the-post-office

Turn one approved idea brief or one raw user thought into a finished LinkedIn post in the owner's voice. Use when the user says "write a post", "draft this thought", "turn this into a LinkedIn post", "polish this for LinkedIn", picks an approved idea from post-ideator, or hands over raw material. Works from that single input only, grounded in the post corpus and post-patterns for voice and shape.

Generate the image-generation prompts for a multi-slide LinkedIn carousel from a `format: carousel` draft — one paste-ready prompt per slide, in a consistent hand-drawn visual system, with each tool's pros/cons rendered in-image and a reserved blank band for the product logo. Use when a carousel draft is approved, the user says "carousel image", "slide prompts for this", "generate the carousel", or `post-cycle` reaches the visual step on a carousel draft. Writes an index `concepts/<date>-<slug>/prompt.md` plus `slide-NN.md` files, updates the draft's `concept_path`, and prints each slide prompt for the user to paste into their image tool. Trigger phrases: "post-carousel", "carousel image", "slide prompts".

Critique one draft against the approved idea brief, the archive winners, and the pattern report. Use when the user says "review this draft", "should I publish this", "critique this post", or after post-writer completes a draft. Approves only strong drafts and returns a single rewrite plan when rejecting.

Run the full LinkedIn post pipeline end-to-end in one go — briefing (if missing), top-posts + patterns context, ideator shortlist, writer draft, critic verdict. Use when the user says "full cycle", "run the pipeline", "do the whole flow", "post-cycle", "give me a post end to end", or wants a single command that replaces invoking topics-briefing, post-ideator, post-writer, and post-critic separately. Optionally accepts an idea number to pick from a freshly generated shortlist.

Generate the image-generation prompt for a `format: decision-tree` LinkedIn post — a single clean hand-drawn flowchart that routes the reader from a root question to a recommendation across 3 to 5 labelled branches, with the question rendered as the in-image title. Use when a decision-tree draft is approved, the user says "flowchart image", "decision tree image", "render the tree", or `post-cycle` reaches the visual step on a decision-tree draft. Saves the prompt to `concepts/<date>-<slug>/prompt.md`, updates the draft's `concept_path`, and prints the prompt to paste into an image tool. Trigger phrases: "post-flowchart", "flowchart image", "decision tree image".

Find LinkedIn post angles that can reach technical builders right now, but only when the angle is specific, differentiated, and defensible. Use when the user says "what should I post about", "pitch me ideas", "give me post angles", "find a topic", "ideate a post", or asks for fresh material without supplying a thought. Returns 3 to 5 scored idea briefs and writes shortlisted ones into ideas/YYYY-MM-DD.md.

Generate an image-generation prompt for a LinkedIn post in one of three selectable styles (a black sketch on white, a warm mid-century hand-drawn illustration, or a believable real-world photo with room for the hook) with the post's hook rendered into the image as overlaid text. Prompts for the style when none is given. Picks a tactile, content-specific metaphor by reasoning over the whole draft, always staging a subject in tension, never a generic stand-in or inert prop. Use when the user says "image for this post", "make a cover image", "generate the post image", "draw an image for X", or picks a draft to illustrate. Saves the prompt to `concepts/<date>-<slug>/prompt.md`, updates the draft's `concept_path`, and prints the prompt for the user to paste into their image tool. Trigger phrases: "post-image", "cover image", "draw the post".

Run the 72-hour retrospective on a published draft and save the conclusion in retros/. Use when the user says "retro this post", "review how this performed", or wants to update the draft lifecycle after publishing.

Generate a weekly SWE+AI topic briefing (HN + Lobsters + RSS newsletters + Exa fresh news, merged and bucketed by recency) for LinkedIn post ideation. Use whenever the user asks "what should I post about", "LinkedIn topic candidates", "weekly briefing", "topic ideas this week", or wants a single markdown brief to paste into their LinkedIn Claude project. Combines all four sources in one run.

Generate retrospective failure analyses for the worst-performing published posts so the writer and critic learn from misses, not just wins. Reads the bottom-5 posts by impressions from `posts/`, classifies each, and writes one postmortem file per post to `retros/postmortems/<post-date>-<slug>.md`. Use when the user says "run postmortems", "analyze bottom posts", "what failed", "post-mortem the losers", or "refresh failure analyses". Also invoked by `post-cycle` when the postmortem corpus is stale.

Fetch top stories from Hacker News (filtered to actual stories) for LinkedIn topic ideation. Use when the user wants "top HN stories", "what's on HN", "fetch Hacker News", or fresh tech signals for a post. Returns JSON entries with title, url, score, comments, author.

Fetch the Lobsters (lobste.rs) hottest list for LinkedIn topic ideation. Use when the user wants "fetch Lobsters", "lobste.rs hottest", or a curated SWE-heavy alternative to HN signals. Returns JSON entries with title, url, score, comments, tags.

Fetch the latest entries from all configured RSS/Atom newsletters and blogs (SWE + AI feeds — JavaScript Weekly, TLDR AI, Import AI, Pragmatic Engineer, Simon Willison, OpenAI Blog, etc.). Use when the user wants "newsletter signals", "what did newsletters publish this week", or curated long-form ideas for a LinkedIn post. Returns JSON.