open-stanley プラグイン

Adversarial reader for a post draft. Reads as the target audience (from strategy.md) and answers three questions; used by the write skill before handover.

Receipt checker for a draft. Verifies every number, name, date, paper, quote and news item against the vault's story files and, where needed, the primary source. Used before publishing anything with a factual claim.

Reads LinkedIn and X feeds through the user's browser and returns scored comment candidates. Used by the scout skill and the 10am/10pm scheduled scans.

Map the user's vertical with public data — rank, compare or chart companies, tools, papers, funding, prices or usage from sources anyone could check, render the graphic with the bundled stanley-chart (no image model), and write the post around the one comparison nobody had seen laid out. Needs no meetings, no voice notes and no inside knowledge, so it is the lane a new account can post in from day one while mining warms up. Use when the user says "map the market", "rank the top N", "what does the data say about X", "make a data post", "do a Scholar-style post", or when the weekly drafts need one post that does not depend on the user's own stories.

Check a LinkedIn/X post or comment for the things that get it demoted, flagged as AI, or skipped by readers — AI-flagged vocabulary and structures, platform rules (hashtags, links, length, hook), unsupported claims without receipts, and overlap with the user's past posts — using the bundled stanley-audit linter. Use whenever the user asks "does this sound like AI", "check this post", "review before I publish", "why isn't this getting reach", or pastes a draft they wrote elsewhere; the write and scout skills run it automatically.

Work through the local queue that cloud scheduled runs left for this machine — LinkedIn comments to post, LinkedIn feed scans, analytics pulls, posts approved for publishing — using this computer's logged-in browser, then mark each item done or expired and report. Use when a session starts with queued items, when the user says "catch up", "run the queue", "post what's pending", or when the launchd/cron drain job fires. Runs only on a machine with a browser.

Get a post written or fully rewritten by a human — the user themselves (default), a retained editor, or a paid writer hired through an API (Prolific, Microworkers, Textbroker, human-mcp.io, Upwork MCP) — from a structured brief rather than from model prose, so the final text is human-authored and carries no model watermark. Use when the user asks for a human rewrite, "hire someone to rewrite this", a second pair of eyes, "make sure this passes AI detection", or when strategy.md marks a lane as human-written.

Turn the user's edits, skips, and results into durable rules — update voice.md and learn/rules.md from draft→final diffs, retune scout scoring from skip reasons, and (only if the user opts in) prepare an anonymized, text-free contribution of rule statistics for the shared Open Stanley skill. Use when the user says "learn from my edits", "here's what I actually posted", "stop doing X", "remember that I never say Y", "why do you keep doing this", or "contribute my improvements".

Write one long piece — a teardown, a field report, or a build log — from the vault's own receipts, then cut it into the posts and comments that point back at it. Use when the user says "write an article", "a blog post", "a teardown of X", "we should write something like that piece", "turn this into an essay", or when the monthly strategy check-in says the lane needs a flagship. Also handles LinkedIn Articles and X Articles.

Find post material in the user's own life through every connected source — meeting transcripts and summaries (Pam, Fathom, Granola, any MCP with meeting tools), Slack/Discord messages they wrote, sent email, calendar events, docs, memory MCPs, uploads and voice notes in the vault inbox — and turn it into story files with receipts. Use when the user asks "what should I post", "anything interesting from my meetings this week", "turn this transcript/voice note/thread into a post", drops a file, or when any other open-stanley skill needs fresh material. Also runs weekly as a scheduled task.

Set up Open Stanley for a person — work out from memory, connected sources, profiles and the machine which platforms, formats, languages and audience they have and confirm it in one message, say plainly which sources are missing, diagnose what they have tried (median engagement, what worked and why), offer strategies with evidence, propose three lanes, build a voice from their own posts plus the changes the evidence supports as experiments, check the profile strangers land on, and schedule the runs. Use when the user says "set up Stanley", "onboard me", shares their LinkedIn or X profile for the first time, asks "what should my content strategy be", or whenever the vault has no strategy.md or voice.md yet.

Post or schedule an approved draft to LinkedIn and/or X through the user's own logged-in browser (or a posting MCP such as SocialClaw/Postiz/X API if they have one), including X threads, first-comment links, and LinkedIn's native scheduler, then record the live URL in the vault ledger. Use when the user says "post it", "publish", "schedule for Thursday 10am", "put this on both", or "post the X version too".

Report what the user's posts and comments did (impressions, reactions, comments, followers, who engaged), attach the numbers to the stories and lanes that produced them, and give one concrete recommendation. Use for "how did my post do", "daily recap", "weekly numbers", "who's engaging with me", and as the nightly scheduled task. Reads LinkedIn analytics and X analytics through the user's browser.

The proactive habits of a head of content — the morning Soapbox question that pulls a voice note out of the user, Sunday weekly drafts, bi-weekly repackaging of the user's best old post shapes, the monthly Orbit (who kept showing up) and strategy check-in, and trend alerts. Use when the user asks for a morning prompt, "plan my week", "what old posts could I redo", "who's in my orbit", "review my strategy", or when a scheduled task names one of these rituals.

Scan the user's LinkedIn and X feeds (through their own logged-in browser, or any social MCP they have) for posts worth commenting on, and draft paste-ready comments in their comment voice. Use when the user asks "anything worth commenting on", "find posts to engage with", "who should I reply to", "what's trending in my niche today", or as the scheduled 10am/10pm scan. Also handles "draft a comment for this link".

Your head of content. Use this whenever the user wants help with LinkedIn or X (Twitter) — writing or scheduling a post, finding things to comment on, turning a meeting, voice note, or Slack thread into a post, reviewing why a post did or didn't work, planning the week's content, or asking "what should I post". Also use it for anything that mentions Stanley, ghostwriting, personal brand, founder-led content, building in public, or growing followers, even if the user doesn't say "post". Start here; it routes to the other open-stanley skills and holds the operating rules they all share.

Learn how a specific writer wins on LinkedIn or X — Paul Graham, Dharmesh Shah, Yamini Rangan, Yuriy Zaremba, or anyone the user names — by reading their recent posts through the user's browser and extracting reusable *shapes* (openers, structures, endings, specificity moves, cadence) into a shapes catalog, never their sentences. Use when the user says "write like Paul Graham", "learn from X's posts", "why do their posts work", "study my competitor", or when write needs a shape for a lane. Ships with a catalog of the creators studied in September 2026.

Short vertical video (on demand, and as a mode of the weekly drafts when strategy.md lists video in formats) for Instagram Reels, TikTok, YouTube Shorts, LinkedIn or X — turn the user's mined stories into video ideas, each paired with a reference video that already works on the platform, a shot list they can film on a phone, the spoken lines in their voice, on-screen text and a caption; then cut and caption their footage with HyperFrames when it is installed. Use when the user says "give me reel ideas", "what should I film", "make a video from this story", "turn this into a reel", "edit my clips", or when strategy.md lists short video in formats.

Make the images that go with content — a feed-accurate preview card of a draft (LinkedIn or X, fold marked) so the user reviews the real thing, a simple chart from the user's own numbers, a PDF carousel for LinkedIn documents, a screenshot of a source, or an image via any image-generation MCP the user has. Use when the user asks "show me how it will look", "make a visual for this", "turn these numbers into a chart", "make a carousel", or when write hands over a draft (a preview is always attached).

Draft or rewrite a LinkedIn post, X post, or X thread in the user's own voice from a story with a receipt, then audit it and hand it over with the one question that makes it theirs. Use whenever the user asks to write, draft, rewrite, shorten, "make this a post", "turn this into a thread", "post this to LinkedIn and X", or reacts to a draft ("too long", "sounds like AI", "change the hook"). Also used by rituals for weekly drafts and repackages.