Plugins

11 skills de workflow partageables (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) en pack de skills installable.

Kit opérationnel axé sur les preuves : six outils en lecture seule (catalogue de capacités, plans de workflow par étapes, lecteur de skills empaquetés, recherche bornée dans la mémoire locale, audit des releases du dépôt, checklist de release) et cinq skills empaquetés — planifie et audite, sans jamais écrire à distance.

SHOPLINE AI Toolkit : relie le serveur MCP officiel SHOPLINE Developer et fournit sept skills d'agent SHOPLINE (Admin REST, GraphQL, OAuth, webhooks, Sline) — l'équivalent SHOPLINE du Shopify AI Toolkit.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

Graphical skill manager for DeepSeek Harness — create, edit, import, and delete SKILL.md skills from the web settings UI. · DSH 技能管理器：在网页设置里图形化新建、编辑、导入、删除 SKILL.md 技能。

Unified DeepSeek Harness connector: edit MCP servers (cordis.patch.yml) and user skills (~/.dsh/skills) from one Web UI settings page.

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

Capability transform & assembly engine (Qian Xuesen cybernetics/systems framework): static resident layer manages the skill/MCP/plugin registries, auto-absorbs skills and tool metrics, and drives a negative-feedback evolution loop (scan Sick/Weak → mutate → select promote/reject → 30s rollback); includes a Web UI panel and a GitHub dsh-plugin store bridge.

Skill Manager page in the DSH settings panel: browse system / user / workspace / preset skills, expand a skill to its file tree, view and edit files, import skills from a zip, and export or delete them (system skills read-only).

Cron scheduler with a sidebar UI: run shell, Python or Node scripts, skills, or agent tasks on a schedule, with push notifications and session archiving.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Ponytail lazy senior dev mode: 6 skills adapted from DietrichGebert/ponytail.

273 ECC skills (95.8% of the 227k-star operator system) ported to DSH in four batches.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Memory Lake as a persistent memory layer for dsh: memory_search, memory_remember, and memory_forget tools over the memorylake CLI, a session status line, and guided setup/diagnostic skills, sharing one ~/.memorylake identity and memory set with the Claude Code and Codex plugins.

Organize DeepSeek Harness workspace sessions by renaming them as 类别｜主题 and reporting archive, rename, and review suggestions.

Gestionnaire de skills pour l'interface web dsh : une entrée dans la barre latérale plus un panneau listant les skills visibles pour la session en cours (répartis en groupes global / local) avec des interrupteurs marche/arrêt par skill, création / import / édition / suppression. Désactiver un skill le retire de la liste active.

Centre de skills intégré à l'interface pour DeepSeek Harness (dsh) : parcourez le catalogue local complet des skills depuis le registre officiel ctx.skills (toutes les racines et les fournisseurs tiers), activez/désactivez des skills, inspectez leur contenu, faites remonter les diagnostics de frontmatter, et créez de nouveaux skills.

Plugin fournisseur optionnel pour dsh-skill-pack-security : enregistre le dossier skills/ (zh) ou skills-en/ (en) du pack dans ctx.skills. Les deux éditions sont embarquées dans pack/.

Relie les skills et la configuration de Pi Agent à DeepSeek Harness.

Relie la mémoire, les skills et la configuration d'OpenAI Codex à DeepSeek Harness.

Couche de compatibilité Claude Code pour DeepSeek Harness : charge les skills/commandes/agents .claude et installe les plugins des marketplaces Claude Code comme skills dsh natifs.

Génération de PPTX stable et modifiable pour agents IA — IR sémantique en entrée, DrawingML natif en sortie.