Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

59 plugins found

H

figcraft

harryheyu/figcraft

Scientific figures as code: agents create a versioned figure IR, patch it incrementally (one node at a time — untouched objects never move), and export publication-ready, true-vector SVG / PDF / PPTX. Seven papercanvas_* tools (create, get, patch, layout, lint, render, inspect) over a deterministic engine with FC001-FC008 quality lint and CJK-aware font resolution. Verified on DSH 0.1.5-rc.3 through 0.2.2-alpha.2. By the author of dsh-sessionflow. Requires the PaperCanvas engine installed separately: Python 3.11+ and the papercanvas CLI (not yet on PyPI — install it from this repository, put it on PATH or set papercanvasBin); the plugin is a thin adapter and ships no engine.

120 days agoTools & CapabilitiesMIT
B

dsh-plugin-baiguangda-style

browhitebyte/dsh-plugin-baiguangda-style

Chinese writing-register plugin for the Gcores/机核 editor 白广大: registers a 40 KB style skill plus style_lint / style_audit / style_rules tools — 4 hard-error and 27 warning checks (banned connectives, slogan inflation, empty quantifiers, uniform paragraphs, unsourced statistics, AI clichés), with thresholds calibrated on 444 articles / 802k characters; a settings page adds an on/off switch, single and batch trial runs, and JSON threshold overrides.

122 days agoTools & Capabilities
L

dsh-prompt-lint

lin-f1sh/dsh-prompt-lint

Reads your past DSH conversations and surfaces recurring prompt gaps — missing paths or versions, an unstated output format, missing preconditions that break tool calls — each with a paste-ready rewrite. Adds a one-click rewrite next to the composer that applies those constraints to the draft in a shorter form.

124 days agoTools & CapabilitiesMIT
5

dsh-wrapup-guard

566001/dsh-wrapup-guard

Enforces a check-fix-recheck loop when a task is wrapping up: it auto-runs your tests/lint/audit, blocks any round that still has unfixed problems, and only calls the task done after three consecutive clean full checks, then notifies the user.

1last monthDev & Plugin ToolsMIT
D

lgtm-dsh

dymzz/lgtm-dsh

DeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.

12 months agoGit & Code Review
C

cn-linebreak

chiang21fcb/cn-linebreak

Static HTML auditor for Chinese line-breaking: checks explicit-`<br>` orphan lines, keep-all CSS coverage, CJK line-start/line-end punctuation rules, and protected-phrase splits, then inserts <wbr> at natural breakpoints; exposes a cn_linebreak_audit tool for agents.

117 days agoTools & CapabilitiesMIT
F

dsh-figgenie-paper-diagram

field209/dsh-figgenie-paper-diagram

Draw paper figures as SVG the way top venues draw them, lint them against layout rules, edit them on a sidebar canvas, and export vector PDF or editable draw.io. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

02 days agoUI EnhancementsMIT
V

dsh-guofeng-studio

vamyane/dsh-guofeng-studio

Chinese-style songwriting studio for DeepSeek Harness: three bundled skills — a composer (mode and scale decisions, number-notation melody, pentatonic chords, arrangement table, three lint gates, multi-track MIDI), a lyricist (rhyme scheme, imagery, allusion control, structure, 14 lint rules, fill-in lyric slots), and a suite entry that connects both through .jp / .lyr / .slots.json files. The Python scripts use only the standard library and run fully locally.

06 days agoSkills
H

dsh-tvkt-vi

hieupt1904/dsh-tvkt-vi

Enforces a Vietnamese technical-writing standard on every agent: one prompt section applied to all modes, a skill with 30 writing rules and 70 terms, an agent mode with draft/review/rewrite discipline, and a bundled L001-L007 linter.

04 days agoTools & CapabilitiesMIT
Z

dsh-verify-kit (dsh-tablelint)

zjukop3/dsh-verify-kit

Markdown table check for generated reports: rows with the wrong cell count, a delimiter row that disagrees with the header, duplicate or empty headers, and tables with no rows. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

02 days agoTools & CapabilitiesMIT
Z

dsh-verify-kit (dsh-outline-lint)

zjukop3/dsh-verify-kit

Shape check for delivered documents: no title, more than one level-1 heading, a lost heading level, no conclusion up front, and nothing a reader can run to reproduce the result. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

02 days agoTools & CapabilitiesMIT
Z

dsh-verify-kit (dsh-numberlint)

zjukop3/dsh-verify-kit

Number consistency check for one document: the same quantity written 4,985 and 4985, the same percentage with and without a space, and ranges with mixed dashes. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

02 days agoTools & CapabilitiesMIT
Z

dsh-verify-kit (dsh-citelint)

zjukop3/dsh-verify-kit

Citation lint for delivered reports: numbering gaps, duplicate sources, sources that are listed but never cited, and local links that do not exist. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

02 days agoTools & CapabilitiesMIT
H

dsh-ubuntu-packaging

hougelangley/dsh-ubuntu-packaging

Ubuntu and Debian source-package tools for DeepSeek Harness: inspect debian/, lint with lintian-compatible codes, scaffold a debian/ directory, plan dpkg-buildpackage or sbuild builds and lintian/autopkgtest runs, and diagnose build logs. Read-only except scaffold; no shell execution and no network access.

05 days agoTools & CapabilitiesMIT
H

dsh-aosc-packaging

hougelangley/dsh-aosc-packaging

AOSC OS packaging toolkit for DeepSeek Harness: six Host tools inspect and lint ABBS packages, scaffold spec and autobuild/defines inside an ABBS tree, checksum source URLs, and draft topics and Ciel build plans, with a bundled aosc-packaging skill; no tool runs a shell, and building the .deb still needs Linux with root and Ciel.

02 days agoTools & CapabilitiesMIT
Y

dsh-policy-linter

yyhy110421/dsh-policy-linter

Read-only linter for AGENTS.md, SKILL.md and plugin prompt files that reports conflicting rules, duplicates, vague qualifiers and dangerous commands with file and line suggestions.

014 days agoDev & Plugin ToolsMIT
G

odoo-lint

getfluvo/odoo-lint

odoo-lint for DeepSeek Harness: lint and fix Odoo addons, and lint every addon file the agent edits

012 days agoTools & CapabilitiesMIT
L

guster

lumos-789/guster

Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones with light profiles, sections may live outside the hub root), a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.

0yesterdayDev & Plugin ToolsMIT
L

make-it-a-bit-better

lumos-789/make-it-a-bit-better

Autonomous product-polish loop skill: every round opens a fresh brainstorm from 3 forced perspectives, picks one small angle capped at ≤3 files and ≈100 lines, implements it, verifies with the repo's own tests, build or lint, and commits it as a single round commit; the round is logged to a per-project ledger, and ideas too big for one round go to an icebox. A red check ships nothing — the round commit is reverted immediately so the failed diff stays in history. Non-git targets are rejected before any work starts. Pure skill bundle: no MCP server, no runtime dependencies. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0.

0yesterdaySkillsMIT
P

dsh-pim-lint

perrylink/dsh-pim-lint

PIM catalog lint: required fields, duplicate SKU, GTIN check digit and price.

016 days agoTools & CapabilitiesApache-2.0
P

dsh-eval-pack

perrylink/dsh-eval-pack

Public/synthetic eval-pack lint and deterministic JSON grader; not a validated benchmark.

016 days agoDev & Plugin ToolsApache-2.0
L

dsh-ai-code-quality

lkdx0220/dsh-ai-code-quality

ai-code-quality (cq) tools for DeepSeek Harness (dsh): deterministic code-quality pipeline — doctor/scan/triage/baseline/diff/gate/waiver/spec-drift — aggregating ruff, mypy, radon, vulture, pytest-cov, import-linter and DeepSec. Read-only scanning plus a

0last monthDev & Plugin Tools
C

wos-pipeline

callyli00/wos-pipeline

Web of Science 文献流水线插件:检索式迭代历史与数量闸门(未过闸门强制用户确认检索词)、PDF 收编与 %PDF- 审计、解析编排(复用 dsh-pdf-mineru)、知识库骨架与五层 lint/index、浏览器作业守卫(强制关 tab / 强制把验证交给人)。全流程不依赖任何 skill。

026 days agoWorkflow & AutomationMIT
D

dsh-mp-catalog-guard

dingchenhui0618-arch/dsh-mp-catalog-guard

Content-catalog guard for WeChat mini-programs: validates catalog.json so every activity price is an integer amountFen, every template renders prices through money(), required fields / duplicate copy / image paths are checked, and the result is an issue list plus a unified diff that can be applied with patch -p1. 29 rules over five groups (catalog shape, required fields and uniqueness, amounts, rendering, images). Three fixes are automatic (legacy yuan amount, string Fen, absolute image path) and preserve the file's own indent, EOL and trailing newline; everything else is reported with a hint instead of being guessed. Dry-run by default; apply re-checks the written file so the report describes what remains. One implementation serves a tool, a conversation panel and a CLI with exit codes 0/1/2. Zero runtime dependencies, no model call, no network.

024 days agoTools & CapabilitiesMIT