---
name: progressive-summarization
source: https://app.decimal.ai/s/progressive-summarization@1/SKILL.md
source_sha256: dc3471b1692b
---

# Progressive summarization

Asked to "summarize this so I can review it later," a base model writes a fresh, shorter paraphrase
and throws the source away. That is the wrong move for something you want to *revisit*. A paraphrase
is lossy and final: when you come back in three months and the two-line summary isn't enough, the
detail is gone, and you can't tell which words in it were the author's and which the model invented.

Progressive summarization does the opposite. You never rewrite the source — you keep it whole and
add emphasis *on top of it*, in nested layers, so a future reader can zoom from a one-glance gist
down to the full original at whatever depth they need. Nothing is discarded; the layers just let you
skim.

## The four layers

Output them top to bottom so the reader moves shallow → deep:

1. **Gist** — a few sentences, in *your own words*, at the very top. The one thing you'd want to know
   before deciding whether to read further. This is the only layer you compose; every other layer is
   pure selection.
2. **The source, preserved verbatim** — the original text, unchanged, beneath the gist. Do not
   delete, reorder, paraphrase, or "clean up" a single sentence. This is what makes the technique
   non-lossy.
3. **Bold** — inside that preserved source, bold the load-bearing sentences and fragments: the ones
   that carry the argument, the decision, the number, the ask. A reader who reads *only* the bold
   should still get the point.
4. **Highlight** — mark a smaller subset *of the already-bolded text* — the essential of the
   essential, the handful of fragments you'd keep if you could keep almost nothing.

## The discipline the base skips

- **Additive only — never rewrite.** The source stays intact and readable underneath. If you deleted,
  reordered, or reworded any of the original, you broke the technique. The whole value is that the
  full text is still there.
- **Layers nest — each is a subset of the one below it.** highlight ⊆ bold ⊆ source. You never
  highlight a fragment you didn't bold, and you never bold text that isn't in the source. Each layer
  is a tighter selection of the layer beneath, not a new pass over the material.
- **Emphasize sparingly.** If most of the passage is bold, nothing is emphasized. Bold roughly the
  minority that carries the weight; highlight a minority of *that*. Over-marking destroys the point of
  the layers — a page that's all yellow is a page with no signal.
- **Only the gist is in your words.** Layers 2–4 are selection, not composition. You are choosing what
  to emphasize in the author's text, not restating it.

## Markup

Use standard Markdown so the layers survive copy-paste:

- Bold: `**load-bearing sentence**`
- Highlight: `==essential fragment==` (Obsidian/Notion style; `<mark>essential fragment</mark>` also works)

## Worked shape

Given a source paragraph, the output looks like:

> **Gist:** The team is delaying the launch two weeks to fix the checkout bug; revenue impact is
> expected to be small.
>
> We met Thursday to review launch readiness. **The checkout flow still fails for about 3% of
> users on mobile,** which the team traced to a payment-timeout race. After discussion, ==**we
> decided to push the launch two weeks**== rather than ship with the known defect. Marketing has
> been notified. **Finance estimates the delay costs roughly $40K in deferred revenue,** which
> leadership judged acceptable against the reputational risk of a broken checkout.

Notice: the full paragraph is still there, the bold alone reads as a summary, the highlight alone is
the single decision, and the gist sits on top — four depths, one preserved source.