Plugins

Tablero de enfoque para agentes de DeepSeek Harness: notas duraderas mantenidas por el modelo en el espacio de trabajo de la sesión que fijan el objetivo, las restricciones y las decisiones a través de compactaciones y sesiones, con inyección automática en el contexto, archivo al limpiar y panel web opcional.

Endurance-coaching skill bundle that defaults to Intervals.icu for training data (activities, intervals, streams, training load, HRV, resting heart rate, sleep in-bed hours, eFTP) and uses COROS only for training-plan read/write and for fields Intervals.icu lacks (sleep score, recovery score), with iGPSPORT as a fallback for ride details. It turns that data into readiness gating, VDOT pace and heart-rate zones, periodized weekly plans, session reviews, race-day pacing and fueling, and weather-adjusted workouts. The bundle registers the endurance-coach skill in the profile, ships deterministic helper scripts, reads an athlete profile created by its init script, and requires the agent to state when data is unavailable instead of inventing it. Data comes through separately installed MCP servers — the Intervals.icu MCP server for training data, the dsh-coros plugin for training-plan read/write and sleep/recovery scores, an iGPSPORT MCP server only as a ride-detail fallback — and its bundled scripts need Python 3.10+; with none of them it works only from numbers you type in.

Bridges the official COROS MCP server into DeepSeek Harness with a self-contained local stdio-to-HTTP bridge and on-device OAuth login, exposing 34 COROS tools on the current endpoint for sleep, HRV, resting heart rate, recovery, training load, activities and FIT files, plus workout and training-plan CRUD and scheduling.

Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.

Nine single-ink print palettes — sage linen, kraft paper, lead type, cyanotype, risograph, CRT tube, phosphor screen, punch card, floppy disk. Each palette carries its own paper grain, type pairing, corner shape, section rule and a whale mark redrawn in its ink, plus a letterpress pass (paper tooth, sheet mottle, ink bite) that can be switched off. Every palette ships separate light and dark tokens.

JetBrains IDE bridge for DeepSeek Harness on Windows: installs as a DSH bundle, publishes the authenticated DSH URL, registers the open IDE project, relays the IDE MCP server, and serves a compact tool-window panel with streaming, approvals, Plan/Act, steer sending, session switching and archived-session filtering. The matching IDEA plugin is attached to the same release; your DSH agent can install it.

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.

Zhinao (second brain) for DeepSeek Harness: Markdown-authoritative layered memory (L1 long-term model gated by user confirmation / L2 knowledge with mandatory sources / L3 recent status under daily quotas), a local recall ledger explaining every injection, lifecycle engine with weekly review and a Web panel. First-run wizard initializes a blank brain, adopts an existing Zhinao directory read-only, or fills in only missing skeleton files; existing files are never touched.

One click beside the composer turns a half-formed draft into a structured prompt the AI can act on: goal, constraints, output format and acceptance criteria filled in, placeholders only where a real decision is missing. Rewritten in place and never sent — undo with one click or Ctrl+Z. Four editable presets (general / code / writing / translation), optional conversation context to resolve references, and a model that either follows the session or is pinned to a chosen provider and reasoning effort. Requests survive session switches and typing while a rewrite is in flight; a result that no longer matches the draft is kept for retry instead of overwriting it. Pure JS, no build, no bundled dependencies.

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.

Global cyber-terminal theme: a click-through full-screen Matrix code-rain overlay, phosphor-green UI styling, a sidebar one-click toggle, and adjustable speed, density, opacity and glow with three palettes.

ADHD-friendly focus soundscape docked under the DSH composer: five procedurally synthesised noise colours (white, pink, brown, rain, fan), a live-waveform orb, a 15-90 minute fade-out timer and a liquid-glass popover. No audio assets and no network requests.

内置 zk 的 DSH 知识库 / 日记插件：装好即用 —— 自动装 zk、建笔记本，给 agent 一组 zk_* 工具（搜索、读写、日记、双链），设置页里管路径、索引与自检。

Matrix-style binary (0/1) digital rain for the Harness interface: columns spawn only while a task is running, fall off screen when it stops, and leave a blank canvas; frosted-glass token layer with adjustable digit and panel opacity.

COROS Sport panel for DeepSeek Harness: sign in to COROS inside the panel, read the account, bound devices, recovery, fitness, recent workouts, daily health and the training schedule in one dashboard, and get a plan from the model with /coros-plan. The plan page writes a fixed four-week, 16-session plan to the account only after a two-step confirmation.

Inyector de inicio de Lingshu: ejecuta brain.py startup en cada nueva sesión de agente e inserta automáticamente persona, memoria y tareas pendientes. Requiere Python 3 y la habilidad Lingshu instalada en ~/.dsh/skills/lingshu; si falta cualquiera, no hace nada sin avisar. El repositorio principal también incluye un punto de entrada SKILL.md en el bundle.

Casco de seguridad para programar con IA: gradúa las escrituras (L0 solo lectura / L1 solo workspace / L2 total) y aísla las ediciones privilegiadas. Por debajo del nivel requerido, rechaza la escritura y devuelve un bloque listo para pegar. Cada ruta pasa por una comprobación raw-string de traversal y realpath, que detecta escapes mediante junctions.

Destila los chats diarios en una ficha de personaje actualizable y un módulo emocional entre sesiones que entrena la persona.

Tres skins retrofuturistas para DSH Web GUI: tren al anochecer, lluvia de neón y costa al ocaso; selector dentro de la página y elección guardada localmente.

Crea copias de seguridad offline en frío de un perfil DSH de Windows y datos Home seleccionados; permite inspeccionar ZIP por separado y restaurarlos con un asistente WPF independiente en un destino nuevo con un runtime compatible ya comprobado.

Añade reacciones de stickers y emojis al chat web/escritorio de DeepSeek Harness: selector en el compositor, stickers del agente que se muestran como imágenes mientras el transcript conserva la etiqueta del paquete, reacciones bajo la burbuja del usuario y efecto de lluvia de emojis.

Tema retro de fósforo CRT: pantallas Matrix verde sobre negro puro, verde ámbar 40K o ámbar TFEL, con texto grueso brillante, animación de arranque de lluvia de código y panel de control estilo BIOS.

Diez fondos animados a pantalla completa para el panel de conversación DSH —cielo estrellado, lluvia de código, circuitos, lucha con espada, gato, chica, caza, carreras, nieve y burbujas—; elige un tema aleatorio por turno y aplica un velo a la columna de texto para conservar la legibilidad.

Audita qué perdió realmente la compactación del contexto. Lee el log bruto de eventos y comprueba si sobreviven las restricciones permanentes del usuario (no hacer, hacer, solo en cierto ámbito), si el resumen inventa rutas/versiones/puertos/IDs, referencias “véase arriba” a texto eliminado, si el resumen ocupa casi lo que libera y si hay podas sin contabilizar. Según arXiv 2608.11242, una medición halló ~17% de supervivencia de restricciones entre compactadores. Incluye cuatro tools de agente, con barrido entre sesiones que ordena conversaciones por daño de compactación. Es determinista, sin LLM: un error señala una regla concreta.