tangcent

Create or update a skill in this repository under skills/<skill-name>. Use when the user asks to add a new skill, improve an existing skill, scaffold skill structure, or align a skill with repository standards.

Work with Obsidian vaults — create and edit Obsidian Flavored Markdown (.md), Bases (.base), JSON Canvas (.canvas), and interact with vaults via the Obsidian CLI. Use when working with Obsidian notes, wikilinks, callouts, embeds, properties, frontmatter, tags, bases, canvas files, or vault operations.

Build and modify Grafana dashboards following the user's established style conventions. Use when creating new dashboards, adding panels, modifying existing dashboards, or reviewing dashboard JSON for consistency. Requires the Grafana MCP to be enabled.

Operate GitLab from terminal with `glab` for repositories, merge requests, issues, pipelines, releases, and API calls. Use for any GitLab task. For template-compliant MR creation, load reference workflow under references/.

Operate GitHub from terminal with `gh` for repositories, pull requests, issues, releases, actions, and API calls. Use for any GitHub task. For template-compliant PR or issue creation, load reference workflows under references/.

Manage day-to-day Git workflow with safe branch creation, conventional commits, rebasing, pushing, MR creation, active-branch sync, and integration-branch consolidation. Use when the user asks to create branches, commit, push, sync feature/fix branches, rebuild dev branches, or open merge requests.

Detect when the user is correcting the AI's approach or pointing out mistakes. Trigger phrases include 'you should', 'why not', 'that's wrong', 'use X instead', 'not like that', 'I said', 'no, do', 'wrong tool', 'wrong approach', 'I meant', 'actually', 'instead of', '不对', '应该用', '为什么不', '错了'. On activation, the AI reflects on what went wrong, identifies the correct approach, and logs the lesson to Obsidian for future reference.

Query, modify, and inspect MySQL databases via mysql-cli, a smart wrapper that supports multiple instances, auto-routes by table name, caches metadata, and executes .sql files. Use when the user asks to query MySQL, modify tables/data, check schemas, run SQL files, or verify database content.

Guide how to write test cases in this project by first analyzing the target class to decide which test pattern, base class, and test utilities to use. Activate when user asks to write tests, add test coverage, or create test cases for any class.

Identifies and fixes bugs systematically. Invoke when user reports an error, test failure, or unexpected behavior that needs debugging and fixing.

Reviews a git commit to create a test plan document. Invoke when user asks to review a commit, analyze changes, or create test coverage plan for recent changes.

Navigate your APIs. Automatically scans source code (Java/Spring, Go/Gin, Node.js/Express, Python/FastAPI) and exports API endpoints to Postman collections, Markdown docs, or cURL commands. Use when the user needs to extract APIs from code, generate API documentation, create Postman collections, or export API endpoints from a codebase.

Resolves GitHub issues end-to-end: assignment, implementation, documentation updates, branching, and PR creation. Invoke when user wants to work on a GitHub issue or mentions issue handling workflow.

Guide how to write test cases in this project by first analyzing the target class to decide which test pattern, base class, and test utilities to use. Activate when user asks to write tests, add test coverage, or create test cases for any class.

Bridges the gap between terminal AI tools and the IDE editor. Activate when user says "this file", "this function", "this class", "explain this", "current file", "selected code", "what I have open", or asks about code without providing it. Skip if the AI already has the file content or path in context. Works with VS Code, Cursor, JetBrains IDEs and their forks via the One-IDE plugin.