Bluesky Post logo

Bluesky Post

Organization
publora
bluesky-post

Use when the user wants to post or schedule to Bluesky through Publora. Handles the 300-character cap, auto-detected hashtags and links, up to 4 images, and videos. Alt text cannot be set through the API. Needs a Bluesky app password, never the main password. Not for Mastodon (use social-post).

Overview

Publisherpublora
Repositoryskills
Skill namebluesky-post
Stars
62
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by publora on GitHub. Read the source before you install it.

Installation

Install the Bluesky Post AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/publora/skills/tree/main/skills/bluesky-post
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/publora/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/bluesky-post .claude/skills/bluesky-post
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bluesky Post in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bluesky Post on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bluesky Post is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bluesky Post

Create and schedule posts to Bluesky using the Publora MCP server. Supports text posts with auto-detected hashtags and URLs, images and videos.

Prerequisites

Plans: Works on the free Starter plan. Current limits and pricing: publora.com/pricing.

Getting Started

  1. Create account at publora.com/register (free)
  2. Generate app password in Bluesky Settings > App Passwords (NOT your main password)
  3. Connect Bluesky in Publora Dashboard using your handle + app password
  4. Get an API key at app.publora.com/dashboard/api, only if your agent cannot sign in with OAuth or you will use the REST API fallback below
  5. Connect your agent to the MCP server at https://mcp.publora.com/mcp:
    • Upgrading a manual connection without /mcp: Claude treats https://mcp.publora.com as a different server from the bundled one. Change that existing connection to https://mcp.publora.com/mcp in its current scope, preserving its authentication and chosen account; sign in again if requested. Alternatively, verify the bundled connection uses the intended account, then remove only the old manual entry. Do not add a second entry or delete credentials automatically.
    • Publora tools already available (the publora-skills plugin or the Publora connector in Claude): nothing to set up. Claude asks you to sign in to Publora the first time a tool runs.
    • Agents that support OAuth (Claude Code, Cursor, and the Claude and ChatGPT apps): add the server by URL and sign in, no API key needed. In Claude Code, add it and then run /mcp to sign in:
bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp
  • Agents without OAuth: send the API key as Authorization: Bearer sk_YOUR_API_KEY:
bash
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp \
  --header "Authorization: Bearer sk_YOUR_API_KEY"

Claude Desktop, Cursor, Codex, OpenClaw and the claude.ai connector each need a different config file or flow: see client setup for the exact path and snippet.

REST API Fallback

If the MCP server is unavailable or returns errors, use the REST API directly:

Base URL: https://api.publora.com/api/v1

Authentication: Use x-publora-key header (NOT Authorization: Bearer):

bash
# Get your connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
  -H "x-publora-key: sk_your_api_key"

# Create a post
curl -X POST "https://api.publora.com/api/v1/create-post" \
  -H "x-publora-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "platforms": ["bluesky-did:plc:abc123xyz"],
    "content": "Your post content here",
    "scheduledTime": "2026-03-25T10:00:00Z"
  }'

Platform ID Format: bluesky-{did} where {did} is from /platform-connections response.

Example IDs: bluesky-did:plc:abc123xyz, bluesky-did:plc:def456uvw

📖 Full API documentation: docs.publora.com

Platform Limits

FeatureLimit
Characters300
ImagesUp to 4 per post
Image sizeexactly 2,000,000 bytes (decimal, not 2 MiB)
Video duration3 minutes
Video size50-100 MB (based on duration)
Videos per day25
Alt text2,000 characters on Bluesky itself, but not settable through this API (see below)

Video Size Tiers

DurationMax Size
Under 60s50 MB
60s - 3min100 MB

Rich Text Facets

Bluesky uses a unique rich text system. Publora handles the complexity automatically:

  • Hashtags: #hashtag auto-detected and made clickable
  • URLs: Any URL auto-detected and made clickable
  • Byte offsets: Calculated correctly for multi-byte characters (emojis, CJK)

No special formatting needed - just write naturally.

Available Tools

create_post

Create a new Bluesky post.

Parameters:

  • platforms: Array with your Bluesky connection ID (e.g., ["bluesky-did:plc:abc123xyz"])
  • content: Post text (up to 300 characters)
  • scheduledTime: ISO 8601 UTC datetime. Optional: omit it and the post is created as a draft. Send a future time to schedule. A time five or more minutes in the past is rejected with SCHEDULED_TIME_IN_PAST, so for immediate posting use the current time plus a minute.
  • mediaUrls: up to 10 public https image or video URLs. Publora downloads them server-side and attaches them before validation, so media and scheduling happen in one call. This is the one-shot alternative to the draft then get_upload_url then complete_media flow. Ingestion is rate-limited to 60 URLs per hour.

get_upload_url

Get presigned URL for media uploads.

Parameters:

  • postGroupId: Post ID to attach media to
  • fileName: File name (e.g., "photo.jpg")
  • contentType: image/jpeg, image/png, video/mp4
  • type: "image" or "video"

complete_media

Finalize a file uploaded through get_upload_url, after the presigned PUT succeeds. Optional, because scheduling also finalizes pending media, but calling it early surfaces format and probe errors before publish. Not needed for media attached with mediaUrls.

Parameters:

  • mediaId: the id returned by get_upload_url

list_connections

List your connected accounts with their platform IDs. Call this first and copy the IDs verbatim; they are never guessable.

post_stats

Engagement counters for a published Bluesky post: reactions, comments, reposts, quotes and bookmarks. Live at request time, cached for roughly two hours.

Parameters:

  • platform: bluesky
  • platformId: your Bluesky connection ID
  • postedIds: the published post ids to look up

profile_stats

Followers, following and post count for the connected account.

Parameters:

  • platform: bluesky
  • platformId: your Bluesky connection ID

list_posts / get_post / update_post / delete_post

Manage scheduled and draft posts. update_post also patches content and platforms on a draft or scheduled post, so fixing a typo or retargeting no longer means delete and recreate. delete_media and prune_media_reference clean up uploaded files.

Examples

Simple Post with Hashtags

Post this to Bluesky:
"Just launched our new API documentation! Check it out at https://docs.example.com #devtools #api"

Hashtags and URLs are automatically made clickable.

Post with Image

Post this to Bluesky with a dashboard screenshot:
"Our new analytics view is live! #buildinpublic"

Multiple Images

Create a Bluesky post with before/after comparison images:
"Office renovation complete! What a transformation."

Note: Up to 4 images allowed per post.

Video Post

Post this 60-second demo video to Bluesky:
"Quick tour of our new mobile app features"

Scheduled Post

Schedule this for tomorrow at 10 AM:
"Good morning! Here's your daily productivity tip..."

Important Restrictions

  1. Alt text cannot be set through the API. The Bluesky publisher reads an alt property on media, but nothing persists it: neither the presigned upload flow nor mediaUrls stores it, and an altTexts value sent to create-post is silently ignored. platformSettings is no help either, since Bluesky is rejected there with 400 PLATFORM_SETTING_UNKNOWN. Post the image, then add alt text in the Bluesky app. Do not tell the user their alt text was published.

  2. App password required: You must use a Bluesky app password, NOT your main account password. Generate one at Settings > App Passwords.

  3. All images converted to JPEG: Regardless of input format (PNG, WebP, GIF), all images are converted to JPEG before upload.

  4. Hard 2,000,000-byte image limit: the AT Protocol enforces an exact decimal byte ceiling, not a rounded 2 MiB. Compress to 80-85% JPEG quality and check the byte count.

  5. DID-based platform ID: Unlike other platforms using numeric IDs, Bluesky uses did:plc:xxx format.

  6. Email verification for video: You must verify your email in Bluesky before uploading videos.

  7. 25 video daily limit: Maximum 25 videos OR 10 GB per day.

Best Practices

Content

  1. Concise posts: 300 chars is shorter than Twitter - be punchy
  2. Natural hashtags: 1-2 relevant hashtags work well
  3. Alt text: worth adding, but you have to do it in the Bluesky app after posting; the API cannot carry it
  4. URLs work: Links are clickable (unlike some platforms)

Timing

  • Growing platform: Less crowded than X, easier to get noticed
  • Tech-savvy audience: Developer and early-adopter heavy
  • Frequency: 1-3 posts per day

Engagement

  • Bluesky favors authentic conversation
  • Reply to comments to build community
  • Follow relevant users to grow network

Troubleshooting

ErrorCauseSolution
"Invalid credentials"Wrong password typeUse app password, not main password
"Image too large"Over 2,000,000 bytesCompress to 80-85% JPEG quality
"Content too long"Over 300 charsShorten content (no auto-threading)
"Video daily limit"25 videos reachedWait 24 hours
"Email not verified"Trying to upload videoVerify email in Bluesky settings

Frequently asked questions

What does the Bluesky Post AI skill do?

Use when the user wants to post or schedule to Bluesky through Publora. Handles the 300-character cap, auto-detected hashtags and links, up to 4 images, and videos. Alt text cannot be set through the API. Needs a Bluesky app password, never the main password. Not for Mastodon (use social-post).

Why use Bluesky Post on TypingMind?

Because you install it once and use it with any model. Bluesky Post is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bluesky Post in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/publora/skills/tree/main/skills/bluesky-post. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bluesky Post?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bluesky Post?

As many as you like. As long as a model supports skills, you can use Bluesky Post with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bluesky Post AI skill free?

Yes. It is published on GitHub by publora under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇