dsh-skill-cockpit
In a curated listMaintenance: Activehuanlin-labs/dsh-skill-cockpit
Skills cockpit: enable or disable each skill, mount skills into presets, keep the user-visible and model-visible lists separate, and read per-skill usage counts.
$ dsh plugin add dsh-skill-cockpitInstall
dsh has no central install command — add this plugin’s entry (documented in its README) to your profile or patch config, then restart.
How installs work10
stars
1
forks
JavaScript
Language
MIT
License
2026-10-14
Created
2026-11-15
Last push
README
dsh-skill-cockpit
v1.7.1 — published on npm. 19/19 self-test suites, all green ·
npm run verify:installpacks the tarball, installs it into an empty directory and boots that copy (13/13 checks;/pingreads back1.7.1). Published asdsh-skill-cockpit; npmlatest= 1.7.1. (The bare namedsh-skill-panelbelongs to a different author.)
Release:
v1.7.1is on npm, tagged in git, and has a GitHub Release. It delivers the D/E UI enhancements (density, sticky header, root grouping, body search, keyboard row actions, copy actions, path-aware search) and fixes the vault page's missingreserveListPathOfhelper. Details are at the top ofCHANGELOG.md.
Honest boundary. This is not a sandbox. It manages only the skill roots DSH itself exposes and writes only inside
~/.dsh/skillsand~/.agents/skills; it cannot stop other processes, manual edits, or skills invoked outside DSH. CLI / doctor /verify:installare covered by automated tests on this Windows machine. The running host was restarted on 2026-11-04 and/pingreports 1.7.1. On 1.7.1 the live page renders 76/76 skills with a clean 76-item health check; this round exercised List / Groups / Presets / Usage / Trash / Vault / Preferences / Checkup, plus one-click repair against a temporary malformed skill (name and short description repaired,.bakwritten, fixture removed afterwards).Back up allproduced 76 skills / 2242 files / 79,703,006 bytes on disk. A button-by-button exhaustive visual pass has not been done, so unlisted controls remain 未验证 (not yet verified) and rest on their unit/route evidence. CI runs the full suites andverify:installon ubuntu, macOS 15 and Windows × Node 20/22/24; run 41076632643 is green on all 27 jobs. A skill cockpit for DSH (DeepSeek Harness): one page in the app-level navigation that shows every skill the machine actually exposes, says why a skill is missing, and lets you toggle a single skill without editing anything but its entry-file name.
npm i dsh-skill-cockpit # or install it as a DSH bundle via the plugin manager
Restart DSH after installing; the page sits in the left nav between Plugins and Schedule.
Self-check: dsh-skill-cockpit-doctor
npx dsh-skill-cockpit-doctor # why is the page missing? state dir / skill roots / assembly / gloss
npx dsh-skill-cockpit-doctor --json # machine-readable
npx dsh-skill-cockpit-doctor --home <dir> --fix # redirected home for tests/CI; fixes only safe things
npx dsh-skill-cockpit-doctor --dry-run # say what --fix would do, write nothing
npx dsh-skill-cockpit-doctor --report out.json # write the same JSON to a file (read-only)
Exit codes: 0 ready · 1 something to fix · 2 environment problem.
Platform matrix (who is verified and who is not): docs/platforms.md.
Pre-release self-check (what is ticked, with evidence, and what is still open): docs/self-check.md.
Something is broken (check-by-check table + three common symptoms): docs/troubleshooting.md.
What is actually done vs. still missing (each row with evidence): docs/status-ledger.md.
Honest boundaries (read this before trusting anything below)
- Verified on Windows desktop DSH only. Every claim here comes from a real DSH desktop install on
Windows 11. CI runs syntax, the full suites and
verify:installon macOS/Linux; nobody has run a real DSH session on them. - Full test suites run in CI on ubuntu + macOS + windows. Passing CI is automated evidence only; it does not replace a real DSH session on those platforms. Nothing here says "all platforms support this".
- Translation uses free public endpoints (MyMemory first, Google as fallback). They rate-limit and change without notice; a bulk translation may return fewer items than asked. Nothing is sent anywhere except those two services, and only when you press 翻译.
- It edits skill files when you ask it to. 一键修 rewrites the frontmatter of the skill you clicked
(always with a
.bak-<timestamp>backup first) and never invents content: it only fixes the entry name, fills a missing description from the skill's own body text, or quotes a YAML-breaking colon. If it cannot fix something it now says so instead of staying silent. - It is not a sandbox. It reads the six skill roots DSH itself resolves (
project-dsh,project-agents,custom,user-dsh,user-agents,bundled) and writes only inside~/.dsh/skillsand~/.agents/skills. Other harnesses' directories are never touched. - Usage counts are a lower bound. They come from parsing session logs for
tool-callblocks namedskill; skills invoked before that log shape existed, or from a different entry point, read as 0.
What it does
More in Plugin Tooling
dsh-context
by bowenliang123
Context dashboard tab + /context command showing context-window composition, per-turn history, compaction/prune events, per-message token costs
deepseek-harness-control-center
by feibi-mochi
Web control center for DSH: account monitoring, usage accounting, completion alerts, official recharge link, flexible layout, agent-assisted session controls (capability-gated)
dsh-context-doctor
by zhenyu98
DSH 上下文注入审计:统计 AGENTS.md 指令链/技能目录/工具 schema/MCP 的 token 成本,检测跨文件重复与 rank shadow 冲突;Web UI 圆环面板 + context_audit 工具
dsh-balance-plugin
by yxxbc
DeepSeek 余额监控与用量统计:CNY/USD 双余额池多账户查询、低余额告警、官方充值入口、Miyu 风格用量仪表盘、三方插件管理、query_api_quota 模型工具
