Use when agents work concurrently in a codebase, shared files have recurring merge conflicts, or AGENTS.md or CLAUDE.md needs maintenance.
Install
npx skills add https://github.com/jssblck/agents --skill parallel-agentsSKILL.md
Parallel agents
Keep independently owned work from colliding in shared files. Apply structural changes when concurrent work or observed conflict history justifies them.
- Give independent behavior its own file when that creates a useful ownership boundary. Keep edits to shared registries small. Do not split a cohesive module merely to achieve a one-line registration.
- Shape shared lists for merging: one item per line, stable insertion order, and no unrelated reformatting. Regenerate generated files and lockfiles.
- Investigate repeated conflict hotspots before splitting them. Keep structural moves separate from behavior changes when both are requested.
- Keep agent docs concise: working agreements, non-obvious constraints, and useful setup/check entry points. Keep module detail near its owner.
References
Read only the reference relevant to the task:
- one-feature-one-file.md: choosing file boundaries for concurrent feature work.
- mergeable-edits.md: editing shared registries, generated files, or conflicting branches.
- hotspot-audit.md: measuring conflict hotspots when an audit or structural repair is requested.
- doc-gardening.md: maintaining agent instructions or reducing duplicated documentation.
Related skills
find-skillsvercel-labs3.6MHelps 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.handoffmattpocock883KCompact the current conversation into a handoff document for another agent to pick up.microsoft-foundrymicrosoft618KBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agcavemanjuliusbrussee544KUltra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".