diff --git a/skills/moli-cdp-server/references/protocols.md b/skills/moli-cdp-server/references/protocols.md
index 94acc4ccb1..9fe5cfa329 100644
--- a/skills/moli-cdp-server/references/protocols.md
+++ b/skills/moli-cdp-server/references/protocols.md
@@ -54,6 +54,28 @@ hard-coding a `/devtools/...` path.
 - Add `--block-private-networks` or `--block-cidrs` for untrusted navigation.
 - Keep loopback binding unless remote clients genuinely require exposure.
 
+## Full-document screenshots
+
+With `--layout`, request an automatic full-document PNG by omitting `clip` and
+setting `captureBeyondViewport`:
+
+```json
+{
+  "method": "Page.captureScreenshot",
+  "params": { "format": "png", "captureBeyondViewport": true }
+}
+```
+
+- Automatic full-document capture requires CSS width and height to each be less
+  than 131,072 pixels; equality is rejected.
+- An explicit page-coordinate `clip` bypasses that whole-document entry check,
+  but must have positive dimensions.
+- Moli renders one complete bitmap. It does not stitch tiles or automatically
+  downscale, so device-pixel, encoder, backend, and memory limits can fail
+  earlier than the CSS boundary.
+- Tile explicit clips in the client when one bitmap cannot fit. Keep each clip
+  within the active raster and encoder limits.
+
 ## Troubleshooting
 
 1. Confirm the Moli process is still running.
diff --git a/skills/moli-webfetch/SKILL.md b/skills/moli-webfetch/SKILL.md
index 5546279470..e939955bbf 100644
--- a/skills/moli-webfetch/SKILL.md
+++ b/skills/moli-webfetch/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: moli-webfetch
-description: Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, screenshot, PDF, or WPT artifact—even when Moli is not named.
+description: Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or full-document screenshot, PDF, or WPT artifact—even when Moli is not named.
 ---
 
 # Fetch Websites with Moli
@@ -66,7 +66,8 @@ structure-first; enable layout only when the result needs pixels or pagination.
 6. For a visual or paginated result, enable layout and redirect binary stdout:
 
    ```bash
-   moli fetch --layout --dump screenshot "https://example.com" > page.png
+   moli fetch --layout --dump screenshot "https://example.com" > viewport.png
+   moli fetch --layout --dump screenshot_full "https://example.com" > full-page.png
    moli fetch --layout --dump pdf "https://example.com" > page.pdf
    ```
 
@@ -85,6 +86,7 @@ structure-first; enable layout only when the result needs pixels or pagination.
 - Use `html` to diagnose DOM serialization or preserve exact markup.
 - Use `screenshot` for a viewport PNG when appearance is evidence. It requires
   `--layout`.
+- Use `screenshot_full` for one full-document PNG. It requires `--layout`.
 - Use `pdf` for a paginated PDF capture. It requires `--layout`.
 - Use `--with-frames` only when relevant content lives inside iframes.
 - Enable `--image` and `--font` when visual fidelity depends on them. Use
@@ -121,9 +123,9 @@ unrelated actions.
   to use. Never expose headers, cookies, or tokens in the response.
 - Remember that `-H/--header` applies to the initial navigation, not every
   subresource.
-- Treat stdout as the requested artifact. Redirect screenshot and PDF output to
-  files, verify that they are non-empty and have the expected type, and never
-  print their binary bytes into a text response.
+- Treat stdout as the requested artifact. Redirect screenshot, full-document
+  screenshot, and PDF output to files, verify that they are non-empty and have
+  the expected type, and never print their binary bytes into a text response.
 - Report a fetch failure rather than inventing content. A browser error page,
   login wall, or empty shell is not successful evidence.
 - Run `moli fetch --help` when the installed version may differ from this
diff --git a/skills/moli-webfetch/references/fetch-recipes.md b/skills/moli-webfetch/references/fetch-recipes.md
index e2deba9a19..faca460d21 100644
--- a/skills/moli-webfetch/references/fetch-recipes.md
+++ b/skills/moli-webfetch/references/fetch-recipes.md
@@ -21,6 +21,7 @@
 | Inspect exact DOM | `--dump html` | Useful when Markdown loses important structure |
 | Diagnose requests | `--dump json --trace-network` | Adds the `network` object |
 | Capture the viewport | `--layout --dump screenshot` | Writes PNG bytes to stdout |
+| Capture the full document | `--layout --dump screenshot_full` | Writes one full-page PNG to stdout |
 | Capture a paginated document | `--layout --dump pdf` | Writes PDF bytes to stdout |
 
 Raw non-HTML responses support only `html` and `json`.
@@ -88,13 +89,18 @@ silently remove behavior or content.
 
 ## Screenshots and PDFs
 
-Enable real on-demand layout for both binary formats and redirect stdout:
+Enable real on-demand layout for binary output and redirect stdout:
 
 ```bash
 moli fetch \
   --layout \
   --dump screenshot \
-  "https://example.com" > page.png
+  "https://example.com" > viewport.png
+
+moli fetch \
+  --layout \
+  --dump screenshot_full \
+  "https://example.com" > full-page.png
 
 moli fetch \
   --layout \
@@ -102,6 +108,11 @@ moli fetch \
   "https://example.com" > page.pdf
 ```
 
+Use `screenshot` for the live viewport and `screenshot_full` for one complete
+document raster. A full-document capture does not tile or automatically
+downscale: its CSS width and height must each be less than 131,072 pixels, and
+device-pixel, encoder, memory, or backend limits can fail earlier.
+
 Use `--image --font` when page appearance depends on external images or fonts.
 Use `--resource` only when every optional resource family is needed. Keep stderr
 separate from the output file, then validate the file signature and size.
@@ -158,6 +169,8 @@ For a crawl rather than a single lookup:
 - **Missing API data:** use response waits; add `--trace-network` to JSON only
   when request diagnostics are needed. Add `--trace-matched-response-body` only
   when the matched response body itself is required.
+- **Oversized full-page PNG:** use a viewport capture or deliberately tiled CDP
+  clips when one `screenshot_full` raster exceeds a backend or memory boundary.
 - **TLS failure:** fix trust or hostname configuration. Use
   `--insecure-disable-tls-host-verification` only after the user explicitly
   accepts that risk.