Categories › Development
Development
1550 pluginsCode, Git, docs, workflows and skill packs — for writing code and running projects.
Sorted by downloads. 100 per page.
dsh-port-inspectortested
Track the origin of local development ports on Windows and safely manage verified DSH serv
↓ 933
dsh-git-managertested
A GitHub-connected visual git manager for DeepSeek Harness: guided GitHub-Flow steps, comm
↓ 931
@istarry/dsh-skill-suitetested
Agent skills: browse, toggle and edit skills in the management page, and let the agent wri
↓ 927
cot-linttested
Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs
↓ 926
dsh-skill-palettetested
A skills button at the bottom-right of the input box: one click opens every installed skil
↓ 925
@zhengjunyao/dsh-updatertested
Track DeepSeek Harness's own releases and update in one click: reads the npm dist-tags and
↓ 925
dsh-evolution-labfails
Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, q
↓ 923
@dsh-self-evolving/coretested
Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot re
↓ 922
@tianbuyu-wwx/dsh-hermes-linktested
Bidirectional Hermes ↔ DSH bridge: import Hermes sessions into DSH, consult Hermes, and re
↓ 919
dsh-subagent-profilefails
Dispatch subagents with named profiles (model, reasoning effort, and tool scope per task),
↓ 917
dsh-agent-relayfails
Loopback-first multi-agent message relay: HMAC-authenticated broker plus dsh plugin (relay
↓ 916
dsh-user-experiencefails
Finds potential UX issues in your project: automatically reviews React/TypeScript code, pi
↓ 916
dsh-pr-boardtested
Maintainer and developer PR board for the DSH sidebar: a five-state review queue (waiting
↓ 914
@ch4acko3/dsh-code-rendertested
Escaped, theme-aware HTML code-block rendering service for DSH Web plugins, built on struc
↓ 913
↓ 910
dsh-smart-restartfails
Wakes the main agent after any DSH restart so interrupted work resumes automatically — add
↓ 909
@s1lencewill/dsh-markdown-readertested
Renders workspace Markdown files in a standalone full-screen reader with GFM, KaTeX, Merma
↓ 905
@xzhi/dsh-simple-worktree-plustested
Manages Git worktrees in DeepSeek Harness with branch deletion controls and scoped workspa
↓ 905
@hhuangpanda/dsh-automationfails
Runs one-time and recurring Agent tasks in fresh DSH sessions, with natural-language sched
↓ 904
dsh-tool-workflow-plustested
Drop-in enhanced fork of the official workflow tool: a verbatim fork of the stock tool plu
↓ 900
dsh-commercial-ui-uxtested
Registers the commercial-ui-ux skill for DSH: task-aware commercial UI/UX/GUI design, revi
↓ 899
dsh-pptx-editorfails
Preview and edit attached PowerPoint presentations in the DSH sidebar through conversation
↓ 898
dsh-overleaffails
Connect multiple Overleaf projects to DSH through OverleafMCP for browsing, analysis, and
↓ 896
dsh-testkitfails
Docker-isolated real-host lifecycle tests for DSH plugins across install, boot, tool regis
↓ 895
dsh-n8n-plugintested
Operate n8n from DeepSeek Harness with a multi-instance registry, alias-addressed agent to
↓ 894
pstack-dshtested
Ports poteto's pstack engineering playbooks to DSH, covering planning, review, verificatio
↓ 890
dsh-plugin-stalegreentested
Freshness gate for the agent's test, typecheck, lint and build claims: each verification r
↓ 890
dsh-updater-npmtested
DSH updater + official docs sync in Settings: one-click npm update of @deepseek-ai/dsh wit
↓ 889
↓ 887
dsh-cite-lenstested
Cite Lens for dsh: select text in a PDF in the Files tab to quote or ask about it in the c
↓ 882
dsh-skill-managetested
Agent-managed procedural memory: a skill_manage tool that creates, patches, disables and d
↓ 882
dsh-tool-generate-imagetested
Model-facing `generate_image` tool for text-only models: the model asks for a picture in n
↓ 880
dsh-plugin-coalignetested
Installs the coaligne-workflow skill for CoAligne team collaboration; requires CoAligne De
↓ 879
@jeremy9682/dsh-skill-packtested
11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait
↓ 877
dsh-project-managertested
Project board: kanban card groups with custom stages, cards linked to landfill-project mem
↓ 873
dsh-context-windowtested
Extends the composer model selector menu with a third Context window row, preset capacitie
↓ 868
dsh-typesafe-ai-skilltested
Registers the TypeSafe/Jev (System One) skill into DeepSeek Harness's global skill layer,
↓ 866
dsh-concurrency-guardtested
Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model reque
↓ 866
@aaronandwork/dsh-evidence-gatetested
Evidence-first conclusion gate that cross-checks first-hand claims against a durable per-s
↓ 862
dsh-region-editfails
In the DSH desktop file preview, click an HTML element (with its source line and column) o
↓ 861
@lanbaolu/dsh-fail-softfails
Automatically disables a failing plugin so the rest of DSH keeps booting — by patching DSH
↓ 860
dsh-time-machinefails
Creates local, content-addressed workspace checkpoints with diff previews and two-phase re
↓ 860
dsh-agent-canvasfails
Interactive canvas for visualizing Agent, Subagent, Workflow, Phase, and tool relationship
↓ 857
codex2dshfails
Migrate Codex (OpenAI Codex CLI / Desktop) MCP servers, skills, instructions, memory and s
↓ 856
dsh-gme-test-generatorfails
Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start
↓ 855
routinekitfails
Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routine
↓ 855
dsh-environment-traytested
Manage environment variables, .env files, and credentials in DeepSeek Harness, including W
↓ 851
@fengbinmov/dsh-git-panelfails
The session page has an extra "Git" page; on the left is a preview of the non-staged/stage
↓ 849
dsh-tender-workbenchfails
Tender search and bid intelligence in DeepSeek Harness with proposed project search, rule
↓ 848
dsh-paperlabfails
Overleaf-style LaTeX paper workbench: annotate any text in the rendered PDF and let a dsh
↓ 846
@longbowzz/dsh-codegraphtested
Turn code flows into source-linked Mermaid diagrams and interactive CodeWalkthrough explai
↓ 845
dao-zang-skillfails
Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture
↓ 845
dsh-perfscopefails
One-click health check for DeepSeek Harness: 0-100 score, plain-language issue list, and s
↓ 845
dsh-doc-readertested
Read PDF, DOCX, XLSX, PPTX and text documents as agent tools, and OCR scanned PDFs or imag
↓ 844
dsh-plugin-mission-controltested
Streams DeepSeek Harness sessions, messages, tool activity, and turn outcomes to a JARVIS
↓ 843
dsh-gitflowfails
Adds approval-gated Git status, diff, log, commit, branch, and optional checkpoint tools.
↓ 843
dsh-hot-reloadtested
Reloads an upgraded plugin inside the running dsh process instead of restarting it, and ro
↓ 842
dsh-mac-keep-awaketested
macOS only: holds a PreventUserIdleSystemSleep assertion (caffeinate -i -w <host pid>) whi
↓ 841
dsh-autoresumetested
When a dsh turn gets interrupted — by a web restart or an upstream hiccup (rate limit, 5xx
↓ 840
dsh-plugin-superselffails
Superself's self CLI as model-facing tools (project context, work units, reports, decision
↓ 839
dsh-auto-continue-429fails
Automatically sends "continue" to recover from RATE_LIMIT (429) and QUOTA (insufficient_qu
↓ 838
dsh-complex-project-presetunregistered
Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written
↓ 838
dsh-task-efforttested
Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[eff
↓ 838
dsh-builtin-togglestested
Evidence-backed inspector for DSH Web built-in capabilities: runtime/config provenance, co
↓ 837
@whybebabo/dsh-file-review-tabtested
Sidebar tab that lists a session's file changes by turn, expands line-level diffs and undo
↓ 836
dsh-mcp-skill-panelfails
MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free c
↓ 835
@dsh-gis/dsh-opengis-skilltested
Bundles the 32 gis/ skills of opengis-skills (GDAL, QGIS, GeoServer, PostGIS, PROJ, PDAL,
↓ 833
dsh-project-kanbantested
Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning pl
↓ 833
dsh-desktop-shortcuttested
Windows desktop shortcut for dsh web: launches the server, auto-opens the browser when rea
↓ 833
dsh-readcachetested
Version-token-validated in-process result cache for the DSH read tool: repeated reads of u
↓ 832
@weibaohui/dsh-thinktanktested
Think tank: a built-in library of 161 classic mental models (decision/strategy/cognition/p
↓ 829
↓ 825
@dsh-error-tell/client-telltested
Boot-time watchdog for DSH web: detects broken plugins, disables them persistently so the
↓ 825
@zihaovistonwang/stata-ai-skilltested
Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH
↓ 824
dsh-env-manager-plugintested
File-based environment registry for DSH: manage environments, services, deployments and op
↓ 824
dsh-devtoolsfails
Metadata-first runtime profiler for DSH agents: turn/step traces, model and tool wall-time
↓ 823
dsh-skill-authoringtested
Ships a skill about writing DSH skills - SKILL.md frontmatter and root precedence, how to
↓ 821
dsh-cursor-acpfails
Hands standalone jobs to the Cursor CLI signed in on the same machine, with CLI readiness
↓ 819
dsh-skill-mini-managertested
Skill manager page in the DSH Web Settings panel, at the same level as Plugins: lists ever
↓ 818
dsh-elab-cockpittested
Embedded closed-loop development cockpit for DeepSeek Harness: the agent builds, flashes,
↓ 818
dsh-dev-workbenchtested
Workbench with an AI assistant, pause/stop controls, separate background-model settings, t
↓ 812
@chtholly-fan/dsh-cpp-optimizationtested
C++ audit skill: detects the target project's actual C++ standard before making any recomm
↓ 808
dsh-syncfails
Policy-driven Git sync for DSH settings and profile configuration, with secret-aware proje
↓ 806
dsh-llm-tracetested
Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provi
↓ 806
dsh-jev-subagent-dispatchtested
Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy a
↓ 805
dsh-skill-stationtested
Sidebar skill hub: scan Claude/Codex/Cursor/Gemini skill directories for one-click import,
↓ 804
dsh-plugin-aiteliertested
Runs AItelier pipelines from DSH over MCP: 39 tools (22 read, 17 write) to generate, run,
↓ 804
dsh-open-code-reviewfails
Alibaba Open Code Review for DSH: host-model delegation with native preview/rule tools and
↓ 803
dsh-startup-guardtested
Boot-time guard that repairs corrupt session logs, preflights plugin composition, vm-check
↓ 803
dsh-fail-fasttested
Fail-fast tool batches for DeepSeek Harness: inside a step, concurrency-safe calls still o
↓ 802
dsh-large-jsonl-viewertested
Read-only JSONL and NDJSON viewer with a byte index, record navigation, and streaming prev
↓ 801
@zebbkira/dsh-skills-mcp-managerfails
Skills & MCP manager in the DSH web settings: browse/enable/import/delete skills across pr
↓ 801
@oxmumu3/dsh-family-assistanttested
Owner workbench for independently connected family WeChat assistants, per-member project a
↓ 798
dsh-wrapup-guardtested
Enforces a check-fix-recheck loop when a task is wrapping up: it auto-runs your tests/lint
↓ 797
dsh-test-frameworktested
Test work framework for DSH that scaffolds a product, module and version directory tree, r
↓ 794
dsh-docx-formattested
↓ 793
dsh-plugin-superpowerstested
Ports the obra/superpowers methodology as 14 native DSH skills — brainstorming, writing-pl
↓ 792
dsh-best-ponytailtested
Ponytail lazy-senior-dev ruleset for DeepSeek Harness: a 7-rung minimal-code ladder (YAGNI
↓ 791
dsh-cloudqtested
Tencent CloudQ integration: AIOps chat mode with usage, inspiration, artifact and architec
↓ 791
dsh-automation-centertested
Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, usi
↓ 791