107 results
并行 agent 开发环境：Codex/ClaudeCode/OpenCode/Pi 并排跑，各在独立 git worktree——一个 prompt 扇出 5 个 agent 比较合并胜者；移动伴侣监控、终端分屏、Design Mode（点击 UI 元素送 HTML/CSS/截图进 prompt）、GitHub/Linear 原生、SSH worktree、AI diff 标注。受 stablyai/orca（49k★ MIT）启发。
Tune the conversation area: font, width, line height, paragraph spacing, and Cursor-like sticky user prompts. 对话区界面设置：字号 / 字体 / 行距 / 段距 / 宽度 / 滚动钉住本轮用户消息。
An API testing sidebar panel (Getman) for dsh-better-sidebar: method/URL, params, headers, raw body, response viewer, shared history — with a host-side proxy that bypasses CORS.
Editable local and desktop dictation for DeepSeek Harness
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness
Tavily-backed search provider for the DeepSeek Harness web capability seam (ctx.web): keyless mode, full official search parameters, settings section, and credentials support
Separator-transparent, abbreviation-aware slash-menu matching for the DeepSeek Harness web surface: provides the slashMatcher service the ui-commands and ui-skill sources consult, so `dshp` matches `dsh-plugin-creator` and `dbc` matches `dsh-better-command`.
Fixes malformed tool-call arguments (nested {"arguments":{…}} wrappers, wrapper-key aliases, param-key aliases) at the llm/stream seam — repairs execution, persistence and history replay in one place. 修复模型产出的畸形工具参数。
DeepSeek Harness bundle: a bounded, de-confounded hyperparameter sweep ledger with a research-campaign playbook skill and paper-ready report tables
A generic provider-dispatcher proxy for DeepSeek Harness. Mounts child plugins under a private isolate realm, records every register* call, and fans one operation out to all recorded children with a configurable strategy (parallel merge / race / bail).
Pacote de idioma Português (Brasil) para a GUI Web do DeepSeek Harness
Ships a skill that tells the agent when to delegate work to subagents instead of doing it inline, how to fan several out in parallel, and how to check what they returned.
Permission matrix for DeepSeek Harness: 3 sandbox modes x 4 approval strategies = 9 selectable presets, with a global default, a separate LLM-robot default, four-tier risk policies, password-gated approval for high-risk operations, audit log and git checkpoint.
DSH web plugin: per-session API cost monitor. Renders as a dsh-better-sidebar tab, which must be installed separately — this package provides no UI of its own.
Appearance plugin for DeepSeek Harness: custom theme color (PS-style color wheel), background wallpaper with opacity/blur controls, and separate main/settings interface opacity.
dsh plugin that turns the iterate skill into an autonomous closed-loop harness with quality command center and experience bank (v3.3). Features: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus dry-run pure-review mode, qu
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
动态滚动窗口子代理任务池：一次调用跑完整批独立任务，内部滚动补位，后台运行不阻塞主对话
Local tool-call failsafe and DWGR-8 personal governance proxy gate for DSH: blocks high-risk shell patterns, credential leaks, and enforces declarative param-level boundaries with hash-linked JSONL audit logs and optional Gateway.
dsh plugin bundle porting the rpiv advisor subsystem: an on-demand zero-parameter advisor() tool that forwards the full session to a separately-configured reviewer model and returns a plan, correction, or stop signal.
Offline content-addressed proof for supplied DSH workflow duty separation
A crystal-structure visualization window for DeepSeek Harness (DSH): a 3D structure + Q-peak viewer and parameter panel, opened as a dsh-better-sidebar tab.
A generic provider-dispatcher proxy for DeepSeek Harness. Mounts child plugins under a private isolate realm, records every register* call, and fans one operation out to all recorded children with a configurable strategy (parallel merge / race / bail).
并行多角色代码评审小队：/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理（每人可单独指定模型与思考强度），汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped report.