Skill Claude CodeCodex
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
Query or maintain a project's Graphify knowledge graph for codebase architecture, symbol relationships, impact analysis, and corpus exploration. Use for codebase questions when graphify-out/graph.json exists, or when the user explicitly asks to build, update, explain, or navigate a graph.
Skill Claude CodeCodex
Install, update, or prepare Sanad for normal use or source development on macOS, Windows, or Linux. Use when an AI agent must inspect a machine for an existing Sanad installation or checkout, explain the release-user and developer-source paths, install the Client and local Agent, install an Agent on a remote server…
Skill Claude CodeCodex
Standard operating procedures for live and isolated Sanad development, sanad-dev runtime control, diagnostics, verification, Git worktrees, and Pull Request delivery.
Skill Claude CodeCodex
Comprehensive testing and interactive verification protocol for the Sanad Flutter client including unit, widget, E2E, and agent-driven UI testing through the Dart VM Service.
Skill Claude CodeCodex
Route Sanad community requests to Discord, Discussions, Issues, or tracked plans and apply the versioned label taxonomy without exposing sensitive reports.
Skill Claude CodeCodex
Standard Operating Procedure (SOP) for planning, task breakdown, repository audits, execution routing, and merge coordination in Sanad.
Skill Claude CodeCodex
Prepare and deliver a focused Sanad pull request through an isolated worktree, bounded verification, CI repair, protected review, and squash-merge handoff.
Skill Claude CodeCodex
Review a Sanad pull request against its owning Issue, plan, contracts, tests, security boundaries, and protected-path label requirements.
Skill Claude CodeCodex
Create, refresh, consume, and audit pinned external reference evidence for Sanad plans and implementation tasks while keeping tracked project knowledge clean and source-neutral. Use when planning or implementing a task that benefits from reference projects, when a task declares referencegrounding or evidenceid, when…
Skill Claude CodeCodex
Maintain the public Sanad Agent repository through its tracked governance, review labels, protected checks, fork-safety rules, and verified GitHub workflows.
Skill Claude CodeCodex
Standard operating procedure for isolated coding, verification, and Pull Request delivery by a focused Sanad subagent.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Codex
Compare two outputs WITHOUT knowing which skill produced them.
Agent Codex
Evaluate expectations against an execution transcript and outputs.
Cursor rule Cursor
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
Instructions file CodexOpenCode
Instructions for EastStarAI/sanad-agent, covering sanad agent repository contract, 1. documentation hierarchy, rules for ai agents and developers, 1.1. the strict separation pact and 1.2. the living project wiki & incremental documentation.