Harmix/open-stanley / open-stanley/skills/stanley
stanley
VerifiedYour 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.2 KB |
| references/capabilities.md | markdown | 3.3 KB |
| references/platform-access.md | markdown | 4.0 KB |
| references/recommended-mcps.md | markdown | 5.5 KB |
| references/recommended.mcp.json | config | 2.0 KB |
| references/research-linkedin-2026.md | markdown | 6.7 KB |
| references/scheduling.md | markdown | 8.6 KB |
| references/vault-backends.md | markdown | 6.8 KB |
| references/verify-live.md | markdown | 2.2 KB |
| references/why-these-rules.md | markdown | 2.1 KB |
| scripts/stanley-auditexecutable | script | 24.6 KB |
| scripts/stanley-briefexecutable | script | 6.4 KB |
| scripts/stanley-chartexecutable | script | 14.5 KB |
| scripts/stanley-previewexecutable | script | 5.8 KB |
| scripts/stanley-statsexecutable | script | 14.9 KB |
| scripts/stanley-trace | other | 6.3 KB |
| scripts/stanley-vaultexecutable | script | 35.1 KB |
references/verify-live.md
View on GitHub# Verify a post or comment is live before saying so
On 2026-11-08 a run told the user "your comment is posted" when it was not. The check searched the page text for the comment, and the page text included the comment box, where the unsent text was still sitting. The user looked and saw nothing.
The rule: nothing is reported as posted, and nothing goes into the ledger as posted, until the page has been reloaded and the text is found outside every editor, under the user's name.
1. Before you press Comment or Post, read the count ("8 comments") if the page shows one.
2. Press the button, wait 3 seconds, then reload the post's own URL (not the feed) and wait for it to load. On LinkedIn, if the comment is not in "Most relevant", switch the comments to "Most recent".
3. Run this with the javascript tool. Set `TEXT` to the first ~60 characters you posted and `NAME` to the user's display name from `my-human.md`:
```js
const TEXT = "<first ~60 characters>"; const NAME = "<display name>";
const norm = s => (s || '').replace(/\s+/g, ' ').toLowerCase();
const t = norm(TEXT).slice(0, 60);
const inEditor = [...document.querySelectorAll('[contenteditable=true],textarea')].some(e => norm(e.innerText || e.value).includes(t));
const hits = [...document.querySelectorAll('article,li,section,div')].filter(e =>
!e.closest('[contenteditable=true]') && !e.querySelector('[contenteditable=true],textarea') &&
norm(e.innerText).includes(t) && e.innerText.includes(NAME));
JSON.stringify({ saved: hits.length > 0, stillInEditor: inEditor });
```
4. Live only when `saved` is true and `stillInEditor` is false. A plain search of `document.body.innerText` is not a check: in the 2026-11-08 test it found unsent text in the box and said yes.
5. If it is not live: say so, try once more, verify again. Never write "posted" on a guess.
6. Record what you saw in the ledger: `comment-add ... --verified "reloaded, found under <name>, comments 8 -> 9"`, or `post-add ... --via publish --verified "reloaded <url>, first line found under <name>"`. The script refuses a posted comment or a `--via publish` post without `--verified`.
Tested 2026-11-08 on a LinkedIn post: a saved comment gave `saved: true`, and text typed in the box but not sent gave `saved: false, stillInEditor: true`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |