Skip to content

Harmix/open-stanley / open-stanley/skills/stanley

stanley

Verified

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.

FileKindSize
SKILL.mdskill md14.2 KB
references/capabilities.mdmarkdown3.3 KB
references/platform-access.mdmarkdown4.0 KB
references/recommended-mcps.mdmarkdown5.5 KB
references/recommended.mcp.jsonconfig2.0 KB
references/research-linkedin-2026.mdmarkdown6.7 KB
references/scheduling.mdmarkdown8.6 KB
references/vault-backends.mdmarkdown6.8 KB
references/verify-live.mdmarkdown2.2 KB
references/why-these-rules.mdmarkdown2.1 KB
scripts/stanley-auditexecutablescript24.6 KB
scripts/stanley-briefexecutablescript6.4 KB
scripts/stanley-chartexecutablescript14.5 KB
scripts/stanley-previewexecutablescript5.8 KB
scripts/stanley-statsexecutablescript14.9 KB
scripts/stanley-traceother6.3 KB
scripts/stanley-vaultexecutablescript35.1 KB

references/why-these-rules.md

View on GitHub
# Why these rules (the failure log they come from)

Observed over 35 days of a paid "AI head of content" running for one founder, Aug–Sep 2026, plus the same failures reported publicly by another founder (AiSDR's CEO, 4 Sep 2026) using the same category of tool.

| Rule | What happened without it |
|---|---|
| Human-origin material first | Day 1: eight drafts, one usable. The usable one was the only one built on a source the user then verified himself. The other founder: "fake stories that fit the viral pattern but have nothing to do with my life." |
| Edit, don't generate | "Sounds like AI" was said seven times. The comments the user actually posted were his 1–2 sentence rewrites of 100-word drafts. |
| No receipt, no claim | Drafts cited 2024–25 papers as new in 2026; one draft said "recent literature shows" with nothing behind it; the tool later admitted a subagent had invented the line. |
| Never re-say | Draft 1 was "almost a copycat" of an existing post; the same three LinkedIn posts were suggested twice four days apart; the user was told to comment on his own posts four times; an old draft resurfaced the day after it was published. |
| Audit before the human sees it | The user was the linter: "too much text", "first sentence not easy to read for non-tech founders", "reads like a research paper", "remove the last two sentences". |
| The edit is the training signal | The tool replied "these edits make the pattern very clear… calibrating" and produced the same style the next day. The other founder: "it keeps happening despite recurring feedback." |
| Run records | 10pm scan on 13 Aug and 10am scan on 15 Aug never fired; LinkedIn was skipped in most early scans while the message said "both platforms"; "LinkedIn posts coming in a separate message" never came. |
| Capability probe | Custom MCP (the user's own meeting note-taker) could not be connected at all; the fix offered was "paste transcripts into the chat". |
| Browser over API | X API cannot reply to or quote accounts that haven't mentioned you, so the "comment on X" job collapsed into "paste this yourself"; LinkedIn search hit a monthly quota twice. |
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall