Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add eric861129/SKILLS_All-in-one --skill sql-migration-managergit clone --depth 1 https://github.com/eric861129/SKILLS_All-in-oneWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/eric861129/skills_all-in-one/sql-migration-manager)<a href="https://agentmods.dev/skills/eric861129/skills_all-in-one/sql-migration-manager"><img src="https://agentmods.dev/badge/skills/eric861129/skills_all-in-one/sql-migration-manager.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.00836 |
| Opus 5 | $0.00026 | $0.00418 |
| Sonnet 5 | $0.00010 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
sql-migration-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
SQL Migration Manager (資料庫遷移管理)
此技能定義了如何為 SKILLS_All-in-one 平台產生增量資料庫更新指令,並將其集中記錄於單一 SQL 檔案中,確保異動軌跡清晰且易於追蹤。
🚀 核心工作流 (Migration Workflow)
Step 1: 判定異動類型 (Identify Action)
- INSERT (新增):當
skill-manager執行Onboard階段時。 - UPDATE (更新):當
skill-updater偵測到版本差異並執行Update階段時。
Step 2: 產出 SQL 語法 (Generate SQL)
根據 database/init_skills.sql 的資料表結構,生成對應的 SQL。
-
新增技能範本:
INSERT INTO Skill (id, name, nameZh, description, descriptionZh, author, category, tags, downloadCount, createdAt, version, githubUrl, folderName) VALUES ({id}, '{name}', '{nameZh}', '{description}', '{descriptionZh}', '{author}', '{category}', '{tags}', 0, '{today}', '{version}', '{githubUrl}', '{folderName}'); -
更新技能範本 (僅針對變更欄位):
UPDATE Skill SET version = '{new_version}', description = '{new_desc}', descriptionZh = '{new_desc_zh}', updatedAt = '{today}' WHERE name = '{name}';
Step 3: 更新增量 SQL 檔案 (File Prepend)
- 目標檔案:
database/incremental_updates.sql。 - 寫入邏輯 (Prepending):
- AI Agent 必須將新的 SQL 指令插入到檔案的 最頂部 (Top)。
- 日期分組:若當前日期與檔案頂部日期不同,需插入新的日期標籤(如
--YYYY/MM/DD)。 - 排序:最新的異動日期應出現在檔案最上方。
範例結構:
--2026/03/11
INSERT INTO Skill ... (新異動)
--2026/03/09
INSERT INTO Skill ... (舊異動)
UPDATE Skill SET ...
🚦 規則與限制 (Guardrails)
- 禁止修改 init_skills.sql:該檔案目前僅作為「初始環境建立備份」,不應手動或自動修改。
- ID 唯一性檢查:在產出
INSERT語句前,必須讀取src/data/skills.ts,抓取最新的id,並確保 ID 沒有重複。 - JSON 轉義:處理
tags欄位時,必須確保 JSON 字串內的引號已正確轉義。 - 編碼保護:寫入
incremental_updates.sql時,必須確保為 UTF-8 (No BOM)。
📝 執行紀錄範本
- Migration: 已將 SQL 異動記錄至
database/incremental_updates.sql(日期標籤: --2026/03/09)。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 69 lines · 51 tokens per session scan A d1b9550730d7
sql-migration-manager is a skill published in the GitHub repository eric861129/SKILLS_All-in-one (52 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 836 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clickhouse-knowledge-patch
Use this skill when writing, reviewing, upgrading, or operating ClickHouse SQL and server configurations. Start with the compatibility-sensitive items below, then load the topic reference that matches the task.
alembic-knowledge-patch
Use this skill when changing an Alembic project, reviewing generated migrations, upgrading Alembic, extending its CLI or operation system, or diagnosing revision graph and backend-specific DDL behavior.
cloudflare-d1-knowledge-patch
Use this skill when designing, implementing, migrating, operating, or debugging Cloudflare D1 databases. Check the project’s Wrangler configuration, binding usage, database generation, account plan, and remote-versus-local command flags before applying guidance.
drizzle-knowledge-patch
Use this skill when work touches Drizzle SQL identifiers or aliases, Drizzle Kit module loading, or Zod schemas generated from Drizzle tables.
duckdb-knowledge-patch
Use this skill when writing DuckDB SQL, upgrading an existing database, working with external files or lakehouse formats, configuring the CLI, or using spatial data. Inspect the project's DuckDB version and load the relevant topic reference before relying on defaults, return types, parser behavior, storage…
lineage
Use when user invokes /lineage with a column name (optionally qualified with table/schema). Also triggers on "trace this column", "where does X come from", "what reads from Y table". Traces column-level data lineage through SQL, Kafka, Spark, JDBC, and ORM codebases. Produces a structured lineage path with confidence…