dsh-rss-daily
A DeepSeek Harness plugin that creates daily RSS news digests, optionally edits them with the configured DSH model, and delivers them through supported webhooks.
Install
$ dsh plugin --profile web add dsh-rss-dailyPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Fetches and deduplicates items from 46 curated RSS sources.
- Schedules a daily digest, with a stated catch-up run within 12 hours after a missed schedule.
- Uses the model configured in DSH through ctx.llm to edit and organize the digest, with a rules-based fallback mode.
- Delivers digests to ServerChan, PushDeer, WeCom, Telegram, Bark, gotify, or a custom webhook.
- Displays digests in the conversation UI without writing them to conversation records or sending them to the model, as stated in the README.
- Provides an rss_daily conversation tool with run, status, redo, and deliver actions.
- Includes a same-origin HTTP API when used with a webserver-enabled profile.
- Includes py/daily.py for standalone execution against an OpenAI-compatible endpoint.
Useful For
- Receive a scheduled morning news briefing in an IM or push-notification channel.
- Ask a DSH agent to generate, redo, check, or deliver a daily RSS digest.
- Manage digest time, sources, item count, model mode, and delivery targets through a DSH interface.
- Run the included Python digest pipeline outside DSH when configured with an OpenAI-compatible endpoint.
Who It Fits
- DeepSeek Harness users running a web or other persistent profile.
- Users who want RSS-based daily news summaries delivered by webhook.
- Users who want a configurable in-DSH news-digest workflow.
Documented Limitations
- Requires DSH and a web or other persistent profile for the plugin workflow.
- Requires Python 3.9+ and the feedparser package.
- LLM editing depends on the model already configured in DSH; the plugin documents a rules-based fallback if model calls fail.
- Webhook delivery requires configuring at least one target.
- The standalone Python mode requires an OpenAI-compatible endpoint and credentials.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- shangjian2023/dsh-rss-daily
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 2f7a7eb · 2026-09-14
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 2GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-31
- Last release
- 2026-08-22
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →A bundle combining a runtime injector and task-aware reasoning-mode router presets for DeepSeek Harness.
View plugin →