skills
anthropics
Public repository for Agent Skills
Tkingxiao/dsh-novel-solo
dsh-novel-solo is a tool for DeepSeek Harness. DeepSeek Harness "single-core writing" plugin: fully slimmed tools and hardened output for quantized small models, suited to running a novel pipeline locally with local models.

REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A niche but well-documented DSH plugin for local small-model novel pipelines; install if you fit that use case.
README documents a clear file structure (lib/index.js, lib/client.js, cordis.patch.yml, template/) and a vendored preset-scoped plugin, but no tests or CI are mentioned.
No download-and-execute or plaintext secrets are described, but the plugin writes to ~/.dsh paths and rewrites persona YAML in place, so risk cannot be fully assessed from the README alone.
Solves a concrete pain point for running long-form novel generation on quantized local models via tool slimming, a fixed pipeline preset, and a per-chapter review loop.
Last updated 2026-09-12, not archived, and the README documents a host-compatibility migration from DSH 0.1.2-rc.1 to 0.1.5-rc.2, indicating active upkeep.
README covers install commands, host compatibility, subagent-count wiring, preset structure, tool slimming, file layout, and env vars, though the install command field itself is listed as unknown.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
VALIDATION LADDER
FAQ
DeepSeek Harness "single-core writing" plugin: fully slimmed tools and hardened output for quantized small models, suited to running a novel pipeline locally with local models.
dsh-novel-solo has 4 stars and 0 forks on GitHub, last updated 2026-09-12.
dsh-novel-solo is distributed under the MIT license.
dsh-novel-solo is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:No valid category tags。