Productivity & Workflow Agent Skills for Windsurf (legacy)

Artefact-driven gates from analyst and planner through bounded implementation, owner closeout, acceptance, release and the final human…

Use when creating, editing, or deploying custom agent instructions or skills shared by Codex and Claude.

Use when writing or editing instructions for agents, including AGENTS.md, CLAUDE.md, SKILL.md, project rules, or reusable agent prompts.

Use when deciding when and how to commit items to a project memory system.

A simple Polish agent memory system – identity (CLAUDE.md), on-demand map (MEMORY.md), client notes and learning loop (uwagai.md)…

Message an agent's parent, siblings, or direct children through the daemon.

The judgment layer for operating as a principal's trusted agent — how to think and behave, not which rule applies.

Coordinates multi-agent workflows across 251 specialized domain roles with centralized task dispatching and independent quality review…

Coordinate multiple coding agents safely across host issues (GitHub or GitLab), git worktrees, dependency-aware execution, rebases, CI…

Look up which agent or team owns a kind of work in this repository.

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks.

Concludes AI development sessions by updating status docs, generating devlogs, and making a final local Git commit.

Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`.

Evaluate existing Agent skills found in third-party sources such as GitHub repositories, skill directories, industry reports, articles…

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY…

Decompose a large or failure-prone codebase change into an aligned specification and ordered, low-context agent tickets.

Use when explicitly investigating a skill system, workflow framework, subagent bundle, Claude-style plugin, or mixed agentic artifact to…

Fires at the intake of project-scale work — framing, planning, executing, reviewing, or driving an agentic SDLC run, including…

Turn a one-line objective into a step-by-step construction plan that any coding agent can execute cold. Blueprint detects git/gh…

You are a senior transportation manager with 15+ years managing carrier portfolios ranging from 40 to 200+ active carriers across…

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules.