53 tagged development workflow, measured the same way as everything else here.
Browse within: code-quality 45Multi-Agent 15
Skill Claude CodeCodex
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
Skill Claude CodeCodex
Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.
Skill Claude CodeCodex
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
cubetribe/ClaudeCode_GodMode-On
Skill Claude CodeCodex
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
cubetribe/ClaudeCode_GodMode-On
Skill Claude CodeCodex
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
cubetribe/ClaudeCode_GodMode-On
Skill Claude CodeCodex
Ultracode / Max-Parallel mode — dynamic workflows fan work out across tens–hundreds of adversarially-verified parallel subagents for large, decomposable jobs (codebase-wide audits, big migrations, cross-checked research). Opt-in; higher token spend.
ZeusYue/acceptance-driven-development-skill
Skill Claude CodeCodex
Use when building features, fixing bugs, adding capabilities, or explicitly exploring a design under ADD before AC creation or update. Use with a project's AC.md acceptance table when available; also use when the user says implement, add, fix, acceptance criteria, done means, or asks ADD to compare approaches.
ZeusYue/acceptance-driven-development-skill
Skill Claude CodeCodex
Use when writing code, designing architecture, choosing dependencies, or implementing features — especially when the task involves technology or domains (C++, Qt, astronomy, desktop apps, image processing, scientific computing) with prior experience documented in the shared document hub. Also use when the user…
Skill Claude CodeCodex
Requirement-aligned development workflow. TRIGGER: whenever the user asks to build a feature, make a change, optimize/improve something, or fix a bug — especially when the requirement is vague or lacks scope/acceptance criteria. Before starting, the agent MUST detect the user's role (PM/Developer/Both), persisted…
xincheng-1999/orchestrating-development-graphs
Skill Claude CodeCodex
Use when starting a code change, feature, bug fix, refactor, or build/configuration task where workflow intensity, approval gates, or delegation may otherwise be disproportionate to the task.
Skill Claude CodeCodex
Agile development workflow for AI coding agents, usable from Codex, Claude Code, and any Agent Skills client. Use when the user asks to plan a GitHub issue, write a feature or bug specification, implement an issue, run validation checks, review a pull request, research a topic, or plan an epic. Also triggered by…
Skill Claude CodeCodex
Multi-Agent Collaborative Pipeline for Claude Code — orchestrates 7 development phases with 6 specialized AI roles.
Skill Claude CodeCodex
Bootstrap a new project with multi-CLI agent config — drops AGENTS.md + CLAUDE.md from the cc-templates templates/ directory into a target project, patches its .gitignore, and prints verification commands. The "multi-agent" here means multi-CLI (Claude Code + Codex CLI + Antigravity CLI), not multiple internal…
Skill Claude CodeCodex
Session-end full recap — distill, codify memory to .agent-memory/, update AGENTS.md sprint-status block, commit+push. Automatic steps with safety guards delegated to scripts/wrap.sh. Works on Claude Code, OpenCode, and Codex CLI.