Skill UI

This skill is designed to prevent AI coding assistants from exhibiting sycophantic agreement bias. When active, it forces a structured, critical assessment of user claims. The process involves extracting the core claim, assessing it independently with evidence (for/against), and concluding solely based on that assessment, ensuring objective and evidence-based responses.

This meta-skill provides an auditable workflow for professional compliance self-assessments (e.g., GDPR, SOC2). It executes deep research while retaining citation evidence, then compiles the findings into a comprehensive package: a signable DOCX report, a read-only PDF archive for permanence, and a persistent memory note to guarantee the evidence chain is recallable. Ideal for structured policy auditing.

This meta-skill is designed for complex decision analysis when a user provides or references structured documents such as contracts, quotes, spreadsheets, or notices. Instead of simple summarization, it extracts key evidence, identifies risks (e.g., renewal risk, payment terms), and structures the output into decision-ready formats, such as 'sign/reject/negotiate' recommendations, evidence tables, or required next actions. It supports input from PDF, DOCX, and XLSX formats.

This meta-skill orchestrates a comprehensive workflow for analyzing PDF documents. It handles complex tasks such as summarizing, cross-document comparison, and targeted Q&A. It ensures findings are traceable by indexing evidence from various sources (full PDFs, pasted excerpts, etc.) and synthesizing structured insights across multiple files.

This meta-skill orchestrates a comprehensive research pipeline for sales professionals. It accepts initial lead requests and systematically performs web searches, reviews public source evidence, and drafts actionable materials. The final output includes a detailed account brief, pain hypotheses, stakeholder maps, personalized outreach emails, and discovery call questions, enabling deep preparation before any sales interaction.

This advanced tool surfaces critical, often unrecorded, evidence of human-AI collaboration during development sessions. It analyzes git diffs and conversational context across multiple layers to classify the signal level (HIGH/MEDIUM/LOW), measure technical complexity, detect decision forks, and quantify the specific contribution of the AI model, providing structured data for post-session retrospectives and accountability.

This agent provides a critical framework for navigating corporate environments, contrasting internal jargon and process visibility (Ding In) with objective, real-world evidence and user experience (Ding Out). It helps users move beyond subjective 'feelings' or polished reports, structuring complex tasks into verifiable components: Goal, Acceptance Criteria, Action, Evidence, and Risk. Ideal for project management, status reporting, and critical thinking in a corporate setting.

This skill allows users to mine their extensive coding history across various AI agents (Claude, Codex, Gemini, etc.) into a persistent, structured corpus. It surfaces reproducible workflows as evidence and interactively helps the user forge these past practices into reusable, installed skills across their agent ecosystem. It is designed to synthesize judgment from raw transcripts into actionable, portable skills.

This skill maps engineering changes (code diffs, architecture designs, IaC) to specific financial compliance controls, such as PCI-DSS v4.0 and MAS TRM. It generates an auditable report detailing compliance gaps, required evidence, and concrete remediation steps, helping teams catch violations before formal audits.

This skill provides a deterministic, git-only method to verify claims made by AI agents (e.g., 'done', 'shipped', 'fixed'). Instead of trusting the agent's self-report, it audits the commit's diff and git history using the DOS kernel (`dos verify`, `dos commit-audit`) to confirm if the claimed change genuinely occurred and is backed by non-forgeable evidence. It acts as a critical quality gate.

This skill guides coding agents through a comprehensive memory loop using AccInt's MCP server. It allows agents to retrieve prior outcomes, resolve complex reasoning frames, and formally close commitments with verifiable evidence (e.g., passing tests, successful merges). Essential for managing non-trivial, multi-step development workflows and ensuring work builds on genuine results.

This skill applies a rigorous, evidence-first discipline to coding tasks, inspired by Fable-like best practices. It guides agents through a structured workflow: inspecting the workspace, tracking goals and findings, grounding all conclusions in verifiable evidence, and executing thorough verification gates before declaring completion. Ideal for complex development, debugging, or adapting cross-model prompt guidance into robust, verifiable project rules.