[!NOTE]
As of 0.1.2 the skill catalog is served by this plugin (shadow catalog): catalog membership follows the conversation's injection selection exactly; a catalog change publishes one replacement frame instead of re-appending every step; container directories (DESCRIPTION.md only) are injectable and loadable. Verified by a three-round external test run (16/16 pass).
Skills, MCP & CLI manager for the dsh web GUI: browse/enable/import/delete skills across project and user roots; manage MCP servers with a REAL connection through @deepseek-ai/dsh-mcp-client (enabled servers connect and register their tools on ctx.tools;
A self-contained DSH web plugin: it adds one first-class settings page for the agent's three kinds of tool (skills / MCP servers / local CLI tools), plus a per-conversation skill injection layer; a guide tab explains how each of the three works and, at the bottom, hands everything back cleanly on uninstall.
Capability
Native dsh web
With this plugin
Skill browsing / toggling
Edit skill directories by hand
One-click linking / unlinking in the settings page; canonical copies go into the store; SKILL.md is never touched
Per-conversation skill sets
—
Session default + sidebar panel + skill_select; each conversation stores only its difference from the default
Skill catalog (AI view)
Static directory scan
Shadow catalog: follows the conversation selection exactly, with one smc-skill-index index row
MCP servers
Hand-edit mcp.json
Form / JSON creation + one-off connection test + activate / archive switches
Local CLIs
—
Auto-discovery of skill-wrapped CLIs, system CLI registry, probes for installed / version / subcommands / API key
Intrusiveness
—
Zero source changes: one npm package + one profile bundle patch line
Tab
Manages
Under the hood
Skills
Browse / enable / disable / delete / import skills; the session default decides what a new conversation starts with
User level: canonical copies in ~/.dsh/S-M-C/skills + directory junctions. Project level: frontmatter rewritten in place
Conversation skills panel | adjust this conversation's injection from the sidebar, under New Session
MCP servers | real connections, one activate / archive switch each
CLI tools | discover / probe / register local CLIs
Guide | how the three kinds work + uninstall escape hatch
💡 Features
Skills: grouped by project / user level and by source (.dsh/skills, .agents/skills, ~/.dsh/skills, ~/.agents/skills). User-level skills are adopted into the unified store~/.dsh/S-M-C/skills; project-level skills are managed in place through their frontmatter. Deletion takes two confirmations. Open a row for details (description / whenToUse / body); import by scanning any directory.
Action
What happens underneath
Enable / disable
Inject / remove a directory junction in the skill root (SKILL.md is never touched)
Delete
Only the store's own canonical copy is deleted (see below); directories outside the store are never touched
Every entry in a skill root is listed, including the ones that are not skills. A directory with no valid admission document (SKILL.md / DESCRIPTION.md) is flagged red as not a valid skill, told why, and cannot be enabled:
Situation
Shown as
Why it is not descended into
Directory holds no admission document
red not a valid skill
dsh reads exactly one level of a root, so a skill buried in <root>/<category>/<skill>/ does not exist as far as dsh is concerned; listing it would only suggest it is reachable
A registered record lost its source
⚠ source gone
see the next bullet
Traceable registry: "Refresh traceability" runs in two stages, because a useless record and a broken source call for different repairs.
Stage
What it decides
Outcome
1. Compare against the current skill list
A row with no matching entry is an orphan (typically a project-level skill registered while another project was open)
Dropped from the ledger outright — it can never be shown, linked or loaded, so keeping it would only bury the real problems
2. Trace the source
Only rows that do appear in the list: does the path still exist, and does it still hold a skill?
A failure is written onto the ledger row (missing, with a timestamp and reason) and shown as ⚠ source gone
A traced failure stays visibly broken across reloads instead of looking healthy again and offering a link that cannot work. Orphans that get cleaned up are reported alongside the verdicts.
Session default and per-conversation injection: the session default is what a brand-new conversation starts with; each conversation can also carry its own differences (one skill turned off, another added). The agent can flip its own skills in-conversation (written to that conversation's own file), and a small "conversation skills" panel right under New Session in the sidebar lets you adjust them by hand at any time — both switches list linked skills only. The window re-checks itself once a second and redraws only when something actually changed, so switching conversations or renaming one is followed within a second — which is why it has no refresh button. A pointerdown outside closes it; the pin keeps it open (the pin governs dismissal only, never dragging or resizing). See the next section.
MCP: two sub-tabs — "manage" gives each server one activate / archive switch (plus delete), "create" offers a form or raw JSON with a one-off connection test before saving. Activating connects for real and registers mcp__<server>__<tool>; archiving disconnects and moves the definition to S-M-C/mcp-archive.json, fully preserved. Live status: connecting / running / failed / stopped.
CLI: discovers skill-wrapped CLIs (scripts/run-cli.* / cli-state.*) and registers system CLIs (gh, git, … in S-M-C/cli.json). Each entry is probed for installed / version / needs-update / API-key state / subcommands, and the row shows where it came from and where it lives. The announce / hide switch only decides whether the CLI is written into the announcement handed to the agent — the plugin cannot start or stop a system-installed CLI, so entries default to hidden.
Guide: explains all three kinds and holds the pre-uninstall escape hatch. "Undo migration" moves stored skills back to their original paths; when the store is empty and the skill roots still hold skills, the same button turns into a green "Migrate" — reversible both ways. "Inject all MCP" moves every archived server back and reconnects. The page also lists the directories and config blocks to remove manually after uninstalling.
Interface: fully bilingual zh / en (220 keys each; English UI renders no Chinese); destructive actions take two confirmations and reset when you click elsewhere.
🧠 Two channels: linking vs injection
Enable (linking)
Injection (conversation selection)
Carrier
A directory junction at ~/.dsh/skills/<slug>
One row per conversation in the session table ~/.dsh/S-M-C/contexts.json
Scope
Global: every conversation, every workspace, sub-agents included
This conversation only
Maintained by
The "enable / disable" button on the skills tab
The session default, the sidebar panel, and the model's own skill_select
Seen by
dsh's own filesystem scan
This plugin's conversation injection
How a conversation stores its choice: the file keeps the difference from the default (overrides: { on, off }), and the effective set is default ∪ on \ off. Editing the default therefore reaches every conversation that never configured itself, while a skill you turned off in one conversation stays off.
🤖 Two tools for the agent
Tool
What it does
skill_select
Enable or disable one skill for this conversation; writes the conversation's own difference and applies immediately. Accepts every linked row — container directories too (their DESCRIPTION.md is the loadable body).
skill_query
Read-only view of the skills visible in this workspace (name / description / group / linked? / injected in this conversation?), computed at call time, with keyword and group filters.
The skill catalog itself is also served by this plugin (shadow catalog): the catalog the AI sees is generated here and carries one extra line, smc-skill-index — an index skill whose body is the complete list of this workspace's skills in the catalog's own shape. Skills that are not injected cannot be loaded ("not enabled in this conversation"); the /skill-name gesture is unaffected.
The guide tab can also switch on announce to agent, which describes the plugin and the current state of all three tool families in every agent's system prompt —
🧱 Architecture
Mounting and the dual-face structure — the plugin is one npm package plus one profile bundle patch; dsh source is untouched:
Requirements: DeepSeek Harness >= 0.1.2-alpha.2 (all @deepseek-ai/* packages release together); Node ^22.19.0 || >=24.
Status: fully tested end-to-end on 0.2.1-alpha.1 (every plugin route, both plugin halves and the settings UI) as well as 0.2.0-rc.1 and 0.1.7-rc.2 (every plugin route, the injection chain and the UI) and 0.1.6-alpha.1, 0.1.6-alpha.2, 0.1.5-rc.2; every API used has been checked for existence and signature since 0.1.2-alpha.2.
The desktop build is supported too — the plugin only uses dsh's host/client plugin interfaces and does not depend on the CLI form factor; verified working on the desktop build.
Install it as a normal package — never as a junction. A junction breaks resolution of dependencies (schemastery / react and friends) and makes the package name disagree with cordis.patch.yml; either one stops DSH from starting.
# From npm
dsh plugin --profile web add dsh-s-m-c-center
# or: npm install dsh-s-m-c-center
# From source (this repository / after cloning)
dsh plugin --profile web add <absolute path to this folder>
# Or from a packed tarball
dsh plugin --profile web add <path>/dsh-s-m-c-center-0.2.8.tgz
# Or the one-shot scripts
bash scripts/install.sh # macOS / Linux / Git Bash
powershell -ExecutionPolicy Bypass -File scripts/install.ps1 # Windows
After the first install, restart DSH and hard-refresh the browser (Cmd/Ctrl+Shift+R), then open "Settings → Web UI plugins → Tool manager".
Upgrading: for UI-only changes, overwrite the files and hard-refresh. Changes on the host side (routes / engines / tools) need one DSH process restart.
🔧 Configuration
The config is fully self-managed in the store as ~/.dsh/S-M-C/settings.json — nothing is written into dsh's settings.yaml any more (dsh 0.1.7 archives that file on upgrade, wiping every third-party block in it):
{
"enabled": true, // master switch (routes, MCP connections, CLI probing)
"announceToAgent": true // describe the plugin in every agent's system prompt
}
Runtime state:
Plugin settings: S-M-C/settings.json, living with the store; when upgrading from an older release the first mount carries the old settings.yaml block (or its archive) over in one shot.
Unified external store: ~/.dsh/S-M-C/ (Skills / MCP / CLI) — skills/ (canonical copies plus index.json manifest), skills-links.json (junction ledger), skills-registry.json (registered external skills, plus the missing traceability flag), mcp.json, mcp-archive.json, cli.json. The old locations are migrated in on first start; the whole store can move elsewhere with DSH_STORE_ROOT (the plugin rebuilds the junctions).
Conversation selections: one table for the whole machine at ~/.dsh/S-M-C/contexts.json — default is the session default and sessions.<sessionId> holds that conversation's difference from it (on / off). No workspace is involved: the key is the session id, so the settings page and the sidebar read the same document. An older version kept one file per workspace; those are folded in once, on the first mount with the table missing.
MCP: active definitions in S-M-C/mcp.json, archived ones in S-M-C/mcp-archive.json (credentials and headers are stored in plain text — keep both files 0600).
CLI registry: S-M-C/cli.json.
🔒 Permissions and dependency disclosure
The plugin runs with the DSH process's privileges and uses four kinds of capability — files, network, commands and credentials:
Capability
What it does
Scope and limits
Files
Reads and writes the store ~/.dsh/S-M-C/**; creates / removes directory junctions in the skill roots; reads and writes the session table ~/.dsh/S-M-C/contexts.json (plus any legacy <workspace>/.dsh/S-M-C/contexts/*.json, read once by the import); reads SKILL.md and skill-embedded scripts
Only the store and the four skill roots dsh scans; in-place skills only get their frontmatter rewritten; no other paths are read or written
Network
Connects to the MCP servers the user configured (stdio through a subprocess, streamable-http over HTTP)
Only the addresses typed into the manager page; the plugin has no built-in external service, no telemetry, and reports nothing anywhere
Commands
Probes local CLI tools: runs their --help / --version or the command declared in cli-state
Only commands inside the registry and visible on the manager page; nothing the user did not register is executed
Plain text under ~/.dsh/S-M-C/*.json, local only, never sent out; keep those files at 0600
External dependencies: the only runtime dependency is schemastery (settings validation); @deepseek-ai/* and react are peer dependencies provided by DSH; no native modules, and no postinstall / prepare lifecycle scripts.
Failure boundaries: a failed scan or route degrades to an empty list and a placeholder; a failed migration is recorded in failures and ignored, never blocking DSH startup; a failed MCP connection only changes the status line and touches no files; a failed conversation injection never vetoes the conversation and only explains itself in the log. None of them can stop DSH from starting.
Known risks:
Risk
Detail
Deletion is irreversible
Physical, and only the store's copy is ever deleted: a native skill must be migrated into the store first, a registered one is unregistered, and "delete junction" only unlinks and never touches its target
MCP credentials are plain text
Passwords / env are stored verbatim in mcp.json; file permissions are the user's to manage
Moving the store by hand breaks junctions
Enabling / disabling works through a directory junction; move it with DSH_STORE_ROOT instead and the plugin rebuilds them
Skills under a category directory cannot be loaded
dsh reads only one level of a root; the panel flags that directory as not a valid skill and says why, but does not list its children (they would not be reachable anyway). Loading them needs the skills moved up a level or adopted into the store
See docs/development.md: dual-half builds (tsdown rebuilds lib/index.js + lib/client.js), type checking (tsc --noEmit) and the test suite (vitest, 20 files / 287 cases).
Skills, MCP & CLI manager for the dsh web GUI: browse/enable/import/delete skills across project and user roots; manage MCP servers with a REAL connection through @deepseek-ai/dsh-mcp-client (enabled
Skills, MCP & CLI manager for the dsh web GUI: browse/enable/import/delete skills across project and user roots; manage MCP servers with a REAL connection through @deepseek-ai/dsh-mcp-client (enabled servers connect and register their tools on ctx.tools;
टूल
टूल
अभी टूल सूची नहीं है। रिमोट सर्वर को पहले हेल्थ चेक के बाद सूची मिलती है।
FAQ
सवाल
Dsh S M C Center कैसे इंस्टॉल करें?
इस पेज पर Cursor, Claude Desktop, Claude Code या VS Code के लिए stdio कॉन्फ़िग कॉपी करें। यह पब्लिशर का इंस्टॉल इस्तेमाल करता है, PlugMCP प्रॉक्सी नहीं।
इस रिकॉर्ड में कोई ज़रूरी एनवायरनमेंट वेरिएबल दर्ज नहीं है।
Dsh S M C Center कौन सा ट्रांसपोर्ट इस्तेमाल करता है?
Dsh S M C Center stdio पर लोकल चलता है।
Dsh S M C Center की पिछली जाँच कब हुई थी?
पिछली जाँच 2026-11-13 को हुई। Skills, MCP & CLI manager for the dsh web GUI: browse/enable/import/delete skills across project and user roots; manage MCP servers with a REAL connection through @deepseek-ai/dsh-mcp-client (enabled servers connect and register their tools on ctx.tools;