Plugins

GitHub issue service for DSH: turns a telemetry failure analysis into a uniform issue report, builds a pre-filled new-issue URL that is shortened when it would exceed a configured length budget, and rewrites a plain description into a structured issue with the deployment's model.

Chinese summaries for the dsh-skill-mcp-panel skill cards: each expanded card gets a short Chinese overview, a category tag and a few bullet points, while the English description the panel already renders is folded behind a "原文" toggle. Skills missing from the bundled map are translated on demand by the host with your current default model and cached on disk, keyed by a hash of the original text, so a new skill needs no manual entry. Skills whose own description is already Chinese are skipped.

Eyes for text-only models: mounts the bundled stdio MCP server as mcp__opencode_eyes__describe_image, which sends an image file to StepFun step-3.7-flash and returns a detailed description.

DSH 循环护栏：① assistant-stream 字符重复检测（可 abort）；①b 低多样性高重复（末窗 + 滑窗两支，抓「带噪声的交替空转」与「正常推理里夹一段空转」——① 线的精确匹配结构上抓不到它们）；①c ① 线命中时注入「停止」类词 + 预注册观测（注入是温和动作，先于掐断）；② 行动层「无进展」停滞检测；②b 同参工具调用连击（按**动作参数**判定，忽略 description 之类自注）；③ 反复卡住达阈值 ⇒ agent.cancel() 真切断；⑤ 零正文 turn（只有思考

中文化 DSH 已知的系统提示词、MCP 指导与运行时提醒；按可见工具裁剪规则，保留工具 description、参数 schema 与动态值。纯 Host 插件，无 UI。

--- description: "面向 DeepSeek Harness 的可安装单包 FreeCodeGo 组合：安装渠道、发布打标，以及随包交付的 Agent Teams 组合。" kind: "package-bundle" ---

Hard break on repeated tool calls: a synchronous ctx.tools.guard gate that counts semantic fingerprints (net/site/sink/cmd/exact) over a per-agent sliding window, ignoring decoy arguments such as description and timeoutMs.

Browse the awesome-dsh-plugin catalog from a page in DSH Settings: filter by category or by installed state, search by name or description, sort by stars, downloads, name or date added, and install a plugin into the current profile. Two further tabs list what is already installed and which of those have a newer version in the catalog, with an update button on each row. The update view reports installed plugins whose update status cannot be determined, and overlapping install requests are refused. The catalog is cached locally for an hour with a mirror, a CDN and the npm registry as fallbacks when the official source is unreachable.

Browse the skill library from a floating-ball panel: you choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin), skills are grouped into first and second level categories, descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and keeps a .bak-toggle backup, and disabled cards grey out until restored. A failure ledger separates automatic from manual entries and records skill successes and failures by listening to tools/result events, reusing an existing ledger file if one is found in the library and otherwise creating one under skill-master/references. The DSH settings page gains a floating-ball section that shows or hides the three balls and offers one-click restore of a ball dragged off-screen.

One-shot DSH skill (SKILL.md) generator: capture intent, draft, validate, package and distribute skills from inside a DeepSeek Harness session (skill_new / skill_validate / skill_package / skill_improve_description).

Analyze the current branch diff and generate a Conventional Commits PR title, motivation/scheme/testing/risk description and a self-review checklist, write PR_DESCRIPTION.md, optionally open the PR via gh.

Skin author workbench: official token browser (169 --dsw-* variables with Chinese descriptions and module-usage tags), live try-on, durable skin save, theme freeze, seven spectrum presets with SVG backdrops and custom backdrop upload.

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

Long-form drafts with the structure already decided. Blog posts, press releases, product and job descriptions, FAQs, email templates, READMEs, changelogs, meeting minutes, weekly reports, cover letters, academic polish, name ideas.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

DSH 插件目录速查 (dsh-plugin catalog): periodically fetches repositories tagged topic:dsh-plugin from GitHub, categorizes them, stores Chinese descriptions locally, and exposes agent tools (plugin_query / plugin_catalog_update / plugin_categories) plus a web GU

Plugin recommender for DSH: search and rank plugins from an embedded 1100+ entry marketplace catalog by need description, category and tags, with match reasons and a live catalog refresh from the awesome-dsh-plugin README.

Document workshop skill pack: four pure-prompt Agent Skills that turn a codebase into READMEs, PR descriptions, changelogs and code reviews, installed into dsh via a dsh.bundle plugin row.

Visão para LLMs somente de texto: descrição de imagens / OCR / VQA via APIs de visão gratuitas do Gemini e GLM