메뉴
Guide for posting to ATProtocol/Bluesky. Use when creating posts, threads, or blog entries. Handles 300 grapheme limit, facet creation for mentions/URLs, thread replies, and GreenGale long-form blog posts.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Write and read W3C Web Annotations on ATProtocol using the at.margin.annotation lexicon. Use when annotating URLs, writing reading notes on web pages, or building a public research trail. Supports single writes, batch writes via applyWrites, and reading annotations from any ATProtocol user. Triggers on annotate, annotation, margin, reading notes, or web annotation.
Manage Semble collections and cards via ATProto CLI. Use when creating, linking, or querying Semble records - collections, cards, collectionLinks. Handles network.cosmik.* lexicons with proper field validation.
Full interaction with X (Twitter) - post, read, reply, like, retweet, follow. Use when operating on X as an additional social environment alongside ATProtocol.
Guide for observing the ATProtocol network. Use when sampling the firehose, taking network pulses, monitoring feeds, or analyzing engagement patterns.
Publish public cognition records to ATProtocol. Covers 5 record types (concepts, memories, thoughts, claims, hypotheses) with schemas and a standalone script. Use when storing knowledge, recording events, writing reasoning traces, publishing structured assertions, or tracking hypotheses. Any agent on ATProtocol can use this.
Guide for managing agent memory blocks. Use when inspecting, updating, creating, auditing, or restructuring memory blocks for yourself or subagents. Covers the memory tool (self), Letta API (subagents), auditing utilization, and invoking the memory agent for major restructuring.
| name | posting-to-atproto |
| description | Guide for posting to ATProtocol/Bluesky. Use when creating posts, threads, or blog entries. Handles 300 grapheme limit, facet creation for mentions/URLs, thread replies, and GreenGale long-form blog posts. |
300 grapheme limit. Facets required for @mentions and URLs (byte offsets, not char offsets).
# Single post
uv run python tools/thread.py "Post text here"
# Thread
uv run python tools/thread.py "Post 1" "Post 2" "Post 3"
# Reply thread
uv run python tools/thread.py --reply-to at://did:.../app.bsky.feed.post/... "Reply 1" "Reply 2"
# From file (posts separated by '---')
uv run python tools/thread.py --file draft.txt
tools/thread.py handles facet detection automatically for @mentions and URLs.
For content exceeding 300 graphemes. Posts stored as app.greengale.document records on PDS, viewable at https://greengale.app/<handle>/<rkey>.
uv run python .skills/posting-to-atproto/scripts/publish-greengale.py \
--title "Post Title" --rkey "url-slug" --file content.md
# Options
--subtitle "Optional subtitle"
--theme github-dark # github-light, dracula, nord, solarized-light, solarized-dark, monokai
--visibility public # url (unlisted), author (private)
Same --rkey overwrites existing post (uses putRecord). Max 100,000 chars markdown.
facets = [{
'index': {'byteStart': start, 'byteEnd': end},
'features': [{'$type': 'app.bsky.richtext.facet#mention', 'did': 'did:plc:xxx'}]
}]
For URLs: app.bsky.richtext.facet#link with uri field.