Compress a long doc / webpage into a usable summary
Recipe template · not yet tested on this site
This page is a recipe template, not yet tested here. Run logs, tokens and time go in after re-testing; until then no estimated numbers are filled in.
When to use
A long article or a chain of pages you have no time to read fully, but need to know what it says and whether it conflicts with elsewhere.
Preparation
- Host version
- To fill (record the exact rc version when testing)
- Model
- To fill
- Mode / permissions
- Standard mode + modify-within-workspace is enough to start
- Plugins required
- None (add name & version after testing if used)
- Input materials
- Keep in a separate workspace; back up originals first
Full instruction
Read [document / webpage URLs] and produce a structured summary.
Structure:
1. One-line conclusion.
2. 3-5 core points, each annotated with the original section it comes from.
3. Any explicit data / numbers, quoted verbatim with source.
4. The author's own stance or bias (if any).
5. A separate section for possible conflicts with other material you were given; do not reconcile them for me.
Requirements: do not invent content not in the source; state plainly what could not be read.Run log
| Item | Value | Note |
|---|---|---|
| Time spent | to be tested | |
| Result | to be tested | |
| In / out tokens | to be tested | |
| Leftovers | to be tested |
Output
After a successful run, list files and screenshots here, and note whether originals changed.
Acceptance checklist
Tap to tick each item off as you verify.
- Each summary point points back to a source location
- Numbers are quoted from source, unmodified
- Conflicts are listed separately, not buried
- Unreadable parts are stated
Failures & boundaries
- Pages must be fetchable; login-walled content can't be read
- Summary does not replace reading key sections
- This is a recipe template and has not been tested on this site
- Blocked on: Runnable, but 'is the summary good' has no mechanically checkable criterion. Today only length and structure can be verified, not whether key conclusions were dropped. Criteria come first.