Plugins

Shell-style prompt history in the DeepSeek Harness composer: ArrowUp walks back through the messages you already sent, ArrowDown walks forward and restores your draft.

The judgment layer for DeepSeek Harness plugins: attribute why a plugin silently disappeared, judge a candidate against your exact environment, and keep a capability ledger. Offline, read-only, evidence-first.

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Compares installed plugins against a downloaded DSH update and reports which interfaces they use that the update no longer exposes. Runs before you install, with a dry-run diagnose command for when it declines to act. Windows only, on the DSH desktop app, with Node.js 18+.

GitLab panel in the DSH right sidebar: commit graph, branches, changes, merge requests (inline diffs, review submission, pipelines), issues, and agent tools with an approval queue for triage and batch actions. GitLab data needs a personal access token or a logged-in `glab`; local git data works without either.

Config-driven lifecycle hooks for DSH: block or observe tool calls, and react to completed turns, messages, and title changes with shell commands.

Plot decision gate for novel writing: seven beat_* tools register each node that changes the story into a decision point with 2-4 structured options; author picks are written to a book-level ledger (canon + obligations) that later chapters inherit, beat_gate returns pass:false until every decision is made, beat_compile turns the picks into a chapter contract, and beat_verify checks the prose for missing changes, forbidden states and overdue obligations. Off by default; /beat on or the composer button enables it.

HarmonyOS delivery orchestration for DSH: freezes a four-dimension acceptance pack whose measurable criteria carry machine-checkable assertions, runs an adversarial pre-review before dispatch, hands the work to DevEco Code in Goal mode, then audits the delivery with independently gathered evidence (screenshots, UI tree, logs, hashed evidence bundle), recomputing assertion verdicts against measured values and filing rework orders; includes a cited rule catalog, a user-confirmation state and a gate calibration ledger.

Group skills into named sets, toggle any combination, drag to reorder, and preview each group catalog token cost.

Whole-PDF paper translation for DSH on top of a BabelDOC installation you provide (Python CLI, with an OpenAI-compatible API key in its config.toml): bilingual dual-page output, a token cost estimate before running, a per-domain glossary reused across papers, and the server-side thinking overhead disabled for translation.

An AI reading buddy: it sits next to you while you read, and only knows the pages you have already reached — so it cannot spoil the rest, and it never summarizes the whole book for you. Highlight a sentence and ask about it, or just ask about what you finished; it usually restates what you seem to mean and asks one concrete question back. What you work out can be saved as a takeaway and later becomes a review card that jumps back to the sentence. EPUB, MOBI, FB2, TXT, Markdown, HTML, CBZ.

Compiles a repository into a source-grounded code map: structured pages where every claim carries a verifiable path:line citation, an interactive dependency graph, knowledge cards, four model tools and the /codemap command. Deterministic, no model calls, zero dependencies.

GitHub Trending radar inside the Harness Web UI: fetches the daily, weekly or monthly board (optionally filtered by a language), analyzes each repository into description, star gain, tech stack, highlights and risks, renders the result as a filterable card panel with paging, and registers the github_trending tool plus the /github-trending command.

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Drive the NI Multisim 14.3 install on a Windows machine through nine msim_* tools: open and save .ms14 designs, read and edit component values and circuit parameters, run DC operating point, AC sweep, single-frequency AC and transient analyses, export schematics, BOM and netlists. A Win32 channel drives the visible window to run the Analyses dialog and capture Multisim's own schematic view and waveform plot; a SPICE command-file engine handles designs that expose no probes; an offline reader unpacks the .ms14 container without starting Multisim at all. Requires Windows, NI Multisim 14.3, and a 32-bit Python 3.11-3.13 with pywin32.

Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.

Indexes public AI-company job boards (Greenhouse, Ashby, Lever, Workable, SmartRecruiters), scores postings for AI relevance, extracts the requirements from each job description, and produces a scheduled daily Markdown digest.

Crée une vidéo explicative narrée à partir d’un script. Par défaut, diapositives en cartes de texte (rapides et précises pour les tutoriels) ou séquences générées par IA pour chaque segment (AGNES_API_KEY requis). Comprend 14 voix neuronales chinoises en ligne et 3 voix hors ligne Windows, avec un pack d’échantillons à générer en une commande pour les comparer. ffmpeg requis. Pour les voix en ligne, copier le skill fourni video-remix vers `<workspace>/.dsh/skills/video-remix` et y lancer npm install.

Compile LaTeX avec le TeX Live installé sur la machine. L’outil `latex` compose une formule en SVG, PNG ou PDF, et un document entier en PDF (le chinois passe à xelatex avec ctexart), enregistre le fichier dans l’espace de travail et renvoie une référence Markdown. Une section du prompt système demande au modèle d’écrire `$...$` et `$$...$$` plutôt que des blocs de code. Si TeX Live est absent, une bannière au-dessus du composeur propose l’installation en un clic de BasicTeX ou TinyTeX.

Mémoire persistante compatible avec Claude Code : l’hôte injecte l’index MEMORY.md au début de la session et le modèle gère les fichiers avec des outils ordinaires de lecture, écriture et modification. Une page de réglages répertorie les souvenirs enregistrés. Même format disque que Claude Code ; le mode claude partage exactement le même répertoire mémoire.

Un interphone entre fenêtres DSH déjà ouvertes. Pas d’équipes ni de nouvelles sessions, seulement des messages pair à pair avec une limite de sauts.

Précalcule en arrière-plan le résumé de compactage et valide le résultat conservé lorsque le compactage sous pression se déclenche, évitant un aller-retour du modèle au premier plan. S’enregistre comme moteur de compactage de session, fixe la portion résumée pour que l’empreinte de la charge corresponde lors de la validation, élague les résultats d’outils avant celle-ci et revient au parcours standard au premier plan en cas de dérive de charge ou de dépassement du contexte.

Exporte en lecture seule une conversation de chat.deepseek.com vers une nouvelle session DSH : le paquet de transfert conserve mot pour mot les tours choisis et réduit les précédents à une ligne chacun, puis préremplit le composeur sans envoyer. Windows uniquement selon la publication ; Edge ou Chrome et une première connexion à chat.deepseek.com sont requis.