agents-workspace

Use when planning or executing delegated work, including execute-the-plan continuations. Covers the full coordination cycle: analyze request, define roles, discover specialists, plan execution, handoff, review and synthesize.

Create, refine, and validate Agent Skills following the agentskills.io specification. Use when writing a SKILL.md, creating a new skill directory, improving an existing skill's triggering or content, running evals, or diagnosing why a skill isn't activating.

Create, evolve, and archive spec-driven workflow artifacts (proposals, outcome specs, task plans). Use when work needs a durable outcome contract before execution — new deliverables or outcome changes, API/contract changes, migrations, security/privacy-sensitive work, or any long-running task where the outcome must be agreed upfront. Do NOT use for trivial fixes, exploratory spikes, or tasks where the handoff's done criteria suffice. Produces specs/ artifacts that orchestrate consumes via Spec ref.

Use this skill when querying workspace knowledge before tasks or ingesting learnings after completing work. Self-learning loop for the workspace.