945 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
Agent Codex
Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
Agent Codex
Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.
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.
Agent Codex
Plans changes to the skill pack — new sub-skills, addons, presets — respecting the ship boundary and the SKILL.md contract.
Agent Codex
Implements a planned change to the skill pack task-by-task, running the local CI gate after each step.
Agent Codex
Reviews a diff in this skill-pack repo for ship-boundary, frontmatter, bash 3.2, and public-surface violations before commit.
DangQuangSE/team-development-skills
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
DangQuangSE/team-development-skills
Agent Codex
Evaluate expectations against an execution transcript and outputs.
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.
Agent Codex
A leaf worker in the OpenSpec workflow that completes its assigned work directly instead of starting other agents.
Agent Codex
A leaf worker in the OpenSpec workflow that completes its assigned work directly instead of starting other agents.
Agent Codex
A set of instructions for an OpenSpec workflow agent that handles one small workflow step itself.
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.
Agent Codex
Deep wiki analysis specialist. Use proactively when the user asks complex analytical questions that require reading many wiki pages, cross-referencing sources, or identifying patterns across the knowledge base.
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Codex
Evaluate expectations against an execution transcript and outputs.
Agent Codex
Long-running codebase scan. Extracts de-facto design tokens from existing UI code, clusters them by frequency, names them, returns a draft DESIGN.md body conforming to the Google Labs spec. Dispatched by /mddesign:harvest.
Agent Codex
Consumes one PhaseSpec v1 and runs it end to end. Reads referenced files itself. Returns a structured result. Default subagent for /mddesign:team dispatch.