lobster can call Clawdbot tools via `clawd.invoke`:
```bash
$LOBSTER 'clawd.invoke --tool message --action send --args-json "{\"target\":\"123\",\"message\":\"hello\"}"'
```
Requires `CLAWD_URL` and `CLAWD_TOKEN` environment variables.
## State Directory
Lobster stores state in `~/.lobster/state/` by default. Override with `LOBSTER_STATE_DIR`.
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把 agent 的记忆与跨技能状态存成带类型和约束的知识图谱的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。