← 返回 Skills 市场
johannesseikowsky

bluesky-skill

作者 Johannes · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
219
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install bluesky-skill
功能描述
Manage a Bluesky (bsky) account — posting, replies, likes, reposts, follows, blocks, mutes, search, timeline, threads, notifications, DMs, and profile update...
使用说明 (SKILL.md)

Bluesky Account Management

Operate a Bluesky social media account via ./bsky \x3Ccommand> [args]. All output is JSON. Run from the project root.

Setup

Install dependencies:

pip install atproto python-dotenv

Requires .env at project root:

BLUESKY_HANDLE=your-handle.bsky.social
BLUESKY_APP_PASSWORD=xxxx-xxxx-xxxx-xxxx

App passwords: https://bsky.app/settings/app-passwords. For DMs, enable "Allow access to your direct messages".

Auth is automatic. A session cache is stored at ~/.bsky_session.json (contains an exported session token). Delete this file to force re-authentication or when revoking access.

JSON Output

Every command prints one JSON object to stdout. Parse with json.loads().

Response Schemas

Post object (returned by get, and inside arrays from timeline, search-posts, my-posts, thread):

{
  "uri": "at://did:plc:abc/app.bsky.feed.post/xyz",
  "cid": "bafyrei...",
  "author": {"handle": "alice.bsky.social", "did": "did:plc:abc", "display_name": "Alice", "avatar": "https://..."},
  "text": "Post content here",
  "created_at": "2026-03-14T10:00:00Z",
  "like_count": 5, "repost_count": 2, "reply_count": 1,
  "viewer": {"liked": "at://...like-uri or null", "reposted": "at://...repost-uri or null"},
  "embed": {"images": [{"alt": "...", "thumb": "...", "fullsize": "..."}], "external": {"uri": "...", "title": "...", "description": "..."}, "record": {"uri": "...", "text": "...", "author": {...}}} or null,
  "reply": {"parent_uri": "at://...", "root_uri": "at://..."} // only present on replies
}

Profile object (returned by profile, and inside arrays from search-users):

{
  "handle": "alice.bsky.social", "did": "did:plc:abc",
  "display_name": "Alice", "description": "Bio text", "avatar": "https://...",
  "followers_count": 100, "follows_count": 50, "posts_count": 200,
  "viewer": {"following": "at://...or null", "followed_by": "at://...or null", "blocking": null, "blocked_by": null, "muted": null}
}

Actor object (short profile, inside post authors, follower/following lists, notification authors):

{"handle": "alice.bsky.social", "did": "did:plc:abc", "display_name": "Alice", "avatar": "https://..."}

Notification object (inside array from notifications):

{
  "reason": "reply|like|repost|follow|mention|quote",
  "uri": "at://...", "cid": "bafyrei...", "is_read": false,
  "indexed_at": "2026-03-14T10:00:00Z",
  "author": {"handle": "...", "did": "...", "display_name": "...", "avatar": "..."},
  "record_text": "Their reply/post text (if applicable)",
  "reason_subject": "at://...the post they liked/reposted/replied-to (if applicable)",
  "subject_text": "Text of the subject post (if reason_subject exists)"
}

Conversation object (inside array from dm-list):

{
  "id": "convo-id", "unread_count": 2,
  "members": [{"handle": "...", "did": "...", "display_name": "...", "avatar": "..."}],
  "last_message": {"id": "msg-id", "text": "...", "sent_at": "...", "sender_did": "did:plc:..."} or null
}

DM message object (inside array from dm-read):

{"id": "msg-id", "text": "Message text", "sent_at": "2026-03-14T10:00:00Z", "sender_did": "did:plc:..."}

Feed object (inside array from feeds):

{
  "uri": "at://did:plc:abc/app.bsky.feed.generator/whats-hot",
  "cid": "bafyrei...", "did": "did:web:...",
  "creator": {"handle": "...", "did": "...", "display_name": "...", "avatar": "..."},
  "display_name": "What's Hot", "description": "Trending posts across Bluesky",
  "avatar": "https://...", "like_count": 12345, "indexed_at": "2026-03-14T10:00:00Z"
}

Command Response Keys

Each command returns these top-level keys:

Command Response keys
post {"uri", "cid"}
delete {"deleted"} (the URI)
like {"liked", "uri"} (post URI + like record URI)
unlike {"unliked"}
repost {"reposted", "uri"} (post URI + repost record URI)
unrepost {"unreposted"}
timeline {"feed": [{"post": \x3Cpost>, "reason": {"type": "repost", "by": \x3Cactor>} or null}], "cursor"}
thread {"thread": \x3Cpost with nested "replies": [...]>}
search-posts {"posts": [\x3Cpost>], "cursor"}
search-users {"actors": [\x3Cprofile>], "cursor"}
follow {"followed", "uri"}
unfollow {"unfollowed"}
followers {"followers": [\x3Cactor>], "cursor"}
following {"following": [\x3Cactor>], "cursor"}
mute {"muted"}
unmute {"unmuted"}
block {"blocked", "uri"}
unblock {"unblocked"}
profile \x3Cprofile> (top-level, no wrapper)
get \x3Cpost> (top-level, no wrapper)
my-posts {"posts": [\x3Cpost>], "cursor"}
user-posts {"posts": [\x3Cpost>], "cursor"}
likes {"likes": [{"actor": \x3Cactor>, "created_at": "..."}], "cursor"}
reposts {"reposted_by": [\x3Cactor>], "cursor"}
notifications {"notifications": [\x3Cnotification>], "cursor"}
notif-read {"success": true}
dm-list {"conversations": [\x3Cconvo>], "cursor"}
dm-read {"convo_id", "messages": [\x3Cdm>], "cursor"}
dm-send {"sent": true, "convo_id", "message_id"}
dm-mark-read {"success": true}
update-profile \x3Cprofile> (top-level, no wrapper)
post-thread {"posts": [{"uri", "cid"}, ...]}
feeds {"feeds": [\x3Cfeed>], "cursor"}

Important: Note that timeline wraps posts in feed[].post (with an optional reason), while search-posts and my-posts use posts[] directly.

Pagination

List commands support --cursor TOKEN. The response includes "cursor" (null = no more results).

  1. First call: omit --cursor
  2. Next page: pass the returned cursor as --cursor
  3. Stop when cursor is null

Errors

Errors return JSON with exit code 1:

{"error": "ERROR_TYPE", "message": "Human-readable description", "type": "SUBTYPE (for AUTH_ERROR)"}

Error types: NOT_FOUND, NOT_LIKED, NOT_REPOSTED, NOT_FOLLOWING, NOT_BLOCKING, FILE_NOT_FOUND, INVALID_ARGS, AUTH_ERROR.

Command Quick Reference

Posting

Command Description
post "text" Create a text post (max 300 graphemes)
post "text" --image photo.jpg --alt "description" Post with image (repeat --image/--alt for up to 4)
post "text" --reply-to \x3Curi> Reply to a post
post "text" --quote \x3Curi> Quote a post
post "text" --quote \x3Curi> --image photo.jpg --alt "desc" Quote with image
post-thread "text1" "text2" "text3" Create a multi-post thread
delete \x3Curi> Delete a post

Engagement

Command Description
like \x3Curi> Like a post
unlike \x3Curi> Unlike (pass the post URI, not the like URI)
repost \x3Curi> Repost a post
unrepost \x3Curi> Undo repost (pass the post URI)

Reading & Discovery

Command Description
timeline [--limit N] [--cursor TOKEN] Home timeline (default 20)
thread \x3Curi> [--depth N] Post thread with replies (default depth 6)
search-posts "query" [--limit N] [--cursor TOKEN] Search posts
search-users "query" [--limit N] [--cursor TOKEN] Search users
feeds [--query "keyword"] [--limit N] [--cursor TOKEN] Browse suggested feed generators (note: --query filters client-side, so results may be fewer than --limit)

Social Graph

Command Description
follow \x3Chandle> Follow
unfollow \x3Chandle> Unfollow
followers \x3Chandle> [--limit N] [--cursor TOKEN] List followers
following \x3Chandle> [--limit N] [--cursor TOKEN] List following
mute \x3Chandle> / unmute \x3Chandle> Mute/unmute
block \x3Chandle> / unblock \x3Chandle> Block/unblock

Profile & Info

Command Description
profile [handle] View profile (own if omitted)
update-profile [--name "Name"] [--bio "Bio"] [--avatar image.jpg] Update your profile
my-posts [--limit N] [--cursor TOKEN] Own recent posts
user-posts \x3Chandle> [--limit N] [--cursor TOKEN] A user's recent posts
get \x3Curi> Fetch a single post
likes \x3Curi> [--limit N] [--cursor TOKEN] Who liked a post
reposts \x3Curi> [--limit N] [--cursor TOKEN] Who reposted a post

Notifications

Command Description
notifications [--limit N] [--unread-only] [--filter TYPE] [--cursor TOKEN] List notifications (filter: like, repost, follow, mention, reply, quote)
notif-read Mark all as read

Direct Messages

Command Description
dm-list [--limit N] [--cursor TOKEN] List conversations
dm-read --handle \x3Chandle> [--limit N] [--cursor TOKEN] Read messages with a user
dm-read --convo-id \x3Cid> [--limit N] [--cursor TOKEN] Read messages by convo ID
dm-send \x3Chandle> "text" Send a DM
dm-mark-read --convo-id \x3Cid> Mark convo as read
dm-mark-read --all Mark all as read

Only text DMs are supported (no images).

Common Workflows

Check and respond to mentions

./bsky notifications --unread-only --filter mention
# Parse → for each notification, extract reason_subject (the post they mentioned you in)
./bsky get \x3Creason_subject_uri>
# Read context, then reply:
./bsky post "Your reply" --reply-to \x3Curi>
./bsky notif-read

Engage with timeline

./bsky timeline --limit 30
# Parse → extract feed[].post objects
# Like interesting posts:
./bsky like \x3Curi>
# Reply to engage:
./bsky post "Your reply" --reply-to \x3Curi>

Search and engage with a topic

./bsky search-posts "topic keywords" --limit 20
# Parse → like/repost/reply to relevant posts[]
./bsky like \x3Curi>
./bsky repost \x3Curi>

Join a conversation (read thread before replying)

./bsky thread \x3Curi> --depth 6
# Parse → read thread.text and thread.replies[] to understand context
./bsky post "Informed reply" --reply-to \x3Curi>

Grow the network

./bsky search-users "topic or niche" --limit 20
# Parse → review actors[] profiles for relevance
./bsky profile \x3Chandle>
# Check their posts before following:
./bsky user-posts \x3Chandle> --limit 10
# Avoid re-following — check viewer.following is null, then:
./bsky follow \x3Chandle>

Check engagement on own posts

./bsky my-posts --limit 10
# Parse → find posts with high reply_count
./bsky thread \x3Curi>
# Respond to replies, like engaged followers
./bsky likes \x3Curi>

Check and respond to DMs

./bsky dm-list
# Parse → find conversations[] with unread_count > 0
./bsky dm-read --convo-id \x3Cid>
# Parse → read messages[], reply:
./bsky dm-send \x3Chandle> "Your reply"
./bsky dm-mark-read --convo-id \x3Cid>

Post a thread

./bsky post-thread "First, let me explain the context..." "Second, here's the main point..." "Finally, the conclusion."
# Returns: {"posts": [{"uri": "...", "cid": "..."}, ...]}

Update your profile

./bsky update-profile --name "New Display Name" --bio "Updated bio text"
./bsky update-profile --avatar new-avatar.jpg

Discover feeds

./bsky feeds --limit 10
# Filter by keyword:
./bsky feeds --query "news"

Check before posting (avoid duplicates)

./bsky my-posts --limit 5
# Parse → check posts[].text for similar content
./bsky post "New post text"

Key Concepts

  • Handles: Always pass handles without the @ prefix — use user.bsky.social, not @user.bsky.social.
  • URIs: Every post has an AT Protocol URI (at://did:plc:abc/app.bsky.feed.post/xyz). Extract from the uri field in JSON. Used as arguments for like, reply, repost, thread, get, delete.
  • Rich text: @mentions, #hashtags, URLs in post text are auto-converted to links. Write naturally.
  • Character limit: 300 graphemes per post.
  • Unlike/unrepost: Pass the post URI, not the like/repost record URI. Auto-resolved internally.
  • Reply threading: --reply-to \x3Curi> auto-resolves the thread root.

Auth Troubleshooting

Auth errors: {"error": "AUTH_ERROR", "type": "\x3CTYPE>", "message": "..."} with exit code 1.

  1. SESSION_CORRUPTrm ~/.bsky_session.json and retry
  2. MISSING_ENV → Ensure .env has BLUESKY_HANDLE and BLUESKY_APP_PASSWORD
  3. INVALID_CREDENTIALS → Handle: user.bsky.social, App password: xxxx-xxxx-xxxx-xxxx (19 chars)
  4. NETWORK → Retry up to 3 times with 10s delay
  5. ACCOUNT_SUSPENDED → Inform user, cannot fix programmatically
安全使用建议
This skill appears to be what it claims: a Python CLI to manage a Bluesky account. Before installing or using it: (1) Understand that providing BLUESKY_HANDLE and BLUESKY_APP_PASSWORD gives the skill full control of your account (including DMs if enabled). Treat the app password like a secret. (2) The tool stores an exported session token at ~/.bsky_session.json — delete that file to force logout or revoke access. (3) The SKILL.md asks you to pip install dependencies — prefer a virtualenv or inspect the packages (atproto, python-dotenv) before installing. (4) The skill's source file is included (scripts/bsky.py); if you don't trust the publisher (no homepage provided), review that file yourself or run the CLI in an isolated environment. (5) If you plan to allow autonomous invocation by an agent, remember the agent could perform any account action using these credentials. If any of those points are unacceptable, do not install or provide your credentials.
功能分析
Type: OpenClaw Skill Name: bluesky-skill Version: 1.0.1 The skill bundle provides a functional CLI for managing Bluesky accounts using the AT Protocol. The implementation in `scripts/bsky.py` uses the standard `atproto` library for all operations, including authentication, posting, and direct messaging. It handles credentials via environment variables and implements a local session cache in the user's home directory (`~/.bsky_session.json`). The code logic is transparent, lacks obfuscation, and aligns perfectly with the stated purpose in `SKILL.md` without any evidence of malicious intent or data exfiltration to unauthorized third parties.
能力评估
Purpose & Capability
Name/description (manage a Bluesky account) matches the requested binaries (python3), the two env vars (BLUESKY_HANDLE, BLUESKY_APP_PASSWORD), and the included Python CLI that calls the AT Protocol client. Nothing unrelated (e.g., cloud provider keys) is requested.
Instruction Scope
SKILL.md instructs running the included ./bsky Python CLI and installing atproto and python-dotenv. It requires a .env with the handle and app password and documents a session cache at ~/.bsky_session.json. The instructions stay within the Bluesky use case but explicitly require writing/reading credentials and a session token on disk; that is expected for this functionality but is sensitive.
Install Mechanism
No formal install spec; SKILL.md suggests pip install of atproto and python-dotenv. This is normal for a Python-only tool, but pip installs execute code from PyPI — run inside a virtualenv or inspect packages before installing. The repo does include the Python CLI source (scripts/bsky.py); there are no external downloads or obscure install URLs.
Credentials
Only two env vars (BLUESKY_HANDLE and BLUESKY_APP_PASSWORD) are required, which are exactly the credentials needed to operate the account. However, those credentials grant full account control (posts, follows, DMs, blocks, etc.), so they are high privilege and should be provided only to trusted code.
Persistence & Privilege
always:false (no forced inclusion). The skill creates a session cache at ~/.bsky_session.json containing an exported session token; this is persistent across runs and should be removed to revoke access. The skill does not request system-wide config modifications beyond that file.
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 bluesky-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /bluesky-skill 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
v1.0.1
**Initial public release with improved setup instructions and dependency management.** - Added pip install instructions for required dependencies (`atproto`, `python-dotenv`) - Detailed location and handling of session cache for authentication - Clarified setup steps for `.env` usage and app passwords - All other command references and response schemas remain unchanged
v1.0.0
Initial release: Manage your Bluesky account from the command line with JSON output for automation and scripting. - Post, reply, quote, delete, like, unlike, repost, unrepost, and create threads. - Search posts and users, view timelines and threads, and browse feed generators. - Manage follows, unfollows, mutes, blocks, and profile updates. - Read and send DMs, manage notifications, and view engagement metrics. - Supports pagination and robust error handling with consistent JSON schemas.
元数据
Slug bluesky-skill
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

bluesky-skill 是什么?

Manage a Bluesky (bsky) account — posting, replies, likes, reposts, follows, blocks, mutes, search, timeline, threads, notifications, DMs, and profile update... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 219 次。

如何安装 bluesky-skill?

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

bluesky-skill 是免费的吗?

是的,bluesky-skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

bluesky-skill 支持哪些平台?

bluesky-skill 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 bluesky-skill?

由 Johannes(@johannesseikowsky)开发并维护,当前版本 v1.0.1。

💬 留言讨论