Skill UI

This skill builds a persistent knowledge base combining LLM wiki patterns with structured graphs. It ingests documents once to generate wiki pages and extract entities/relations, avoiding re-derivation. It supports agents with evidence-based querying, wiki search, and knowledge accumulation, ensuring cross-references are never lost.

This tool clusters keywords based on SERP overlap rather than text similarity, designing hub-and-spoke content architectures with internal links. It expands seed keywords, classifies intent, and generates interactive cluster maps. Ideal for SEO planning and content strategy before execution.

This skill automatically routes founder questions to the appropriate C-level advisor or boardroom based on keywords and intent. It eliminates the need to memorize specific slash commands by intelligently directing queries like 'runway pressure' to the CFO or 'win rate dropped' to the CRO. It handles multi-role topics by triggering a boardroom session and logs routing decisions for context awareness.

A self-hosted, semantic memory service designed for AI agents. It allows agents to save worklogs, decisions, and notes, and recall this knowledge across sessions based on meaning rather than exact keywords. Using pgvector and structured workspaces, it maintains persistent, context-aware knowledge bases, making it ideal for collaborative AI projects.

Generate professional, ATS-optimized CVs and resumes by consolidating data from multiple sources (LinkedIn, GitHub, Portfolio). This skill tailors your content to specific Job Descriptions (JD), adapts tone based on seniority, and outputs paste-ready plain text optimized for tools like FlowCV or Canva. It also provides a detailed ATS flaw report and actionable improvement suggestions.

A robust toolkit for deterministic, structural PDF manipulation. This skill allows users to perform programmatic tasks such as extracting text and tables from reports, merging multiple PDF files, splitting documents by page ranges, filling out form fields, or generating entirely new PDFs from structured data (e.g., JSON). It is designed for explicit, byte-level operations, distinguishing it from LLM-based natural language rewriting tools.

This guide details how to implement Identity-Aware Proxy (IAP) using gcloud. It enforces per-request identity verification and context-aware access policies (e.g., device posture, location) across major GCP backends, including Compute Engine, App Engine, Cloud Run, and GKE. It is essential for migrating from traditional VPN access to a robust, zero-trust, identity-based security architecture for cloud applications.

This skill facilitates the systematic triage and closure of open promises or commitments within a project context. It guides the user to reliably close these commitments using verifiable, real-world outcomes via the acc_act(runtime="outcome") command. It emphasizes maintaining rigorous provenance discipline, ensuring that status updates are based only on external or runtime validated results, thereby maximizing data integrity and accountability.

This guide provides a comprehensive reference on Agent Skills, a standardized and powerful method for providing structured context, workflows, and tools to Large Language Models (LLMs). It details the anatomy of the SKILL.md file, the three-stage progressive disclosure loading process, and best practices for creating both capability (tool-based) and process (workflow-based) primitives. Use this resource when designing, reviewing, or debugging agent-driven applications to ensure reliable and context-efficient performance.

This skill fetches the latest, live documentation and code examples for specific libraries and frameworks (e.g., Next.js, React, Prisma). Instead of relying on static or outdated training data, it utilizes the Context7 MCP to provide accurate, up-to-date answers for setup questions, API references, and code generation based on current best practices.

This is an advanced, structured workflow designed to conduct deep, multi-source investigations. It synthesizes current public evidence with user-provided context to generate highly structured reports. The workflow explicitly differentiates between verifiable facts, user-supplied evidence, logical inferences, and actionable recommendations, making it ideal for complex comparative analysis or continuous monitoring tasks.

Performs advanced semantic search across all stored brand knowledge, including guidelines, campaign learnings, and competitor insights. By combining vector databases, knowledge graphs, and local indices, it provides comprehensive, context-aware answers to complex natural language questions, ensuring users make decisions based on the brand's entire historical knowledge base.