NL2SQL/Text2SQL 知识基座(供 extends 继承)。聚合两阶段架构、查询类型分类、字段/术语映射、条件与 metric 抽取、多表 JOIN 推理、SQL 正确性与评测的深度知识与踩坑。通常被 devlab-nl2sql-engineering 继承,不直接面向用户触发。
Scanned 9/4/2026
Install to Claude Code
npx -y skills add seed-forge/harness-ai-kit --skill public-nl2sql-expert-base --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Public Nl2sql Expert Base?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/seed-forge-public-nl2sql-expert-base)More formats (shields.io, HTML) on the badges page.
---
name: public-nl2sql-expert-base
description: NL2SQL/Text2SQL 知识基座(供 extends 继承)。聚合两阶段架构、查询类型分类、字段/术语映射、条件与 metric 抽取、多表 JOIN 推理、SQL 正确性与评测的深度知识与踩坑。通常被 devlab-nl2sql-engineering 继承,不直接面向用户触发。
---
# public-nl2sql-expert-base
> **知识基座**:本技能不做流程编排,只提供 NL2SQL 领域的深度知识与判据,供 `devlab-nl2sql-engineering` 等技能通过 extends 继承。
## 覆盖主题
| 主题 | reference |
|------|-----------|
| 架构与管道 | `references/REFERENCE-ARCHITECTURE.md` — NL2DSL2SQL 两阶段、DSL 中间表示、查询类型分类、strategy-per-type |
| 理解与抽取 | `references/REFERENCE-UNDERSTANDING.md` — 意图识别、知识增强检索、字段/术语映射、条件/metric/时间/实体抽取 |
| 正确性与评测 | `references/REFERENCE-CORRECTNESS-EVAL.md` — 多表 JOIN 推理、SQL 标准化比对、评测集组织、常见错误模式 |
## 使用原则
- **证据优先**:以评测集正确率、EXPLAIN、日志为依据,而非拍脑袋规则。
- **区分表象与根因**:修一个 badcase 要定位根因并沉淀回归用例,避免只压症状。
- **可解释可追溯**:DSL 中间表示保留完整语义链路,便于审计与调试。
- **破坏性变更同步调用侧**。
## 与其他 Skill 的关系
- 被 `devlab-nl2sql-engineering` 通过 extends 继承(提供知识,流程由其编排)。
- 与 `public-mysql-expert-base` 互补(后者聚焦 DB 侧 schema/索引/事务)。
- 评测细节交 `devlab-eval-driven-agent`。
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!
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', ...
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.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**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. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.