1,014 tagged deepseek-harness, measured the same way as everything else here.
Browse within: dsh-plugin 873dsh 612deepseek 260agent 212ecc 200skills 144dsh-skill 141plugin 121codex-skills 98marketing-automation 98cordis 91codex-cli 87ctf 87cybersecurity 87
Asaiuta/reverse-workbench-skill
Skill Codex
Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
SparkElf/deepseek-harness-plus
Skill Claude CodeCodex
Use before adding, moving, publishing, curating, or default-mounting a DSH capability to decide plugin ownership, npm distribution, repository placement, and profile composition independently.
Skill Claude CodeCodex
Review DeepSeek Harness session history as a local evidence-backed workflow retrospective. Use for DSH usage review, friction analysis, privacy-bounded session insights, or an offline HTML dashboard; do not use for token billing or non-DSH logs.
Skill Claude CodeCodex
A skill for finding plugins in the DeepSeek Harness ecosystem, a collection of add-ons for that coding-agent platform.
Skill Codex
Open and orchestrate the local DeepSeek Harness Skin Studio, co-design a structured DSH theme through MCP or JSON CLI, show live preview in the independent web UI, and safely apply or restore only after the human confirms in that visible UI. Use when the user asks to design, preview, change, inject, install, repair…
Skill Claude Code
Publish an HTML document as a shareable link the recipient can open in one tap, with PDF/image/Word export. Use when the user has an HTML document — a proposal, report, invoice, dashboard, landing page — and wants to send, share, deliver, or show it to someone, or asks how to get it to a client. Also use after writing…
Skill Claude CodeCodex
Use Guardian MCP tools to monitor, intervene, and analyze ML training. Covers 35 tools across monitoring, checkpoint analysis, recovery, dashboard config, and cross-experiment queries. Use when the user asks about training status, anomalies, checkpoints, experiments, model analysis, or when Guardian MCP server is…
nigedazhima/dsh-plugin-chatcut
Skill Claude Code
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user wants generated speech from text, wants to clone a consented voice from uploaded reference audio, wants to add/replace/align narration or voiceover for an existing video/timeline, wants…
Skill Claude CodeCodex
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
Fly2Kiana/Codex-DSH-Orchestrator
Skill Codex
A set of instructions for coordinating work between Codex and DSH through an existing tool connection. DSH is treated as a worker for bounded coding tasks, while Codex keeps responsibility for planning, technical decisions, supervision, and final review.
Skill Claude CodeCodex
A workflow for learning reusable rules from completed tasks. It recalls relevant rules, applies them, records whether they helped, and learns new situation-to-action lessons when appropriate.
Skill Claude CodeCodex
Supervise a coding task through the dsh-gate MCP tools, including durable reconnect, interaction handling, observation cursors, the five-minute aggregated progress cadence, and strict completion validation. Use when the user asks Codex to delegate or supervise work in a DSH Host. Do not use for ordinary local coding…
BENZEMA216/wechat-archive-harness
Skill Claude CodeCodex
Safely diagnose, synchronize, verify, and report a local macOS WeChat archive through the wechat MCP tools. Use when the user asks to archive, export, refresh, verify, or periodically synchronize their own WeChat history, including local text, image, voice, and video coverage.
Skill Claude CodeCodex
An interface for using Kling AI, a tool that generates images and videos from written or existing visual material. It supports several image, video, motion-control, and task-status workflows.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: