dsh-skill-hub

中文版 | English

In-GUI skill hub for DeepSeek Harness — manage the full ctx.skills catalog from the Web GUI. Beyond browsing, toggling and market installs, it puts the weight on two things other managers don't do: audit before install (hidden characters, remote-execution pipes, credential paths, size caps — a blocking finding is refused before it lands) and budget after install (the name + description characters of the first progressive-disclosure layer, so you learn at 8000 that a skill would install but never trigger).

Host runs in the dsh process via official SDKs only; browser renders through official slots. No dsh source changes.

Quick start

dsh plugin --profile web add dsh-skill-hub
# restart dsh web → Settings → 技能 → Market → scan → import

Requires Node ^22.19 || >=24 + dsh web >=0.1.7-alpha.1 <0.3. dsh 0.2.2 and later require Node >=24.9.

Two surfaces — the hub panel lives at Settings → 技能, and this plugin's own configuration card sits on the plugin's page in the Plugins manager (sidebar → 插件 → dsh-skill-hub). The card is registered by the plugin itself into the plugins.bundle.config slot — dsh has no auto-generated config page — and covers the master switch, announce-to-agent, dot colors, usage display and the stats window/interval.

Features

Settings → 技能 — 3 tabs: Sources (skills, flat/grouped + project tree), Scenes (custom tag groups), Market (install + update).

• Browse — every root of the ctx.skills registry: project / user / bundled + third-party providers. Search across name, description, displayName; filter by source and invocation (model / user); sort by name, added time, or usage. Same-name skills from different sources get a duplicate badge instead of silently hiding.
• Content audit — enabled skills' bodies (SKILL.md) are checked too: raw ESC control characters, Unicode tag characters, and bidirectional controls (these three make "reviewed" not equal "seen" — a market import carrying them is refused outright), zero-width characters, curl … | sh remote execution, SSH/cloud-credential/keychain paths, over-long descriptions, and the 2 MiB per-file / 10 MiB per-skill / 500-file limits. Pure local static matching: no model call, no network. A market import scans the whole bundle (including scripts/); the standing check only reads SKILL.md — it runs on every 5-second poll, and walking every directory would slow the panel down.
• Announcement budget — the name + description total that the first progressive-disclosure layer injects comes back with the catalog, so the panel can show characters and an estimated token count; past 8000 characters it turns red (clients truncate the tail there, which shows up as "installed but never triggers").
• Toggle — per-skill switches and per-group tri-state switches with a conflict dialog (close all / keep on). Disabling renames the discovery file (never deletes); disabled skills stay inspectable and re-enableable from their detail page. Only ~/.dsh/skills & ~/.agents/skills are writable; everything else is read-only.
• Organize — scenes (tags) plus auto-aggregated source collections, all drag-reorderable and persisted in ~/.dsh/dsh-skill-hub.json. Edit mode reveals delete/reorder without cluttering the read view.
• Diagnose & fix — files the provider skips (missing frontmatter, bad YAML, name mismatch, short description) show up with reasons; auto-fixable ones (e.g. unquoted : in descriptions) get a one-click Fix button.
• Scaffold — new-skill wizard writing to ~/.dsh/skills or ~/.agents/skills (SKILL.md template below).
• Market — built-in curated repos plus custom owner/repo sources. Any top-level directory containing SKILL.md scans as a root (no allowlist), and a SKILL.md at the repo root itself scans as a single skill named after the repo (minus repo tooling such as .github/). Async import with byte-level progress and cancel. Each source pins a version — click the ref badge to switch between releases, branches, or a custom ref. Every import passes the content audit first: a skill with a blocking finding is refused as a whole and its temp directory is removed (nothing left on disk).
• skills.sh search — beyond the built-in catalog, search the skills.sh index by skill name; results show the hosting repo and its install count, with two actions per row: Install pulls that one skill straight in (one step, but it does not track upstream — the index gives a skill directory name, never its path inside the repo, so no source record can be registered), while Add source registers the repo and scans it, after which update tracking, version pinning and trash behave exactly like a hand-added source. Both paths pass the same content audit. Requests are proxied server-side — the upstream sends no CORS headers, and a search should not hand the user's egress IP to a third party — and both source and package paths are validated against strict shapes before use.
• Track updates — imported skills record a repo + commit snapshot. Check all / update-all, per-source badges (installed / updatable / deleted upstream / new release). Sync overwrites local edits (with confirm); upstream deletions move into a restorable trash that keeps source and scene membership.
• Local-edit detection — a content hash of the whole skill (path + size + body) is sampled right after the bytes land and compared on every check: skills that no longer match get an "edited locally" badge, and the sync dialog marks exactly which ones the overwrite will discard. Records without a hash are treated as unknown, never as edited.
• Import from another agent — read-only scan of the skill folders of Claude Code / Codex / Cursor / Gemini CLI / Copilot / OpenCode / Goose, at two levels: user-level (~/.claude/skills and friends) into ~/.dsh/skills, and project-level (<projectRoot>/.claude/skills and friends, project roots derived from registered workspaces) into that project's .dsh/skills. The originals are untouched; flat skills land as directory bundles; the same content audit and size caps apply.
• Project skill toggles — project skills can be switched off via an invocation override: the hub registers its provider once more into every live agent's skill layer (nearer than the preset layer) and publishes a same-name entry that outranks the host's native one, flipping that skill's modelInvocable to false. The model stops auto-invoking it, "/name" keeps working, and not a single byte of the project changes (zero git pollution). The state lives in the hub's sidecar; flipping the switch again restores it.
• Import from ZIP — pick a .zip: every directory containing a SKILL.md becomes one skill, so a single-skill archive and a collection both work, each passing the content audit independently. Before anything is unpacked the reader rejects path traversal, symlinks, encrypted and ZIP64 archives, and decompression bombs; writes go through a temp directory plus an atomic rename, so a failure leaves nothing behind. A name that is already enabled is skipped — only a disabled placeholder or an empty shell steps aside into the restorable trash.
• Stats — per-skill call counts + last-used times from session logs (incremental cache), group summaries; window and scan interval live-configurable from the settings card.
• Settings card — registered on the plugin's own page in the Plugins manager (sidebar → 插件 → dsh-skill-hub; collapsed until you expand the title): master switch, announce-to-agent, invocation dot colors, usage display toggles, stats window/interval.

Choosing between managers

Several skill managers exist in this ecosystem and they cover more ground than this one: @michengai/dsh-skills-manager adopts 20+ agent folders, aggregates both the ClawHub and skills.sh markets, and supports ZIP import and self-update; dsh-skill-importer / dsh-find-skill focus on import alone.

This plugin's trade-off is to go deep on what happens after something is installed:

Two capabilities nothing else here has:

Scaffold format (SKILL.md):

---
name: my-skill
description: One line when the agent should use this skill.
---
# my-skill
Body...

How it works

GitHub repo ──scan/import──▶ ~/.dsh/skills
     ▲                          │
     └─check/sync/delete── ctx.skills ◀─ provider
                                │ snapshot/get
                                ▼
                    /api/skill-hub/* ──▶ Panel (Settings → 技能)

Host uses only ctx.skills.snapshot/get, ctx.webServer.register, ctx.systemPrompt.section. Routes sit behind dsh's own /api trust fence (loopback / the listener's bind address / --trusted-host), JSON; write routes (POST) additionally require an x-dsh-skill-hub: 1 header — a cross-site page cannot forge a custom header, and a same-origin request skips the CORS preflight so it costs no extra round trip. The provider registers in the global skill layer and once more into every live agent's skill layer (nearer than the preset layer), so an invocation override can outrank the host's native entries.

HTTP API

Development

npm run typecheck  # tsc --noEmit
npm test           # 413 tests, 23 suites
npm run build      # tsc + tsdown → lib/index.js + lib/client.js

Don't run two dsh web on the same $DSH_HOME + cwd — no session-log lock (seq gap corruption). Use separate DSH_HOME.

Troubleshooting

• duplicate loader entry id: skill-hub — remove the duplicate install (keep one dsh plugin add method).
• Skill missing — check the diagnostics section (frontmatter / name mismatch / short description / two discovery forms claiming the same name: a <name>/SKILL.md bundle and a <name>.md file can coexist on disk, and the registry keeps only one of them).
• Empty source group — its skills were deleted, or their disabled records were lost (sidecar restored/hand-edited). Startup reconciles .disabled files on disk and prunes records whose file is gone (a record left behind by a hand-deleted directory used to be un-actionable: enable, create and delete all failed). Source groups with no visible member are no longer rendered.
• A skill cannot be created / stays "disabled" — the disabled record pointed at a file that no longer exists. At startup (and on the next enable attempt) the record is repointed at the surviving .disabled file, or dropped so the name is free again.
• Dots missing in / menu — dsh internals changed; catalog still works.
• Settings card missing — open the plugin in the Plugins manager (sidebar → 插件 → dsh-skill-hub) and expand the 「技能中枢」 card at the top of the page (collapsed by default). On dsh older than 0.1.7-alpha.1 this plugin does not load at all (the settings API it targets does not exist there).

Community

Issues · Discussions · Showcase · Market PR · Discord

License

MIT — LICENSE.