whh110112/human-writing-skills--plugins-deepseek-harness ↗★ 2
dsh-advanced-human-writing
DeepSeek Harness bundle for verified long-form writing audit, continuity ledgers, and bounded reviewer coordination.
AI Analysis
核心用途是在本地协调和验证长文写作的审计与审阅任务。适合需要规划长文、分发审计任务并验证覆盖率的写作与编辑团队。必要条件是需在 Python 环境中安装 `human-writing-skills`。
Install
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:whh110112/human-writing-skills#2b02ae77bd1ea009ea2d7a1cc6d2dcdce1437a00&path:plugins/deepseek-harnessREADME
Read the full README ↗Advanced Human Writing for DeepSeek Harness
This DeepSeek Harness bundle mounts the human-writing-mcp tools from the
parent repository. It coordinates bounded long-form reviews locally: create a
plan, let separate agents claim focused work, require complete coverage
receipts, and unlock the final reconciliation only after verification passes.
Prerequisites
Install the Python package in the environment selected by PYTHON or python:
pip install human-writing-skills
For development from this repository:
pip install -e .
Install
After publishing this folder to npm, add it to a DeepSeek Harness profile:
dsh plugin --profile web add dsh-advanced-human-writing
Restart the affected DSH profile. The bundle uses the workspace as its allowed
file root. Set PYTHON before launching DSH when the desired interpreter is
not named python.
The mounted tools are plan_long_form_audit, list_audit_tasks,
claim_audit_task, submit_audit_report, verify_audit_coverage,
get_reconciliation_task, and read_project_context.
This package does not send drafts to a third party and does not call a model by itself. The active DSH agent performs each assigned review and must submit its own report.