dsh-learning-mode

English | 中文

An agent preset for DeepSeek Harness (DSH) that teaches while coding, modeled on Claude Code's official Learning output style: explain concretely with usage scenarios, guide your thinking with questions, and leave explicit practice blanks for you to do by hand.

Learning output style (Claude Code): "Collaborative, learn-by-doing mode where Claude will not only share 'Insights' while coding, but also ask you to contribute small, strategic pieces of code yourself."

Three Pillars

Interaction protocol: Teaching-first by default; "just do it / no time / asap" switches to direct mode; asks your familiarity level (beginner/intermediate/advanced) once at the start; ≥2 failed attempts downgrades to a guided reveal. Output language follows your input: Chinese in, Chinese out; English in, English out.

Examples

Teaching DeepSeek Harness's principles — the verbatim output of a real learning-mode session — a full teaching turn showing how concrete explanations, guided thinking, a context-tied TODO(你), and the one-time opening calibration work together. This file is human documentation and is never loaded by any skill: the learning-mode skill teaches only principles and forms (placeholder templates); concrete examples are invented at runtime from your current task, so fixed examples cannot degrade generalization. If you want to keep a permanent example, put it here — not in learning-mode/skills/.

Install

Requires a DSH deployment using @deepseek-ai/dsh-persona 0.1.5-rc.1 or later (prefix schema). Older persona versions requiring text are not supported.

# Option 1: clone and copy
git clone https://github.com/CHplus0/dsh-learning-mode.git
cp -r dsh-learning-mode/learning-mode ~/.dsh/.agent-presets/

# Option 2: run the installer
bash dsh-learning-mode/install.sh

# Option 3: install the npm bundle (auto-installs the preset)
dsh plugin --profile web add dsh-learning-mode

Then open the DSH web UI, start a new session and pick 学习模式 (Learning Mode) — no restart needed.

Upgrade an existing installation

The npm installer skips existing preset directories to preserve user edits. Updating the bundle alone does not repair presets installed by [email protected] or earlier.

1. Locate ${DSH_HOME:-$HOME/.dsh}/.agent-presets/learning-mode/agent.cordis.yml. If you configured presetId, use that directory name instead.
2. Back up the file. Under the @deepseek-ai/dsh-persona row's config, change only text: |- to prefix: |-, keeping the indentation and persona prose unchanged. Update the persona.text comment to persona.prefix too. If it already uses prefix, no change is needed.
3. Restart the DSH host and select Learning Mode in a new session.

Alternatively, run bash dsh-learning-mode/install.sh from an updated checkout. It backs up the entire existing directory before replacing it; local customizations must be restored from that backup. This script honors DSH_HOME but always targets the default learning-mode directory.

Customization

• Tone & identity: edit learning-mode/agent.cordis.yml → persona.prefix.
• Style details & phrasing templates: edit learning-mode/skills/learning-mode/SKILL.md.
• Rename: edit only name in learning-mode/preset.yml (the directory name is the preset id, must match [a-z0-9][a-z0-9-]*; renaming requires renaming the directory too).

How it works

• agent.cordis.yml is a full copy of the standard preset with two changes: the persona is replaced with the teaching identity (the three pillars, always in the system prompt), and skill-filesystem gains customSkillDirs pointing at this preset's bundled skills/ directory (the full guide loads on demand, not in the standing prompt). The toolset is identical to the standard coding agent (Shell, files, search, Skills, planning, goals, subagents, workflows).

License

MIT © 2026 CHplus0. The preset composition is adapted from the standard agent preset of deepseek-ai/deepseek-harness (MIT © 2026 DeepSeek); see LICENSE.