Skill UI

This skill ingests public complaints from X/Twitter, automatically detecting, classifying, and clustering reported bugs. It cross-references symptoms with repository evidence (commits, deploys) and assigns ownership using defined routing rules. It is essential for product teams needing to monitor product health and gather early bug signals from social media channels.

This tool performs a rigorous Level 2 semantic epistemic review of Agent-Native Research Artifacts (ARAs). It assesses six critical dimensions—including evidence relevance, falsifiability, and methodological rigor—to determine the content's intellectual soundness. It is used after initial structural validation to provide objective, constructive criticism, scoring the work from Strong Accept to Reject.

This skill enforces output quality and evidence verification across security audits like SAST, SCA, and code reviews. It prevents suppression of valid findings and ensures reports meet quality thresholds before delivery. Includes components for self-critique, anti-rationalization, and continuous learning to maintain intellectual honesty and accuracy in security analysis workflows.

This tool assists engineers in transforming vague work logs into structured, evidence-backed impact statements for professional documentation. It uniquely mines Copilot CLI session logs, git commits, and GitHub PRs to reconstruct forgotten work. It enforces a mandatory 'Action → Result → Evidence' impact contract, making it indispensable for preparing performance reviews, promotion packets, and self-assessments.

This skill performs a rigorous, 5-dimension expert critique on any digital artifact, such as landing pages, presentations, or prototypes. It systematically evaluates five critical areas—Philosophy, Visual Hierarchy, Detail Execution, Functionality, and Innovation—scoring each 0-10. The output is a comprehensive, evidence-backed HTML report providing actionable insights, a radar chart, and prioritized lists (Keep/Fix/Quick-wins) to guide systemic design improvements.

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.

A professional methodology for writing penetration test and red team reports, covering executive summaries, technical findings, CVSS scoring, evidence handling, remediation tracking, retest notes, and delivery formats for clients and internal teams.

Drafts self-assessments, peer reviews, and upward feedback using WorkIQ evidence from emails, meetings, and contributions. It helps you write honest, impact-focused performance reviews in your own voice with STAR-based structure.

A specialized CLI alias designed to implement the PUA P9 protocol, simulating the role of a P9 tech lead for AI coding assistance (Codex/Claude Code). This tool helps users structure complex development tasks by focusing on writing precise prompts, managing execution steps, and strictly adhering to a defined professional protocol, minimizing direct code implementation unless reassigned. It ensures rigorous process management and evidence-based output.

This CLI alias executes a comprehensive teardown protocol for PUA agents, designed for development environments. It safely releases all active agent and loop states, ensuring a clean system reset. It automatically manages configuration files like ~/.pua/config.json, preserving unknown fields while providing reliable, evidence-based cleanup.

Integrates the FLOW framework for evidence-led SEO, providing stage-specific AI prompts (Find, Leverage, Optimize, Win) from a 41-prompt library. Use for structured SEO analysis and optimization.

A specialized assistant designed to navigate and accurately retrieve commands and parameters from the offline Alibaba Cloud CLI Chinese documentation mirror. It enforces a strict, hierarchical workflow: first consulting quick usage guides, then checking the main index, and finally drilling down to specific chapter pages. This structured approach ensures all provided information is accurate, evidence-based, and highly relevant to the user's intent.