K
klaus-2/dsh-nextsteps
Suggested next-step prompts under every finished agent turn in the DeepSeek Harness chat — one click sends the followup.
★ 1·updated 2026-11-19
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site
- Star count
- 1 ★ · klaus-2/dsh-nextsteps · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-15 · last seen 2026-11-20 · seen 6× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
klaus-2/dsh-nextsteps;first catalogued 2026-11-15;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# dsh-nextsteps
Excerpted from the repository README (abridged)
English · Português (Brasil) · 简体中文
Every finished agent turn ends with ready-to-click next steps.
dsh-nextsteps is a DeepSeek Harness plugin that suggests about three followup prompts at the end of every turn, renders them as clickable cards under the completed turn, and sends the clicked prompt as your next message — one click, zero typing. Auto lets the answering model write them; an explicit language makes the plugin produce them with its own clean model call, so the cards stay in that language even when the conversation is in another one.
dsh plugin --profile web add dsh-nextsteps
## Product tour
1. Ask anything. In Auto the model writes the cards itself, as the last step before its final answer; with an explicit language or model the plugin generates them after the turn instead.
2. The completed turn renders its own suggestion cards — attributed to that turn, never repeated across messages.
3. Click a card: the prompt is sent verbatim as your next queued message and the card flips to a sent state.
4. Each card also carries an action bar: copy, favourite, edit, discard and expand. Expand reveals the full prompt without sending anything.
5. Everything survives restarts: cards, their turn attribution, and which ones you already clicked.
6. Open the dsh settings → Nextsteps to pick the generation language (15 languages or Auto), how many suggestions you get per turn (1–6), the suggestion styles, the generation mode, the latency budget, the suggestion length and whether the small header shows.
## Features
Per-turn attribution — suggestions stay attached to the turn that produced them, across reloads and app restarts.
One-click send through the session's own conversation controller, with a composer fallback.
Persistent captures: clicked cards stay marked after restarts (content-addressed keys, turn backfilled from history).
Labels, with automatic truncation when absent; strict payload validation with corrective model feedback.
Suggestion styles — a multi-select of Next action, Explore and Deep dive. The generator is told to vary the prompts across the selected angles; the default is all three.
On-demand generation — choose On demand and the model is told not to call the tool; a Generate suggestions button under the answer asks for the cards instead. The button is there in both the inline and the host mode, and it asks the host exactly once.
Copy a suggestion with one click, straight to the clipboard.
Favourites — keep the suggestions you want to reuse, and copy or remove them from the settings page.
Discard a suggestion you do not want, and restore the most recent discard; the discard list lives in the settings page too.
Edit a suggestion before sending it: the edited text is what gets sent, and the stored card is left untouched.
Expand a suggestion to read the full prompt without sending it.
Test model — a button next to the Model setting probes the selected model with one tiny streaming call and shows the time to the first token, or the failure inline.
Export the favourites as a Markdown download, ordered by the date each one was saved.
New conversation with this suggestion — a card action that opens a fresh conversation with the prompt prefilled in the composer; nothing is sent for you.
Every finished agent turn ends with ready-to-click next steps.
dsh-nextsteps is a DeepSeek Harness plugin that suggests about three followup prompts at the end of every turn, renders them as clickable cards under the completed turn, and sends the clicked prompt as your next message — one click, zero typing. Auto lets the answering model write them; an explicit language makes the plugin produce them with its own clean model call, so the cards stay in that language even when the conversation is in another one.
dsh plugin --profile web add dsh-nextsteps
## Product tour
1. Ask anything. In Auto the model writes the cards itself, as the last step before its final answer; with an explicit language or model the plugin generates them after the turn instead.
2. The completed turn renders its own suggestion cards — attributed to that turn, never repeated across messages.
3. Click a card: the prompt is sent verbatim as your next queued message and the card flips to a sent state.
4. Each card also carries an action bar: copy, favourite, edit, discard and expand. Expand reveals the full prompt without sending anything.
5. Everything survives restarts: cards, their turn attribution, and which ones you already clicked.
6. Open the dsh settings → Nextsteps to pick the generation language (15 languages or Auto), how many suggestions you get per turn (1–6), the suggestion styles, the generation mode, the latency budget, the suggestion length and whether the small header shows.
## Features
Per-turn attribution — suggestions stay attached to the turn that produced them, across reloads and app restarts.
One-click send through the session's own conversation controller, with a composer fallback.
Persistent captures: clicked cards stay marked after restarts (content-addressed keys, turn backfilled from history).
Labels, with automatic truncation when absent; strict payload validation with corrective model feedback.
Suggestion styles — a multi-select of Next action, Explore and Deep dive. The generator is told to vary the prompts across the selected angles; the default is all three.
On-demand generation — choose On demand and the model is told not to call the tool; a Generate suggestions button under the answer asks for the cards instead. The button is there in both the inline and the host mode, and it asks the host exactly once.
Copy a suggestion with one click, straight to the clipboard.
Favourites — keep the suggestions you want to reuse, and copy or remove them from the settings page.
Discard a suggestion you do not want, and restore the most recent discard; the discard list lives in the settings page too.
Edit a suggestion before sending it: the edited text is what gets sent, and the stored card is left untouched.
Expand a suggestion to read the full prompt without sending it.
Test model — a button next to the Model setting probes the selected model with one tiny streaming call and shows the time to the first token, or the failure inline.
Export the favourites as a Markdown download, ordered by the date each one was saved.
New conversation with this suggestion — a card action that opens a fresh conversation with the prompt prefilled in the composer; nothing is sent for you.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/klaus-2-dsh-nextsteps/)
- Source
- github · https://github.com/klaus-2/dsh-nextsteps
- Browse by field
- Open source
- Traction
- 1 ★
- added
- today
More entries
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.