harness-ai-kit 资产操作手册(dsh 随包精简版):list/search/info/install/doctor 团队 Skill/CLI/Plugin/Loop 资产,及 doctor dsh 环境检查。当用户在 dsh 会话中询问团队资产、安装技能、检查 dsh 环境时使用。
Scanned 9/1/2026
Install to Claude Code
npx -y skills add seed-forge/harness-ai-kit --skill harness-ai-kit-ops --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Harness Ai Kit Ops?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/seed-forge-harness-ai-kit-ops)More formats (shields.io, HTML) on the badges page.
---
name: harness-ai-kit-ops
description: 'harness-ai-kit 资产操作手册(dsh 随包精简版):list/search/info/install/doctor 团队 Skill/CLI/Plugin/Loop 资产,及 doctor dsh 环境检查。当用户在 dsh 会话中询问团队资产、安装技能、检查 dsh 环境时使用。'
---
# harness-ai-kit 操作手册(dsh 随包版)
本技能随 `harness-ai-kit-plugin` bundle 注册。完整版见团队仓库
`skills/harness-ai-kit-ops/`(可 `install skill harness-ai-kit-ops --scope global` 获取)。
## 核心命令
- `harness-ai-kit list assets --json`:列全部资产(或 `list clis` / `list skills`)
- `harness-ai-kit show <kind> <id> --json`:看单个资产元数据
- `harness-ai-kit install skill <id> --runtime dsh --scope project`:装技能到 `.agents/skills`
(dsh rank 200 原生扫描,无需额外配置)
- `harness-ai-kit install plugin <id> --profile <p>`:装 dsh 插件(委托 `dsh plugin add`)
- `harness-ai-kit doctor dsh`:dsh/pnpm 版本、DSH_HOME、profile 检查(基线 dsh 0.1.0-rc.6、pnpm >=10)
## dsh 会话内使用
直接调用 `harness-ai-kit` 工具:
- `harness-ai-kit(action: list, assetType: skill)`:列 registry 技能目录
- `harness-ai-kit(action: search, query: "kafka")`:关键词搜索
- `harness-ai-kit(action: info, assetType: cli, assetId: <id>)`:看 CLI 详情
- `harness-ai-kit(action: install, assetType: skill, assetId: <id>, runtime: dsh)`:安装技能
## 约束
- 安装类操作会落入 dsh 权限审批流(workspace-write),这是特性而非缺陷。
- CLI 不在 PATH 时工具自动回退直读 registry index(只读动作可用)。
- 技能正文按需加载:本手册只占一行元数据,调用时才读取。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.