Plugins

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

Spec-driven development discipline for dsh: five keel skills (anchor/spec/probe/build/audit), three review tools and six spec templates enforce specs-before-code, assumption verification and scope control.

Scans the skills visible to the current session and ranks them by relevance to the recent conversation.

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

Skill manager for the dsh web GUI: a sidebar entry plus a panel listing the skills visible to the current session (split into global / local groups) with per-skill on/off switches, create / import / edit / delete. Disabling a skill removes it from the mod

Bridge Pi Agent's skills and configuration into DeepSeek Harness

Bridge OpenAI Codex's memory, skills, and configuration into DeepSeek Harness

Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Puts the agent on the Muretai network: its own identity, invite-based introductions, signed end-to-end encrypted messaging with agents owned by other people, and an inbound-mail wake that lets it reply on its own.

Native Search1API (s1) web research tools: search, news, page crawling, sitemap discovery, and trending topics as first-class `s1_*` tools, with a bundled s1 skill.

Project .pack.json/.pack.zip into .agent-pack/modpacks/ and expose skills via a workspace allow-list.

Control labscript-suite experiments from DeepSeek Harness: runmanager globals and scans, submits and waits, YAML fixed-operation protocols with postprocess write-back, panel snapshots, a built-in mock backend and a read-only doctor.

Multi-platform Git workbench for DeepSeek Harness: manage Gitea, GitHub, GitLab and Gitee accounts at the same time, browse repositories and branch graphs, review pull and merge requests, check contribution heatmaps, and sync-push one commit to several platforms.

Build named subagents and skills in a sidebar panel, then call any subagent by name in a conversation. Each subagent selects a model, reasoning effort, spawn or fork mode, a tool allowlist and skills; skills can be global, per workspace or per conversation.

Local previews for 450 file formats with a session file workspace, including Office, PDF, iWork, CAD/3D, RAW and 360° media.

Pre-install security gate: quarantines each plugin, skill and subagent bundle with install scripts disabled, scans it with Cisco Skill Scanner, SkillScan, Cisco MCP Scanner, OSV-Scanner, Trivy, Gitleaks and optional SARIF tools or an LLM judge on a DSH model, then passes, asks for review or blocks it. Needs the install-gate hook proposed in deepseek-ai/deepseek-harness#12999.

Skill manager for the DeepSeek Harness sidebar: lists global and project-level skills with call counts, last-used dates and estimated context tokens, and archives or restores a skill by moving its directory into a reversible skills-archived next to the skills root.

Chinese tax and cross-border e-commerce workbench: a local BigInt statement parser for Amazon, TikTok Shop, and Stripe CSV/TSV/XLSX exports (fintax_parse_statement), a 7-scenario deterministic tax and reconciliation calculator (fintax_calc), 4 read-only Tencent IMA knowledge-base tools (ima_list_kbs, ima_browse, ima_search, ima_read), 4 bundled compliance skills, and an in-app settings section. Statement files are parsed locally; optional IMA credentials are read from environment variables or ~/.config/ima/ (write-only via authenticated /api/fintax routes, never echoed back) and sent only to ima.qq.com; zero runtime dependencies.

Browse local AI agent projects in one DeepSeek Harness panel: filter and pin projects, pick memories, skills, and recent sessions, then continue in the original directory with an editable DSH handoff draft or export it as Markdown.

A DSH Desktop enhancement plugin offering Skills/MCP management, global instructions, task notifications, and other practical features, with options to streamline built-in functionality as needed.

Extract CSS themes from URLs, DOCX or PDF; generate, validate and export ColaMD contract themes, and export Markdown to standalone HTML or PDF.

Reviews each finished turn, distills reusable skills as drafts, runs code-level checks over them, and holds each draft until the user approves or rejects it with a directive; every write is recorded in a SHA-256 ledger that supports rolling back a single entry. On by default, it reviews finished turns with the current session model (or an OpenAI-compatible endpoint set through DSH_EVOLUTION_BASE_URL), sending a bounded excerpt of the conversation, and writes drafts to ~/.dsh/skills/.staging until you promote them. Its bundle patch lowers DSH's skill-catalog description limit from 500 to 80 characters for every skill, and it starts an unauthenticated HTTP server on 0.0.0.0:18890 (DSH_EVOLUTION_PORT) that can list and promote drafts, change settings and trigger reviews.

Load skills to reveal bound tools on demand, with per-tool blocking and MCP support.