Loading...
Loading...
Found 72 Skills
GitHub Research Assistant. Use this skill when the user wants to analyze a GitHub repository. Analysis dimensions -- 1) Basic information; 2) Purpose, what it can be used for; 3) Tech stack, including frameworks, languages, algorithms, etc.; 4) Usage and examples; 5) Technical architecture and module analysis
Provider-agnostic wait-for-change skill that uses the Dumbwaiter MCP server to wait on PR events (GitHub first) via wait.start/status/cancel/await, with progress notifications and durable state.
Natural language → SQL → execute read queries against the database. Auto-detects local connection, discovers project connectors for remote environments and domain knowledge. TRIGGER when: user asks a data question in natural language (count, list, show, verify, check, how many, cuantos, traeme, muéstrame), mentions database tables, or asks about data in any environment (production, staging, dev, local). DO NOT TRIGGER when: user provides raw SQL ready to execute.
Asks for user feedback after each task or cron job completion and runs a recursive learning flow. If output is good, asks what was good until 10 approvals; if needs improvement, asks why/how/what via multiple choice plus optional examples, uses web search and iterative thinking to resolve, and caps iterations by severity (slight 5, medium 10, severe 20). Keeps feedback non-intrusive. Use when completing discrete tasks or cron jobs for the user.
A validation framework that ensures Claude's responses are current, accurate, complete, and clear. Use this skill whenever the user asks a factual or research question, requests analysis or recommendations (e.g., "What's the best framework for X?", "Compare options for Y"), or any prompt where recency and accuracy matter. Also trigger when the user explicitly asks for validated, verified, or fact-checked answers. This skill should activate broadly — if the answer depends on facts that could have changed in the last few months, use it. Even questions that seem straightforward ("Is X still the recommended approach?") benefit from this skill's validation pipeline. Do NOT trigger for purely creative writing, casual chat, or tasks that are entirely opinion-based with no factual claims.
Constructive, evidence-based dialogue mode that avoids sycophancy. This skill should be used when the user wants balanced multi-perspective analysis, critical feedback, or rigorous challenge of their ideas. Triggers on "/balanced" or requests for honest/critical/balanced feedback. Supports passive, interactive, tldr, steelman, and decision modes.
Interact with Google Contacts to search and create contacts.
Query and update Lee's goals graph through natural language. Translates conversational questions and updates into goals_query.py commands.
Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.
Score assistant responses for guidance & actionability on a strict 1-5 scale, then return strict JSON only with dimension, score, rationale, and improvement suggestions. Use when the user asks to evaluate how actionable, helpful, or step-by-step a response is.
World BOB Skill
Operate Feishu Bitable, supporting management of data tables, records, fields and media. Usage scenarios: When the user mentions "Feishu Bitable", "Feishu Spreadsheet", "bitable", or needs to read/write table records, operate data table structures, manage fields, or upload media.