Total 46,961 skills
Showing 12 of 46961 skills
Convergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.md.
Generate custom reports, query reports, and script reports for Frappe applications. Use when creating data analysis and reporting features.
Designs system architecture and selects technology stack based on vision analysis. Use after vision analysis for technical decisions. Triggers on: design architecture, select tech stack, choose framework.
Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.
Use when needing to check PR review comments on current branch, before addressing reviewer feedback, or when asked to fetch/review PR comments
This skill should be used when creating a new runtime provider for the vx tool manager. It provides complete templates, code generation, and step-by-step guidance for implementing Provider and Runtime traits, including URL builders, platform configuration, test files, provider.toml manifest, system package manager fallback, and optionally project analyzer integration for language-specific tools. Use this skill when the user asks to add support for a new tool/runtime in vx.
Use when creating or modifying API functions in */api/ directories. Enforces Firestore patterns and data fetching conventions.
Show infrastructure standards compliance status (read-only)
Create and manage structured meeting notes with automatic action item extraction and governance integration. Use when user mentions "meeting notes", "record meeting", "create meeting", "standup", "retrospective", "planning", or any meeting-related keywords.
Worktree-first implementation workflow for isolated, focused work. Use when starting any implementation task — single issue, feature, or multi-issue parallel work. Each worktree provides a clean, isolated directory with its own branch, preventing cross-contamination and enabling atomic PRs.
Sense accessibility barriers with gentle awareness. Listen to the forest, scan for obstacles, test the paths, guide toward inclusion, and protect all wanderers. Use when auditing accessibility, testing for a11y, or ensuring inclusive design.
Docker development environment CLI. Use for managing containers (start/stop/restart), executing commands in services, viewing logs, and running project scripts from kool.yml.