dsh-forge: Forging reusable skills for DeepSeek Harness
`dsh-forge` is an MIT-licensed community plugin for DeepSeek Harness, designed to automatically transform repetitive and successful conversation trajectories into reusable skills. Running on Node.js >=20 with zero external dependencies, the plugin monitors the harness's real-time session event stream to accumulate user intent, tool call sequences, and completion status. When the same normalized initial intent is successfully completed in two or more sessions, the plugin automatically triggers the "forging" process. It invokes the harness's built-in LLM distillation to generate a `SKILL.md` file containing the name, description, and usage guide, and writes it to the `.dsh-forge/skills` directory (which is configurable). The skills are subsequently registered via the `ctx.skills` interface for use in subsequent sessions.
Read Morerxa3c/chat2skill: Extract project memory and reusable skills from assistant sessions
`rxa3c/chat2skill` is a plugin designed to address the issue of corrections, preferences, and project facts in assistant sessions failing to be stably accumulated. Its core functions are "post-session extraction" and "pre-session injection": by analyzing session signals, it distills information into local SQLite memory and `SKILL.md` skill files, automatically retrieving and injecting it in subsequent sessions. The plugin supports LLM mode (Proposer/Generator/Judge flow) and non-LLM mode (keyword detection). Data is stored locally, while the cloud is used solely for stateless execution and claims not to store data. Typical extraction requires approximately 4 LLM calls and is triggered only upon detecting correction or constraint signals. Documentation suggests it is best suited for Claude Code, Codex, and Cursor, while other agents require lifecycle support.
Read More