← 返回 Skills 市场
X Reply Unreplied
作者
Dishant Sharma
· GitHub ↗
· v1.1.2
· MIT-0
209
总下载
0
收藏
0
当前安装
12
版本数
在 OpenClaw 中安装
/install x-reply-unreplied
功能描述
Check X notifications, mentions, or reply threads and answer posts that still need a response from the user. Use when the user wants help replying to unrepli...
安全使用建议
This skill appears to do what it says: review X notifications and post very short replies. Before installing, confirm the platform provides the OpenClaw-managed browser and that it will be logged into the correct X account — the skill will act in that browser session and post as you. If you do not want automated posting, only use the skill manually or review drafts before posting. Also verify you are comfortable with the 'like before drafting' and non-refresh rules. If you need more assurance, ask the developer to declare the browser dependency explicitly and to document how authentication is handled.
功能分析
Type: OpenClaw Skill
Name: x-reply-unreplied
Version: 1.1.2
The skill bundle is designed to automate the process of replying to X (Twitter) notifications and mentions using a managed browser. The instructions in SKILL.md and the reference files (inbox-workflow.md, reply-rules.md) focus on maintaining a specific, human-like workflow, enforcing short reply lengths, and ensuring resource cleanup by closing browser tabs. There are no indicators of data exfiltration, malicious command execution, or harmful prompt injection; the use of 'CRITICAL NON-NEGOTIABLE' directives is aimed at task consistency and preventing spam-like behavior rather than subverting security controls.
能力评估
Purpose & Capability
The name and description match the instructions: the skill is explicitly about reviewing X (formerly Twitter) notifications and posting short replies. It reasonably requires browser interaction and an authenticated account, but the registry metadata lists no required binaries or credentials even though the SKILL.md mandates using the 'openclaw browser start' command and posting as the user. This is a minor mismatch: the skill assumes the platform provides the managed browser and an active logged-in session but does not declare that dependency.
Instruction Scope
The SKILL.md stays on-topic: it instructs the agent to open the managed browser, navigate X notifications, read threads, draft one- or two-sentence replies, and post them. It does not ask to read unrelated files or environment variables. It does require the agent to like posts and to post replies on the user's behalf, and enforces non-refresh and sequence rules — these are operational constraints rather than scope creep.
Install Mechanism
This is an instruction-only skill with no install spec or code to download — low install risk. Nothing will be written to disk by an installer as part of this skill.
Credentials
The skill declares no environment variables or credentials, which is coherent for an instruction-only skill. However, it implicitly requires an authenticated browser session (cookies/credentials stored in the managed browser) to post on the user's behalf. The skill does not request or document how authentication is provided; users should verify the managed browser will be logged into the correct account and that they are comfortable allowing the agent to act in that session.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system modifications or cross-skill configuration changes. It is user-invocable and the agent can invoke it autonomously (platform default), which is expected for this type of automation.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install x-reply-unreplied - 安装完成后，直接呼叫该 Skill 的名称或使用
/x-reply-unreplied触发 - 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
v1.1.2
No changes detected in this version.
- Version 1.1.2 was released with no modifications to existing files or documentation.
v1.1.1
- Updated workflow to require launching the browser using the openclaw command: `openclaw browser start`.
- Clarified as a CRITICAL NON-NEGOTIABLE that only this browser launch method must be used, adding extra guidance to step 1.
- No changes to logic, functionality, or other skill usage instructions.
v1.1.0
Version 1.1.0 of x-reply-unreplied
- No file changes detected; documentation and skill description remain unchanged.
- Maintains concise, manual reply handling guidelines for X (formerly Twitter) notifications and mentions.
- Continues to enforce strict limitations on reply length and workflow order.
- Criteria for skipping threads and the completion report process remain as previously detailed.
v1.0.9
Version 1.0.9 of x-reply-unreplied
- No file changes detected in this release.
- All documentation and process details remain unchanged from the previous version.
v1.0.8
- No changes detected in this version.
- Skill functionality, workflow, and documentation remain the same as the previous version.
v1.0.7
- No changes detected in this version.
- The SKILL.md content remains unchanged from the previous version.
v1.0.5
Version 1.0.5 (no file changes detected)
- No code or documentation updates in this release.
- All usage instructions and workflow remain unchanged.
v1.0.4
Version 1.0.4 of x-reply-unreplied
- No file changes detected in this version.
- No updates to features, workflow, or skip conditions.
- No changes to documentation or user-facing functionality.
v1.0.3
- Now requires liking the post before drafting or replying in each candidate thread.
- Updated workflow steps to include the new like action before reply.
- No other workflow or skip/reporting requirements changed.
v1.0.2
- Clarified that X (Twitter) must be opened using openclaw managed chrome.
- Added a strict rule: never refresh or reload the notifications page; use only clicks and the back button to navigate.
- Updated the workflow and completion steps for clearer tab management, requiring immediate closure of all x.com tabs after completion.
- Improved wording to emphasize sequential thread processing and stricter navigation discipline.
v1.0.1
- Clarified and emphasized that all replies must be 1–2 short sentences; this rule is now marked "CRITICAL NON-NEGOTIABLE."
- Explicitly stated that relaxing the reply length is never allowed unless the user directly requests longer replies.
- Added new "CRITICAL NON-NEGOTIABLE" instructions to process only one thread at a time and to fully finish handling each thread before moving to the next.
- No changes to core workflow or reply criteria.
v1.0.0
- Initial release of x-reply-unreplied skill.
- Allows users to efficiently answer X (Twitter) mentions or thread replies that still need a response.
- Handles up to 5 relevant reply opportunities per run by default.
- Replies use a short, first-person, on-topic style (1–2 sentences).
- Includes guidance on when to skip replying (e.g., abuse, spam, or already answered).
- Provides a completion report summarizing actions taken, replies sent, and items skipped.
元数据
常见问题
X Reply Unreplied 是什么？
Check X notifications, mentions, or reply threads and answer posts that still need a response from the user. Use when the user wants help replying to unrepli... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 209 次。
如何安装 X Reply Unreplied？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install x-reply-unreplied」即可一键安装，无需额外配置。
X Reply Unreplied 是免费的吗？
是的，X Reply Unreplied 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
X Reply Unreplied 支持哪些平台？
X Reply Unreplied 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 X Reply Unreplied？
由 Dishant Sharma（@dishant0406）开发并维护，当前版本 v1.1.2。
推荐 Skills