diff options
| author | Igor Soarez <igor@soarez.org> | 2026-08-05 13:42:46 +0100 |
|---|---|---|
| committer | Igor Soarez <igor@soarez.org> | 2026-10-14 12:19:26 +0100 |
| commit | 681ea9d0b3b89bec1ad8c57ef79ae2d4d82ef49b (patch) | |
| tree | 6aee901bedca763e09f53e2778b5a7d50d1f3028 /skills | |
| parent | cdcfb137a83d178d0d22df0eb97aae768e8abf9c (diff) | |
docs(readpage): flag SPA-shell results so models don't trust them as the page
Diffstat (limited to 'skills')
| -rw-r--r-- | skills/pi-browser-harness/SKILL.md | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/skills/pi-browser-harness/SKILL.md b/skills/pi-browser-harness/SKILL.md index e3bf7dc..a5ca4ca 100644 --- a/skills/pi-browser-harness/SKILL.md +++ b/skills/pi-browser-harness/SKILL.md @@ -41,6 +41,8 @@ Pass `@(x,y)` from `browser_snapshot` straight to `browser_click`. No screenshot `browser_web_search` and `browser_read_page` each run in their own isolated tab and never touch the user's current tab. Pair them for a research question: search for candidate URLs, then read the promising ones. +`browser_read_page` runs a reader-mode heuristic: JS-rendered pages (X, social SPAs, login walls) can come back as a short nav shell — if the result is tiny or reads like chrome, don't treat it as the page; re-read the `og:title`/`og:description` meta or pull the content with `browser_execute_js` (e.g. `document.querySelector('article')?.innerText`). + ## Connection Setup Browser control is **on-demand** — the daemon does NOT start automatically. |