メニュー
Read the per-pair posted.jsonl history file and show recent entries. Use when the user asks "what did I repost from <pair>", "show <pair> history", or "tail repost history".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run Repost-with-agent for one pair, all enabled pairs, or an explicit subset — scrape source, dedupe (local + destination), expand URLs, publish when allowed, append history, and notify the user. Use when the user asks to "run pair <id>", "post the latest from <pair>", "tick the <pair-id> pair", "run all pairs", or invokes /repost-run. Also invoked by scheduled agents for listen-for-future pairs.
Process one selected source item across every enabled destination pair for that source, especially scheduled/backfill slots. Use when the user or scheduler asks to backfill/catch up a source platform such as LinkedIn to all configured destinations, or when a partial fanout needs resume.
User-configured allow/skip rules for Repost-with-agent candidates. Apply before dedupe/publish so Ethan can block categories such as X video/livestream promos without polluting publish ledgers.
Walk back through historical source posts and repost the missing ones (newest-first). Use when the user asks to "backfill <pair>", "catch up the destination", "repost the last N posts", or invokes /repost-backfill. Multi-post operation with rate-limiting between publishes.
Install current-harness scheduler entries for Repost-with-agent. Default listen mode is one fresh agent/subagent running /repost-run all across enabled listen-for-future pairs; source backfills use source-item fanout; custom per-pair, subset, dry/preview, and arbitrary cadence jobs are supported when the user asks.
Create or save a new Repost-with-agent source → destination pair. Use when the user wants to set up cross-posting between websites the agent can safely operate through a logged-in browser (with documented examples for LinkedIn, X, Bluesky, Threads, and Facebook), or asks to "configure a repost pair", "set up reposting", "wire up cross-posting", or "add a new pair to repost-with-agent / repost_with_agent".
| name | repost-history |
| description | Read the per-pair posted.jsonl history file and show recent entries. Use when the user asks "what did I repost from <pair>", "show <pair> history", or "tail repost history". |
| when_to_trigger | User wants to see what's been reposted from a given pair. |
Tail the per-pair posted.jsonl and show recent entries.
Read the requested pair's posted.jsonl at ~/.repost-with-agent/pairs/<id>/posted.jsonl.
If file doesn't exist or is empty, tell the user "No posts yet for ." and stop.
Default tail length: 20 lines. Accept --limit N from the user.
Read with tail -<N> via Bash. Each line is a JSON object with fields:
ts (ISO-8601)sourceItemId (e.g. urn:li:activity:7000)canonicalSourceUrldestinationUrldestinationIddraftText (the text we posted, ≤500 chars summary if longer)Format each entry compactly:
2026-04-30T22:53Z urn:li:activity:7000
Source: https://www.linkedin.com/feed/update/urn:li:activity:7000/
Posted: https://x.com/REEEthan_YT/status/123
Text: "Yesterday I shipped v3.0.0 of Repost-with-agent — instructions + JSON state, no more SDKs..."
If the user asks for --with-learnings (or similar) on top of the history
tail, also read ~/.repost-with-agent/pairs/<id>/learnings.md and print the
last 3 ## … entries under a === Recent learnings (last 3) === heading
below the post history. This is handy when the user is reviewing a sequence
of posts and wants the institutional context that informed them.
If learnings.md is empty or only contains the placeholder stub, print
(no learnings recorded yet). See skills/repost-learnings/SKILL.md for
the file format.
By default (no --with-learnings), this skill is a pure history tail and
doesn't touch learnings.md.
skills/repost-pair-show/SKILL.md — full pair inspection (config + history
skills/repost-learnings/SKILL.md — format of the learnings.md file.Read-only. No Telegram on this skill.