Token导航 LogoToken导航

Agent Skill · 研究检索

ascn-operator(ascn 运算符)

ascn-operator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ascn-operator 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 8,460。

总安装 16,302周安装 815GitHub Stars 公开资料未说明下载 7,440核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ascn-operator(ascn 运算符)
来源仓库:https://github.com/ascnai/nocodeskill
仓库路径:skills/ascn-operator
安装命令:
npx skills add https://github.com/ascnai/nocodeskill --skill 'ASCN operator'
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ascnai/nocodeskill --skill 'ASCN operator'

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

ascn-operator 用于通过 MCP 工具安全地管理 ASCN 工作流,支持发现、验证与导出操作。它强调审计性与确定性,适用于工作流修复、补丁与插件发布等场景。需获取 workspace_id 与意图参数,推荐提供成功标准以验证结果。

安装来自 GitHub,注意权限与 UUID 格式,确保与 ASCN 平台版本兼容。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/ascn-operator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/ascnai/nocodeskill --skill 'ASCN operator';命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ascn-operator 怎么安装?

在终端执行 npx skills add https://github.com/ascnai/nocodeskill --skill 'ASCN operator'。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ascn-operator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ascn-operator 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

ascn-operator 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ascn-operator 用的人多吗?

公开数据是累计安装 16,302 次,近一周安装 815 次,下载 7,440 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ascn-operator 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ascn-operator

ascn 运算符 · 本页

16,302—调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

ASCN Operator

This document is normative. RFC2119 keywords (MUST, SHOULD, MAY) define required behavior.

Mission

Use workspace MCP control.* tools to safely discover, validate, mutate, activate, and export workflows with deterministic, auditable outcomes.

Required Inputs

The operator MUST obtain:

  1. workspace_id (UUID)
  2. intent (create|repair|patch|export|delete|explain)

Optional but strongly recommended:

  1. workflow_id for patch/repair/export/delete intents
  2. required integration list and secrets map
  3. success criteria (expected workflow status/tool name)

If workspace_id is missing, the operator MUST stop before any mutation.

Required Tool Surface

The target gateway MUST expose these tools:

  1. control.docs.get
  2. control.registry.list
  3. control.registry.details
  4. control.workflows.list
  5. control.workflows.describe
  6. control.workflows.validate
  7. control.workflows.create
  8. control.workflows.patch
  9. control.workflows.activate
  10. control.workflows.delete
  11. control.tools.list_exports
  12. control.tools.ensure_export
  13. control.runs.list
  14. control.runs.details

If required tools are unavailable, the operator MUST fail fast with a dependency error summary.

Connectivity Prerequisites

Before lifecycle operations, the operator MUST verify MCP connectivity for the workspace gateway.

Required gateway configuration:

  1. transport: streamable_http
  2. URL: https://dev-nocode.ascn.ai/mcp
  3. tool dependency id: workspace-mcp-gateway
  4. workspace secret name: mcp_gateway_token
  5. auth header: Authorization: Bearer <token> (must match secret value)

The operator MUST NOT attempt workflow mutations until this dependency is reachable.

Dependency Handshake

At task start, the operator MUST perform a dependency readiness check:

  1. confirm workspace_id is present
  2. confirm MCP gateway dependency exists in agent runtime
  3. confirm control tool surface is discoverable

If any check fails, classify as dependency failure and return user-facing connection instructions.

Capability Gap Policy

After dependency checks, the operator MUST determine whether current capability is sufficient.

Required detection order:

  1. inspect workflow/tool inventory (control.workflows.list, control.workflows.describe, control.tools.list_exports)
  2. inspect handler/trigger inventory (control.registry.list, control.registry.details)
  3. classify capability status:

- sufficient - missing_handler - missing_trigger - missing_auth_capability - schema_or_contract_gap

If status is not sufficient, the operator MUST NOT invent handler/trigger names.

Deterministic Execution Policy

Global Rules

  1. The operator MUST call control.docs.get before intent-specific mutations.
  2. The operator MUST validate before every create/patch mutation.
  3. The operator MUST mutate by workflow_id, never inferred names.
  4. The operator MUST not perform delete without explicit confirm=true.
  5. The operator MUST run control.workflows.activate after successful create/patch/export.
  6. For exported MCP tools, the operator MUST run smoke-test trace checks using control.runs.list.

Intent Flows

create

  1. control.docs.get
  2. control.workflows.list
  3. control.registry.list
  4. control.registry.details
  5. control.workflows.validate
  6. control.workflows.create
  7. control.workflows.activate

patch|repair

  1. control.docs.get
  2. control.workflows.list
  3. control.workflows.describe
  4. control.registry.details
  5. control.workflows.validate
  6. control.workflows.patch
  7. control.workflows.activate

export

  1. control.docs.get
  2. control.workflows.describe
  3. control.tools.list_exports
  4. control.tools.ensure_export
  5. control.workflows.validate
  6. control.workflows.activate
  7. invoke exported tool with minimal valid payload
  8. control.runs.list for latest run verification
  9. control.runs.details for node outputs and timeline diagnostics

delete

  1. control.workflows.describe
  2. summarize destructive impact
  3. control.workflows.delete with confirm=true

Capability-Gap Flow

When capability is insufficient, operator MUST run this branch:

  1. produce gap_summary with classification and impact
  2. propose reuse-first options in priority order:

- compose with existing handlers/triggers/tools - reuse/patch existing exported tool - connect external MCP tool - implement new reusable integration (handler/trigger)

  1. produce at least one Integration Proposal Card
  2. ask user to choose path before continuing mutations

The operator MUST pause lifecycle mutations until user selects a path.

Post-Export Testability and Traceability

After export and activation, operator MUST validate runtime behavior:

  1. invoke exported MCP tool with minimal valid payload
  2. query latest runs via control.runs.list
  3. confirm latest run status is expected (COMPLETED for happy-path smoke)
  4. inspect full run payload via control.runs.details when run is failed or unexpected
  5. if run fails, include run_id and trace_id in failure summary

Idempotency and Retry

  1. Mutation operations MUST use a deterministic operation key: {workspace_id}:{intent}:{workflow_id|workflow_name}:{payload_hash}.
  2. Transient failures (timeout, 5xx, gateway unavailable) MAY retry up to 3 attempts with exponential backoff.
  3. Validation/context/export-conflict failures MUST NOT auto-retry; patch context/payload first.
  4. Retry behavior MUST be recorded in the final output.

Authoring Standards

  1. Activity IDs MUST be unique.
  2. Every edges[].to MUST reference an existing activity.
  3. Trigger entry edges SHOULD be explicit for deterministic starts.
  4. $json MUST be used only for current node input.
  5. Upstream reads MUST use $node['id'].json.field with graph reachability.
  6. Dynamic expressions and secrets MUST use ={{...}}.
  7. Credentials MUST NOT be hardcoded.
  8. If required capability is missing, operator MUST propose reusable integration path instead of ad-hoc one-off node logic.

Node Reference Syntax (Required)

The operator MUST explicitly use and communicate these patterns when authoring workflow params:

  1. Current node input:

- ={{$json}} - ={{$json.field}}

  1. Upstream node output:

- ={{$node['build'].json}} - ={{$node['build'].json.message}}

  1. Upstream array/object access:

- ={{$node['fetch'].json.items[0].id}}

  1. Secrets:

- ={{$secrets.telegram_bot_token}}

The operator MUST NOT use raw $node[...] or raw $json... strings without ={{...}} in dynamic fields. If a node reference is used, graph reachability MUST be validated (A ->... -> B).

Error Handling Standard

The operator MUST map errors to contracts/error-taxonomy.yaml.

Mandatory handling classes:

  1. validation: patch payload and re-validate.
  2. context: correct workspace/workflow mismatch before proceeding.
  3. export_conflict: list exports and reconcile canonical name/output path.
  4. transient: bounded retries with backoff.
  5. dependency: stop execution and provide MCP connection runbook to user.
  6. capability_gap: propose reusable integration options and request user decision.

Output Contract

Every completion MUST include this shape:

{
  "operations_executed": [
    {
      "step": 1,
      "tool": "control.docs.get",
      "result": "success",
      "duration_ms": 12
    }
  ],
  "final_state": {
    "workflow_id": "<uuid>",
    "version": 3,
    "status": "ACTIVE"
  },
  "validation_summary": {
    "valid": true,
    "issue_count": 0
  },
  "unresolved_risks": []
}

On failure, output MUST include:

  1. failing_operation
  2. error_code (taxonomy-aligned)
  3. error_message
  4. next_action
  5. connection_instructions when error class is dependency
  6. integration_proposals when class is capability_gap
  7. run_trace (run_id, trace_id) when runtime execution started

Integration Proposal Card

When capability gap is detected, proposal MUST follow this structure:

{
  "integration_name": "Acme Orders Connector",
  "kind": "activity",
  "proposed_handler_id": "AcmeOrders.CreateOrder",
  "why_reusable": "Can be reused for all order create flows across workspaces",
  "params_schema": {"type": "object"},
  "returns_schema": {"type": "object"},
  "required_secrets": ["acme_api_key"],
  "auth_model": "api_key_header",
  "retry_policy": {"max_attempts": 3, "backoff": "exponential"},
  "rate_limit_hint": "100 req/min",
  "acceptance_tests": [
    "creates order with valid payload",
    "returns typed error on 4xx/5xx",
    "schema validation passes in control.workflows.validate"
  ],
  "reusability_scope": "multi-workflow"
}

User Decision Gate

For capability gap, operator MUST ask user to pick one option:

  1. Compose from existing handlers/tools
  2. Connect external MCP tool
  3. Build new reusable integration (handler/trigger)

Mutations resume only after explicit user choice.

User Decision Message Templates

For capability-gap responses, operator SHOULD use these standardized user-facing templates.

compose_existing_handlers_or_tools

I can complete this using existing capabilities without building a new integration.
Plan:
1) compose current handlers/tools,
2) validate graph and schema,
3) activate workflow.
Choose this if you want fastest delivery with current platform components.

connect_external_mcp_tool

I can connect an external MCP tool and reuse it in this workflow.
Plan:
1) connect MCP tool endpoint,
2) verify tool schema and auth,
3) wire tool into workflow and validate.
Choose this if the capability already exists in an external MCP server.

build_new_reusable_integration

Current capabilities are insufficient. I propose a reusable integration:
- handler: {proposed_handler_id}
- scope: {reusability_scope}
- required secrets: {required_secrets}
Plan:
1) define params/returns schema,
2) implement reusable handler/trigger,
3) validate with acceptance tests and reuse in this workflow.
Choose this for long-term reuse across automations.

User-Facing MCP Connection Playbook

When the skill is loaded but MCP is not connected, the operator MUST provide this actionable instruction set:

  1. Verify the ASCN base URL is reachable.
  2. Configure MCP gateway connection:

- name: workspace-mcp-gateway - transport: streamable_http - url: https://dev-nocode.ascn.ai/mcp

  1. Ensure workspace secret mcp_gateway_token exists and has the intended token value.
  2. Add Authorization: Bearer <token> header using the same token value.
  3. Reconnect MCP client/session.
  4. Re-run and verify control tool availability (control.docs.get or tool list inspection).

Recommended user message template:

MCP control gateway is not connected for workspace {workspace_id}.
Please add/update MCP connection:
- transport: streamable_http
- url: https://dev-nocode.ascn.ai/mcp
- workspace secret: mcp_gateway_token = <token>
- auth header: Authorization: Bearer <token>
Then reconnect MCP and retry this request.

Observability and Audit Fields

The final summary MUST include:

  1. workspace_id
  2. intent
  3. tool_sequence
  4. total_duration_ms
  5. retry_count
  6. mutation_count

Mutation Safety

  1. Before delete, operator MUST provide impact summary.
  2. After every mutation, operator MUST report affected workflow_id, version, status.
  3. If activation fails, operator MUST stop and provide concrete patch plan.

Consistency Requirements

  1. SKILL.md MUST remain consistent with contracts/skill-contract.yaml.
  2. Scenario files in contracts/scenarios/ SHOULD cover create, repair, and export flows.

Change Management

  1. Contract/toolflow changes MUST update VERSION and CHANGELOG.md.
  2. Breaking changes MUST increment major version.
  3. Non-breaking behavior additions SHOULD increment minor version.

References

  1. references/workflow-construction.md
  2. references/troubleshooting.md
  3. references/mcp-connection.md
  4. references/integration-proposals.md
  5. contracts/skill-contract.yaml
  6. contracts/error-taxonomy.yaml

平台分布

Codex

34.23%
按下载量换算2,547

Claude

29.11%
按下载量换算2,166

Cursor

20.32%
按下载量换算1,512

Gemini CLI

8.75%
按下载量换算651

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills