Plugins

Local SQLite taskboard as a native overlay page: projects, tasks, comments, relations, attachments and workflow automation, with backlog → todo → in_progress → in_review → done statuses, `taskboard_*` Agent tools that can only submit work to in_review, a headless JSON CLI and a packaged skill.

给 HR / 猎头的 AI 招聘工作流：岗位标准梳理、Boss直聘 + 猎聘双通道寻源初筛、市场人才盘点、简历评估、约面试、候选人台账与日报。可装成 Claude Code 插件或 DeepSeek Harness (dsh) 插件——后者自带可直接上手操作的「招聘浏览器」面板；也能配合任意读 AGENTS.md 的 AI 编程助手使用。

Complete reverse-skill pack (85 SKILL.md) as a DeepSeek Harness Cordis plugin: reverse engineering, authorized pentesting and security-research skill router.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

Block-addressed document editing: an MCP server exposing geml_get / geml_set / geml_check and friends, so an agent reads or rewrites one addressed block of a Markdown or GEML document instead of the whole file. Ships the GEML authoring skill and a code-graph skill that builds and navigates a project call graph as GEML codemaps.

DSH Web UI plugin: Skills settings section with hot enable/disable, delete and add（Web界面的skill管理工具）

Accessibility-first macOS computer use: fresh observations, stale-state rejection, scoped permissions, and safe input.

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Automatic conversation distillation: background subagent reflection + skill create/update.

Superpowers skills for DeepSeek Harness: TDD, debugging, planning, and collaboration skills adapted from obra/superpowers

Collection of skills for Upstash

Quantum Algorithms Best Practices

Claude Science-style research workbench: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), and 10 science skills for genomics/pathogens/bioinformatics.

Blender 3D production plugin with 30 modeling/reconstruction skills, 13 runtime tools, and 26 deterministic helpers for reference fitting, rendering, validation, animation, and portable export; installable as `dsh-blender`.

WorkBuddy-style skill picker: a button beside the composer opens a searchable list of installed skills; picking one inserts the official /skill-name gesture, so the skill loads with your message.

Context injection audit: token costs of instruction chains / skill catalogs / tool schemas, duplicate and conflict detection.

DeepSeek Harness adapter for the Swift Cycle governance skill.

Design-aesthetics skill pack (10 styles: dark SaaS, minimal white, neumorphism, brutalism, glassmorphism, Japanese minimal, bento grid, cyberpunk, vaporwave, art deco) with runnable landing-page demos: tokens, component rules, forbidden lists, and acceptance checklists per style.

Infinite-canvas e-commerce visual workspace for product photography, virtual try-on, background edits, and video, synced live with the Harness conversation.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Complete chinese-traditional-wisdom (玄枢 / XuanShu) skill pack as a DeepSeek Harness Cordis plugin: bazi, ziwei-doushu, liuyao, meihua, qimen, daliuren, taiyi, wuyun-liuqi, constitution and fengshui calculation, with a local deterministic engine and a visualization dashboard.

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.