DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Skill Manage — DeepSeek Harness 插件(DSH Plugin)
← Plugins
S

dsh-skill-manage

Skill Manage

DSH skill_manage:代理管理的程序性记忆。在 ~/.dsh/skills(用户范围)或 <projectRoot>/.dsh/skills(项目范围)中创建/修补/编辑/禁用/删除技能,并提供验证、删除保护(代理创建标记、固定标记、路径限制)、通过 disable-model-invocation 禁用/启用,以及英文触发规则系统提示部分。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-skill-manage@0.2.2
README兼容性版本

说明

DSH skill_manage:代理管理的程序性记忆。在 ~/.dsh/skills(用户范围)或 <projectRoot>/.dsh/skills(项目范围)中创建/修补/编辑/禁用/启用/删除技能,并提供验证、删除保护(代理创建标记、固定标记、路径限制)、通过 disable-model-invocation 禁用/启用,以及英文触发规则系统提示部分。基于 skill-filesystem 的热重载监视器构建。

兼容性与来源证明

Skill Manage 以 dsh-skill-manage 发布,当前版本为 0.2.2。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
npm
Registry 更新时间
2026/8/22

版本

0.2.2stable
2026/8/22
0.2.0stable
2026/8/21

相关插件

正在加载相关插件…

最新版
0.2.2
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
37 kB
文件数
5
Surface
any
许可证
MIT
发布源
npm
GitHub
★ 3
周下载
0
最近提交
2026/8/22
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录

README

dsh-skill-manage

A DSH (DeepSeek Harness) plugin that gives the agent procedural memory: a skill_manage tool for authoring its own skills — create, patch, disable, delete — with layered delete guards. Built on skill-filesystem's hot-reload watcher, so a skill created mid-session is usable in the same session, no restart.

Pair with dsh-auto-memory for declarative memory: that one remembers facts (logs, notes, preferences), this one remembers how to do things (workflows, pitfalls, procedures).

What it adds

skill_manage tool — actions: create / patch / edit / delete / disable / enable / pin / unpin / write_file / remove_file / list

  • Two scopes — scope: 'user' (default, ~/.dsh/skills, all workspaces) or scope: 'project' (<projectRoot>/.dsh/skills, this workspace only). The project root is resolved exactly like the harness's own skill lookup: walk up from the session cwd to the nearest .git, falling back to the cwd itself. list shows both scopes in one table.
  • Both on-disk layouts — directory skills (<root>/<name>/SKILL.md, what create writes) and single-file skills (<root>/<name>.md), matching the two layouts the skill-filesystem watcher actually loads. list shows a layout flag; single-file skills refuse supporting-file actions.
  • Disable/enable (reversible) — toggles disable-model-invocation in SKILL.md frontmatter, the same key the harness's skill catalog filters on (isModelInvocable). Disabling hides a skill from the model's catalog without touching its content; enabling restores it. Prefer disable over delete for seasonal or off-context skills.
  • Pin/unpin (reversible) — toggles the same pinned frontmatter flag the delete guard reads. A pinned skill cannot be deleted by skill_manage (patch/edit still allowed); pin skills that must survive cleanups.
  • Trigger discipline (English, static system-prompt section, cache-stable): create a skill when a complex task succeeded (5+ tool calls), errors were overcome, a user-corrected approach proved itself, or the user asks to remember a procedure; patch immediately when a skill hits uncovered pitfalls.
  • Delete guards:
    • only skills carrying the created_by: agent frontmatter marker are deletable — marketplace/user skills are refused
    • pinned: true frontmatter blocks delete (patch/edit still allowed)
    • path confinement to the resolved skills root; symlinked skill directories refused
    • name-drift guard: patch/edit cannot silently rename a skill
  • Validation: name regex + length, frontmatter requires name + description, description ≤1024 chars, SKILL.md ≤100k chars, supporting files ≤1 MiB, supporting paths confined to references/ templates/ scripts/ assets/
  • Atomic writes (temp + rename) so the watcher never sees a half-written SKILL.md
  • CRLF-safe frontmatter parsing

Install

Option A — via dsh plugin (recommended; handles both steps below automatically):

dsh plugin --profile web add dsh-skill-manage

Option B — manual npm install, in your DSH profile dir (e.g. ~/.dsh/profiles/web):

# 1. add the dependency
npm install dsh-skill-manage        # or: pnpm add dsh-skill-manage

# 2. register the bundle in package.json → dsh.profile.bundles:
#    "dsh": { "profile": { "bundles": [ ..., "dsh-skill-manage" ] } }

# 3. restart dsh web

The plugin needs no configuration. Log line [dsh-skill-manage] ready confirms it loaded.

From source (local link) — for development:

# in your DSH profile dir (e.g. ~/.dsh/profiles/web)
# 1. package.json dependencies:
#    "dsh-skill-manage": "link:/abs/path/to/dsh-skill-manage"
# 2. dsh.profile.bundles: append "dsh-skill-manage"
pnpm install
# 3. restart dsh web

Develop & test

node test.mjs      # guard-level smoke tests (73 cases, sandboxed DSH_HOME)
node loadtest.mjs  # host-shape contract + real round-trip (set DSH_HOME to sandbox it)

CI runs both on every push/PR (.github/workflows/ci.yml).

v0 known limitations

  • Nested category dirs (<root>/<category>/<name>/SKILL.md) are not listed or operable — the harness watcher does not load them either (it loads only <root>/<name>/SKILL.md and <root>/<name>.md)
  • No YAML flow collections in frontmatter (tags: [a, b] stays a raw string)
  • Project scope assumes one root per session (the session cwd's git root)

License

MIT

相关插件

继续浏览 memory-context 分类下经过校验的插件。

Memsearch Dsh@zilliz/memsearch-dsh适用于 DeepSeek Harness 的 MemSearch 插件:在多个代理之间共享 Markdown 记忆,支持捕获、步骤前上下文注入、记忆召回技能和技能候选审核面板。Reme@agentscope-ai/reme面向 TypeScript 代理的 ReMe 客户端和记忆集成Stratagate Dshstratagate-dsh最近的对话依然鲜活。较早的对话会逐渐淡化为摘要,而不是被遗忘。StrataGate 为 DeepSeek Harness 提供六层、随时间衰减的记忆,同时将持久的事件和关系沉淀为知识图谱。将你在其他 AI 中的记忆带来Meow Memorymeow-memoryDeepSeek Harness 的跨会话项目记忆:七层 SQLite 记忆、首轮快照注入、每条消息的关键词命中、memory_remember/search/project 工具、带 reflection-fold UI 的自动反思,以及由空闲触发的梦境整合