retro
Run the following command in DeepSeek Harness:
dsh plugin install StellatoL/retro
Paste the following prompt into your AI chat to install this plugin:
Install the plugin by running dsh plugin install StellatoL/retro in DeepSeek Harness (DSH); the source code is available at https://github.com/StellatoL/retro .
About this plugin
You finish a DeepSeek Harness session, the goal is met, the tool errors are logged, the feedback is noted, yet the lesson evaporates the moment you close the tab. retro plugs that gap: it captures goals, feedback, and tool failures from each session into reviewable retrospective cards, then walks you through drafting, reviewing, and archiving them as permanent notes in an Obsidian vault so the knowledge outlives the chat window.
The core workflow is a full retrospective pipeline. Use /retro draft to generate cards scoped to today, this week, the workspace, or a specific session; /retro review to keep, discard, or annotate each card; /retro entry keep to promote a card into a permanent experience note and refresh the index; and /weekly to produce a seven-day summary of sessions, materials, and feedback. Beyond individual cards, retro can surface rule proposals that you adopt into a skill or global rules file with /retro adopt, and turn the material into blog posts that you commit and push to a Git repository via /blog draft and /blog publish. A live Web panel in the DSH sidebar tracks pending cards, entry drafts, proposals, and the publishing queue, with one-click command copying.
retro is built for DeepSeek Harness users who want structured, repeatable retrospectives rather than ad-hoc journaling, and who already keep their long-term notes in Obsidian. If you have ever tried to re-read a week-old chat log and realized you cannot remember what you actually learned, retro is the plugin that will save you that hassle.
Use Cases
- Auto-capture session goals, feedback, and tool failures into reviewable retrospective cards
- Summarize a week of sessions, surface rule proposals, and adopt them into skills or global rules
- Turn retrospective notes into blog posts, commit, and push to a Git repository
Best For
- Developers using DeepSeek Harness daily who want to systematize session learnings
- Obsidian users who want AI session outcomes integrated into their personal knowledge base
- AI-assisted practitioners who distill rules from repetitive sessions to iteratively improve workflows
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.