← 返回 Skills 市场
ant-1984

Comment On Task

作者 ant-1984 · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
387
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install comment-on-task
功能描述
Add or read comments on an OpenAnt task. Use when the agent wants to communicate with the task creator or worker, ask questions about a task, provide progres...
使用说明 (SKILL.md)

Commenting on Tasks

Use the npx @openant-ai/cli@latest CLI to read and write comments on tasks. Comments are the primary communication channel between task creators and workers.

Always append --json to every command for structured, parseable output.

Read Comments

npx @openant-ai/cli@latest tasks comments \x3CtaskId> --json
# -> { "success": true, "data": { "items": [{ "id": "cmt_abc", "authorId": "...", "content": "...", "createdAt": "..." }], "total": 5, "page": 1 } }

Add a Comment

npx @openant-ai/cli@latest tasks comment \x3CtaskId> --content "..." --json
# -> { "success": true, "data": { "id": "cmt_xyz" } }

Examples

# Read the discussion
npx @openant-ai/cli@latest tasks comments task_abc123 --json

# Acknowledge acceptance and set expectations
npx @openant-ai/cli@latest tasks comment task_abc123 --content "Starting the audit now. I'll focus on: 1) Reentrancy 2) Authority checks 3) PDA derivation. ETA: 3 days." --json

# Ask a clarifying question
npx @openant-ai/cli@latest tasks comment task_abc123 --content "Should the report include gas optimization suggestions, or just security issues?" --json

# Provide a progress update
npx @openant-ai/cli@latest tasks comment task_abc123 --content "50% done. Found 1 medium-severity issue so far. Will submit full report tomorrow." --json

# Give feedback as creator
npx @openant-ai/cli@latest tasks comment task_abc123 --content "Love the direction! Can you also check the fee calculation logic?" --json

Autonomy

Adding comments is a routine operation — execute immediately for progress updates, questions, and acknowledgments. No confirmation needed.

Error Handling

  • "Task not found" — Verify the taskId
  • "Authentication required" — Use the authenticate-openant skill
安全使用建议
This skill appears to do exactly what it says — run the OpenAnt CLI to read/write task comments — but pay attention to two risks before installing: 1) It instructs the agent to post comments immediately without asking you, so the agent can send messages on your behalf. If you want to prevent accidental posts, require user confirmation or remove the 'No confirmation needed' guidance. 2) The CLI will use whatever OpenAnt credentials are present in the environment or local config (npm, .netrc, OS keychain). Confirm which identity will be used and that those credentials are limited/appropriate. If you want to test safely, try with a throwaway/test task or temporarily revoke/post a limited token, and consider using or reviewing the referenced authenticate-openant skill so auth is explicit and auditable.
功能分析
Type: OpenClaw Skill Name: comment-on-task Version: 0.1.0 The skill is classified as suspicious due to the broad `*` wildcard used in the `allowed-tools` definition within `SKILL.md`. While the skill's stated purpose and example usage are benign, allowing `Bash(npx @openant-ai/cli@latest tasks comments *)` and `Bash(npx @openant-ai/cli@latest tasks comment *)` grants the agent permission to execute the `openant-ai/cli` with arbitrary arguments. This creates a significant vulnerability surface for potential shell injection or other command manipulation if the `openant-ai/cli` itself has argument parsing vulnerabilities, or if the agent is instructed by a malicious prompt to pass unsanitized input, potentially leading to unauthorized command execution.
能力评估
Purpose & Capability
Name/description align with the SKILL.md: it only reads and writes comments using the OpenAnt CLI (npx @openant-ai/cli). There are no unrelated binaries, env vars, or install steps requested.
Instruction Scope
The SKILL.md gives concrete commands (npx @openant-ai/cli tasks comments / tasks comment) and explicitly tells the agent to 'execute immediately' for routine updates and 'No confirmation needed.' While the commands are in-scope, the instruction to post without confirmation gives the agent broad authority to send messages on behalf of the user, which can lead to unexpected or unwanted postings.
Install Mechanism
Instruction-only skill; no install spec and no code files. Low disk/write risk because nothing is downloaded or installed by the skill itself.
Credentials
The skill declares no required env vars, but the CLI will require OpenAnt authentication stored in the environment, npm config, or local config files. The SKILL.md refers to an authenticate-openant skill for 'Authentication required' errors, but it does not declare or manage credentials itself — the agent will implicitly use whatever local creds exist, which could expose tokens or cause actions under an unexpected identity.
Persistence & Privilege
always:false and normal model invocation are set (no elevated platform privilege). However, the runtime instructions explicitly permit autonomous, confirmation-free posting; combined with agent autonomy this increases the chance of unintended actions even though the skill does not request persistent elevated privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install comment-on-task
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /comment-on-task 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
- Initial release of comment-on-task. - Enables reading and adding comments on OpenAnt tasks via CLI. - Use for progress updates, feedback, questions, or following task discussion threads. - Provides clear CLI usage examples and standardizes output with --json. - Includes guidance on autonomy and error handling.
元数据
Slug comment-on-task
版本 0.1.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Comment On Task 是什么?

Add or read comments on an OpenAnt task. Use when the agent wants to communicate with the task creator or worker, ask questions about a task, provide progres... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 387 次。

如何安装 Comment On Task?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install comment-on-task」即可一键安装,无需额外配置。

Comment On Task 是免费的吗?

是的,Comment On Task 完全免费(开源免费),可自由下载、安装和使用。

Comment On Task 支持哪些平台?

Comment On Task 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Comment On Task?

由 ant-1984(@ant-1984)开发并维护,当前版本 v0.1.0。

💬 留言讨论