Token导航 LogoToken导航

Agent Skill · 研究检索

ataski(ataski 搜索)

ataski 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。

ataski 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,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 69,087。

总安装 220周安装 9GitHub Stars 公开资料未说明下载 71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:ataski(ataski 搜索)
来源仓库:https://github.com/hebilicious/ataski
仓库路径:skills/ataski
安装命令:
npx skills add https://github.com/hebilicious/ataski --skill ataski
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/hebilicious/ataski --skill ataski

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。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务需求快速定位候选结果。它通过 ataski/ 目录协调子任务分配与进度跟踪,支持 git worktree 并行开发与多分支管理。

使用时需预先创建工作树目录(默认 ataski/worktrees/),由主 Agent 维护任务清单并控制分支合并顺序。安装前请确认是否具备 GitHub 访问权限,并评估是否会触发网络请求或令牌写入,避免安全风险。ataski 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ataski

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/hebilicious/ataski --skill ataski;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

ataski 怎么安装?

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

ataski 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。

ataski 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

ataski 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。

ataski 用的人多吗?

公开数据是累计安装 220 次,近一周安装 9 次,下载 71 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。

ataski 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
ataski

ataski 搜索 · 本页

220—只读未明确通过

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

Ataski

Use this skill to coordinate work through files in an ataski/ directory.

Canonical Board Rule

When using git worktrees and sub-agents:

  • The main agent is the coordinator.
  • Break the work into the smallest sensible set of parallelizable tasks before implementation starts.
  • Create one canonical feature worktree inside the configured worktree directory (worktreesDir, default: ataski/worktrees/).
  • The canonical worktree MUST use the parent feature branch (example: feature/faucet-cli).
  • Keep the shared ataski/ board only in that canonical feature worktree.
  • Only the main agent may change task files or ataski/tasks.md.
  • Sub-agents MUST treat ataski/ as read-only context.
  • Prepare or update the board in the canonical feature worktree first, then create task worktrees for sub-agents.
  • When task work is done, the main agent merges each task branch back into the canonical feature branch before review.
  • The configured worktree directory MUST be git-ignored.

Default config.jsonc

If ataski/config.jsonc exists, it overrides defaults. Default configuration:

{
  "structure": {
    "0": "todo/",
    "1": "in-progress/",
    "2": "done/"
  },
  "taskID": {
    "prefix": "T",
    "length": 3,
    "example": "T001"
  },
  "taskFrontMatter": {
    "id": "The task ID",
    "title": "The task title",
    "status": "The task status",
    "blockedBy": "Array of task IDs that must be done before this task can start",
    "owner": "Optional current owner/agent",
    "created_at": "The task creation datetime",
    "updated_at": "The task update datetime"
  },
  "testStrategy": "BDD/TDD/DDD (choose the best fit)",
  "tracker": "tasks.md",
  "worktreesDir": "ataski/worktrees/"
}

The same default file contents are mirrored in skills/references/config.jsonc.

Structure

Default structure:

ataski/
  todo/
  in-progress/
  done/
  worktrees/
  config.jsonc
  tasks.md

If it does not exist, create it before writing tasks.

The default ataski/worktrees/ directory is reserved for git worktrees and MUST be git-ignored.

Worktree Configuration

Use worktreesDir to control where git worktrees are created.

  • Default: ataski/worktrees/
  • The canonical feature worktree lives inside worktreesDir.
  • Each parallel task gets its own separate worktree inside worktreesDir.
  • The canonical branch should use the feature branch name (example: feature/faucet-cli).
  • Task branches should stay task-scoped (example: task/T001-short-title).

Create Tasks

  1. Allocate the next task ID (example: T001).
  2. Infer a short slugged title (example: T001-implement-typechecking.md).
  3. Create a new task file in directory 0 (default: ataski/todo/).
  4. Append a matching entry to ataski/tasks.md.

Never reuse task IDs.

For non-trivial source-code work, plan the feature first and split it into explicit tasks that can run in parallel whenever dependencies allow.

When splitting work for sub-agents, write each task so it is self-contained and executable without follow-up clarification.

Allocate Task IDs

Task IDs must follow config.jsonc. For default config, IDs are T001, T002, T003,...

Find the next ID by reading ataski/tasks.md, taking the highest existing ID, and incrementing it. If no tasks exist, start at T001.

Task File Naming

Always prefix the file name with the task ID.

Example:

  • T001-short-title.md

Keep file names lowercase after the ID slug.

Task File Template

Every task file must be markdown with YAML frontmatter:

---
id: T001
title: "Short task title"
status: todo
blockedBy: []
owner: unassigned
created_at: 2026-02-21T00:00:00Z
updated_at: 2026-02-21T00:00:00Z
---
## Requirements

- Describe the concrete behavior, acceptance criteria, and constraints.

## Test Plan

- State whether the task will use BDD, TDD, or DDD, and describe the intended RED path before implementation (tests, harness updates, or prerequisite test setup).

## RED Evidence

## GREEN Evidence

Use status values from configured structure. Default statuses:

  • todo
  • in-progress
  • done

Task content requirements:

  • The task content MUST contain all context required to complete the task.
  • A sub-agent MUST be able to complete the task without asking the main agent for missing scope, constraints, or acceptance criteria.
  • Put all required implementation context in the task file, including relevant requirements, boundaries, dependencies, and validation expectations.
  • A task file is not ready for implementation if Requirements or Test Plan is missing, vague, or leaves key decisions unstated.

blockedBy Rules

blockedBy controls dependencies between tasks.

  1. Use blockedBy as an array of task IDs (example: blockedBy: [T001, T004]).
  2. Default to an empty array for independent tasks.
  3. Reference only IDs that exist in ataski/tasks.md.
  4. Never include the task's own ID.
  5. Reject dependency cycles (direct or transitive) when creating or editing tasks.
  6. Treat dependencies as a hard gate: do not claim/start a task until every ID in blockedBy is done.

Tracker Workflow

Keep ataski/tasks.md as a bullet list in ascending ID order.

Use this line format:

- T001 | todo | title-1 | todo/T001-title-1.md

When task state changes, update both:

  • task frontmatter (status, updated_at, optional owner)
  • matching ataski/tasks.md line

In multiple-worktree flows:

  • The main agent is the only board coordinator.
  • The canonical feature worktree is the only place where the board is writable.
  • Task worktrees MUST treat task files and ataski/tasks.md as read-only.
  • Sub-agents report RED/GREEN results to the main agent; the main agent records that evidence in the task file.
  • The main agent updates the board only when planning/claiming work, and after task branches are merged back.
  • Board-before-PR gate: for completed task work, the main agent MUST update the task to done and sync ataski/tasks.md before opening, updating, or pushing a PR/branch that represents that completed work.
  • Completion-state board updates (ataski/done/ move, task status: done, and ataski/tasks.md sync) MUST be committed on the canonical feature branch so they are included in the PR diff.
  • Completion-state board updates MUST NOT be deferred as a post-merge manual step on main.

Lifecycle Rules

Use directory location and status together:

  1. New task: create in ataski/todo/ with status: todo.
  2. Claimed task: move to ataski/in-progress/ with status: in-progress.
  3. Completed task: move to ataski/done/ with status: done.

Always update updated_at when status or task content changes.

Source-Code Scope and Hard Gates

The rules in this section apply to source-code changes and are hard-gated.

Source-code changes include changes that affect runtime behavior, business logic, test behavior, or execution paths, including examples such as:

  • route rewiring
  • deleting runtime code paths
  • service rewrites
  • data-path migrations
  • changing tests that validate behavior

Chore-only changes are not source-code changes unless they alter behavior, including examples such as:

  • README edits
  • .gitignore edits
  • lockfile updates (unless they intentionally change runtime behavior)
  • formatting-only or comment-only edits

For source-code changes, the agent MUST follow this ordered workflow and MUST NOT skip or reorder the gates:

  1. The main agent creates the task in ataski/todo/ (status: todo).
  2. The main agent writes Requirements and Test Plan in the task file.
  3. The main agent moves the task to ataski/in-progress/ (status: in-progress).
  4. Record RED evidence in the task file, or (if no test-first strategy is truly applicable) document a Test Strategy Exception before source edits. In multiple-worktree flows, sub-agents report this evidence and the main agent records it.
  5. Implement code changes.
  6. Record GREEN evidence in the task file. In multiple-worktree flows, sub-agents report this evidence and the main agent records it.
  7. The main agent moves the task to ataski/done/ (status: done).
  8. The main agent updates ataski/tasks.md to reflect the final completed state and path.

Apply the normal tracker/frontmatter updates when status changes (create/claim/complete). Step 8 is the required final tracker sync/check.

Pre-edit coordination rule (source-code changes):

  • Before any agent edits any source file, the main agent MUST already have created the task, written concrete Requirements and Test Plan sections, and moved the task to ataski/in-progress/.

No retroactive tracking (source-code changes):

  • The main agent MUST NOT create or claim a task after source edits have already started.
  • The main agent MUST NOT create a new completed task for already-finished untracked source-code work.
  • Moving an already-tracked task to done after implementation, validation, and merge is required and is not retroactive tracking.

Test Strategy

Each source-code task MUST choose the test-first method that best matches the work and name it in the Test Plan:

  • Use BDD for user-visible behavior, acceptance criteria, CLI flows, API contracts, and end-to-end scenarios.
  • Use TDD for implementation-level logic, refactors, utility behavior, and tight feedback loops.
  • Use DDD for domain rules, invariants, aggregates, value objects, and business-model correctness.

All three methods still follow the same Red/Green discipline:

  1. RED first: write meaningful failing tests that express the intended behavior, rule, or acceptance criteria.
  2. Record RED evidence in the task file (command + failure summary). In multiple-worktree flows, the main agent records task-file evidence from sub-agent reports.
  3. GREEN second: implement the smallest correct change to satisfy the failing tests.
  4. Record GREEN evidence in the task file (command + pass summary). In multiple-worktree flows, the main agent records task-file evidence from sub-agent reports.
  5. REFACTOR optional: improve the design without changing behavior.

Test gate requirements for source-code changes:

  • RED evidence MUST be recorded before implementation edits.
  • The chosen test method MUST guide the implementation. Tests exist to define correctness, not to turn the task green with shallow validation.
  • Tests MUST be thorough and meaningful for the task's risk and behavior. Write assertions that prove the intended behavior, not placeholder tests that merely execute code.
  • If no test-first method is applicable, add a Test Strategy Exception section in the task file before source edits. This section MUST explain why BDD, TDD, and DDD are all not applicable and what validation will be used instead.
  • A Test Strategy Exception replaces the RED requirement only. It does not waive GREEN validation.
  • GREEN evidence is always required before moving the task to done.
  • For new features, new packages, service rewrites, route rewiring, and other behavior-bearing work, automated tests are mandatory. Build, lint, typecheck, and manual smoke checks alone do NOT satisfy this requirement.
  • Missing test coverage, missing test harnesses, greenfield package setup, or scaffolding work are NOT valid reasons to skip test-first development. The agent MUST first add or extend a test harness, or create a prerequisite task to do so, and then continue with RED/GREEN.
  • A full feature or public package MUST NOT use a blanket Test Strategy Exception to avoid writing tests for its user-visible behavior.
  • If only part of a task cannot be tested first, the exception MUST be narrowly scoped to that part, and the agent MUST still write tests for the remaining behavior or split the work into smaller tasks.

Do not mark task done without passing tests (or the documented exception validation) for source-level work.

Completion Compliance Checklist

Before completing a source-code task, verify all items below:

  • task was created before source edits
  • task requirements and test plan were written before source edits
  • task was moved to in-progress before source edits
  • RED and GREEN evidence were recorded, or a pre-edit Test Strategy Exception plus GREEN evidence was recorded
  • task was moved to done only after implementation and validation were complete

AGENTS.md Interaction

Keep and use the AGENTS.md guidance (see skills/references/AGENTS.md) to mandate Ataski at the project level.

For source-code changes:

  • AGENTS.md provides the project mandate/policy to use Ataski.
  • The ataski skill provides the exact operational procedure, lifecycle ordering, and hard gates.
  • If AGENTS.md says to use Ataski, then the Ataski lifecycle and testing/compliance gates in this skill are mandatory.

Multi-Agent Coordination

Core rules:

  1. The main agent is the coordinator.
  2. The main agent owns the canonical feature worktree and the only active ataski/ board.
  3. The canonical worktree MUST use the parent feature branch (example: feature/faucet-cli).
  4. The main agent creates one task worktree per task branch under worktreesDir (example branch: task/T001-short-title).
  5. Sub-agents work only in task worktrees.
  6. Sub-agents never edit the board.
  7. The main agent merges task branches and updates the board.

Follow this sequence:

  1. The main agent creates the canonical feature branch/worktree first.
  2. The main agent prepares the board there and creates the tasks.
  3. The main agent claims only tasks whose blockedBy entries are already done.
  4. For each claimable parallel task, the main agent creates a dedicated task branch/worktree from the canonical feature branch.
  5. The main agent assigns exactly one sub-agent to each task worktree.
  6. Each sub-agent implements only its assigned task and reports completion.
  7. The main agent reviews and merges each completed task branch back into the canonical feature branch.
  8. After each merge, the main agent updates the task on the canonical board to done in the canonical feature branch, commits that board change, then re-checks which blocked tasks are now claimable.
  9. Once all task branches are merged, the main agent reviews the complete feature from the canonical feature worktree.
  10. The main agent opens or updates the final review/PR from the canonical feature branch.

Coordination constraints:

  • Do not claim blocked tasks.
  • Do not claim more than one task per agent or sub-agent at a time.
  • Only the main agent edits ataski/.
  • Sub-agents MUST NOT create, claim, move, or complete tasks.
  • Sub-agents MUST NOT commit changes under ataski/.
  • Sub-agents MUST NOT open, update, or push PR branches.
  • The main agent MUST include done-state board updates in the canonical feature PR branch; never apply them only after merge on main.
  • Do not edit unrelated task files unless explicitly requested.
  • If two agents race for the same task, the first canonical board update wins; other agents must re-pick from todo.

Plan Mode

When an agent is operating in plan mode:

  • The agent MUST use Ataski to represent the plan.
  • Every meaningful plan item MUST be written as an Ataski task.
  • The plan MUST be split into the maximum safe level of parallelizable tasks.
  • The plan is not complete until the Ataski tasks capture the full intended work.
  • Do not keep extra implementation plan steps outside the Ataski board.

Git/worktree policy prerequisite:

  • If project policy (for example AGENTS.md) requires git and/or worktrees for task execution and they are unavailable, the agent MUST stop before source edits and ask the user to initialize git or enable the required worktree workflow.

平台分布

Codex

39.17%
按下载量换算28

Claude

28.53%
按下载量换算20

Cursor

17.98%
按下载量换算13

Gemini CLI

10.3%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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