Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

222 plugins found

5

dsh-peak-reminder

54nanmiao/dsh-peak-reminder

Peak-hour reminder: while DeepSeek charges peak rates it shows a banner at the top of the DSH Web UI every N minutes (default 5, range 1-120), adds one at each peak/valley switch, stays silent during valley hours, and keeps a sidebar row with the current state and a countdown to the next switch. Peak rules (Beijing time Mon-Fri 09:00-12:00 and 14:00-18:00; weekends, Chinese public holidays and 调休 weekends are valley all day) are evaluated in the host and served over two no-auth routes, /plugins/dsh-peak-reminder/state and /config; settings live in settings.section and are stored in ~/.dsh/peak-reminder.json.

211 days agoUsage & BillingMIT
S

dsh-linghun-assembler

syyr1987/dsh-linghun-assembler

Memory-assembly team for DeepSeek Harness: every message triggers a five-step cognition loop (judge, retrieve, assemble, feedback, calibrate) carried by role-playing subagents (judge, retriever, archivist, advocate, editor, scribe), using BM25 retrieval, time-ordered material, and LLM assembly to build useful material packs injected into linghun. Works with dsh-linghun.

215 days agoMemory
P

dsh-skill-intelligence

polinnizhong/dsh-skill-intelligence

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

2last monthSkillsMIT
N

insta360-ai-content-studio

nicecx/insta360-ai-content-studio

Automated daily content pipeline for Insta360 GO 3S: BLE/WiFi remote capture of aquarium footage, wireless import, ffmpeg quality evaluation with decision log, Auto editing (segment selection, TTS narration, music, subtitles), and Bilibili upload via biliup (dry-run by default).

23 months agoTools & CapabilitiesMIT
O

dsh-webbridge

omdsh-dev/dsh-webbridge

Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon

23 months agoTools & CapabilitiesBSD-3-Clause
J

semantic-search

johnxu22786/semantic-search

Local semantic code search for DeepSeek Harness: fragment-level symbol-aware indexing, offline lexical embeddings or an OpenAI-compatible endpoint, and hybrid vector + BM25 retrieval fused with RRF - three dsh tools plus a sema CLI.

23 days agoTools & CapabilitiesMIT
G

dao-zang-skill

godners-code/dao-zang-skill

Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture chunks with exact original-text extraction (line numbers, hit markers), and one-command workspace setup from the Godners/DaoZang dataset.

23 months agoSkillsMIT
Z

dsh-plugin-thread

zhaoyuntao-wl/dsh-plugin-thread

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

24 days agoMemoryMIT
K

dsh-side-chat

karloflaw/dsh-side-chat

Native side-by-side chat beside the main conversation: an independent archived DSH session with full native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

23 months agoUI EnhancementsMIT
Y

dsh-profile-lab

young-tim/dsh-profile-lab

Runs reproducible DSH profile and patch experiments with guided case authoring, assertions, Web comparison reports, recovery, and policy gates.

23 months agoDev & Plugin ToolsMIT
V

dsh-code-reference

victorzhong0110/dsh-code-reference

Surveys local code and GitHub/npm for reusable implementations before development, evaluates reuse versus rewrite, and checks architecture coupling.

22 months agoWorkflow & AutomationMIT
Z

dsh-cdp-browser

zaiwenj/dsh-cdp-browser

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

23 months agoTools & CapabilitiesMIT
J

dsh-meta-orchestrator

jiruidai/dsh-meta-orchestrator

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

23 months agoWorkflow & AutomationMIT
O

dsh-kb-sieve

omdsh-dev/dsh-kb-sieve

Build auditable KB packs (SQLite FTS5) from md/txt/docx/pdf with deterministic retrieval and original-text reading.

23 months agoMemoryApache-2.0
L

API-MRI

lee-eee-eee/api-mri

Inspect API latency, streaming output and model-response fingerprints from a native DSH panel, with classic-task previews and public benchmark rankings.

16 days agoTools & CapabilitiesMIT
Y

dsh-calc-tool

yhy854/dsh-calc-tool

Calculator tool that evaluates arithmetic expressions with a hand-written recursive-descent parser. No eval or new Function; whitelisted identifiers, length and nesting limits, and structured error codes.

18 days agoTools & CapabilitiesMIT
A

dsh-plugin-dualtransfer-trial (dualtransfer)

axtut/dsh-plugin-dualtransfer-trial

Cross-computer Harness Agent messaging, commit-specific task handoff and parallel-branch or shared-baseline Git project collaboration with diff and conflict previews. Pairing, binding and the receiver's existing local authorization remain required. Not open source (UNLICENSED evaluation build, not for production); requires Node.js 24+ and Git 2.38+ for project collaboration, tested only on macOS arm64 and Windows 11 x64 build 22621+. The project.3 candidate passed 60 targeted checks per platform; full Host/browser, physical two-machine and model end-to-end validation remain pending. DSH 0.2.2-rc.1 has only limited gate/SDK checks, not full installation and runtime validation.

13 days agoIntegrations & Remote
A

dsh-skill-author

apq/dsh-skill-author

Model-facing skill_manage tool that saves, replaces, or deletes Harness skills at user or project scope, with a standing system-prompt section that asks the model to evaluate skill retention before ending a reusable task.

17 days agoSkillsMIT
Z

almost-for-ever

zwebzzz/almost-for-ever

Derives the index from your Markdown memory files on every turn instead of keeping a hand-written index table, so renames, splits and deletions never leave a stale entry. Retrieval ranks by library tags, section tags, title tokens and body text, then injects the matching line ranges rather than whole files. Writing is model-proposed and user-confirmed through a sticky note; entries are appended after the target section's format is detected. Ships a structure panel showing each library and section with line ranges and token estimates, a starter template for an empty memory directory, and optional appearance controls.

12 days agoMemoryMIT
D

dsh-plg (dsh-plugin-pack)

dreanzy/dsh-plg

Disable plugins per workspace: a disabled plugin stops contributing tools to the model tool list and prompt sections to the system prompt, cutting the per-turn schema cost. A plugin is switched as a whole, with packs evaluated by workspace binding, then default.

1yesterdayDev & Plugin ToolsMIT
H

scenes-skill-creator

huaweicloudskill/scenes-skill-creator

DeepSeek Harness web panel for creating, evaluating, repairing, and installing skills, delegating generation to the official generic and Huawei Cloud skill creators. Needs git, bash and python3, and network access to gitcode.com (the creators and reference data are pulled from there); the creator runs shell commands with danger-full-access by default.

19 days agoSkillsMIT
H

dsh-memory-agent

heart3-xdugt2/dsh-memory-agent

Local DSH companion plugin with long-term memory, graph-assisted retrieval, emotional state, reflection, group context, and audit views. Targets Windows with Node 24 and Python 3.14 (the basic engine uses the Python standard library, no pip; without Python it falls back to the JS retrieval path).

17 days agoMemoryMIT
A

dsh-prompt-optimizer-button

az-666316/dsh-prompt-optimizer-button

Prompt optimizer inside the DSH composer. One click rewrites the current draft with the model you already selected: it classifies the scenario (paper / repo evaluation / agent task / daily question / English writing), returns a compact three-check diagnosis panel (is acceptance testable? missing information or capability? raising depth or widening scope?), and lets you pin a scenario manually. A running rewrite can be stopped without writing a half result back, a selected fragment can be rewritten on its own, and every rewrite keeps an undo history per session in the browser (up to ten steps). The draft is replaced in place, with no extra chat turn. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

13 days agoUI EnhancementsMIT
S

dsh-fine-tune

songrui111/dsh-fine-tune

Local LoRA and QLoRA fine-tuning in a panel: import JSONL, see a VRAM estimate before training starts, evaluate, and export an adapter. One-click Python venv setup, but you must supply your own Python 3.10+ and an NVIDIA GPU (6 GB or more). Verified end to end on Windows 11 with an RTX 3060 6 GB; the installer refuses non-Windows hosts, so Linux, macOS and other GPUs are unsupported for now.

17 days agoModels & ProvidersMIT