Skip to content

hariharapanigrahy/layerkit / skills/layerkit-multi-agent

layerkit-multi-agent

Verified

Coordinate specialist agents for integrate or contract heal; brownfield production code.

layerkit-multi-agent

Team of agents on the same integration pipeline. The lead agent coordinates specialists directly; Layerkit does not generate a deterministic multi-agent plan.

Start

Contract heal (map already exists — human supplies OpenAPI/docs)

  • Discover task omitted
  • Researcher = evidence-backed semantic rename decisions when needed
  • If only docs are supplied, researcher/AI must read/cite docs before source edits
  • AI agents edit production source/test files directly
  • Record rename decisions in the handoff note only when docs/code evidence supports a removed-to-added field rename

First-time / multi-vendor

Use the lead agent to assign vendors/files explicitly. Keep one writer per production file and use handoff notes for state.

Roles

RoleSkillHeal note
orchestratororchestrate-integrationstatus shows mode=heal|full
discovererdiscover-data-layernot in heal plan
stylistalign-client-styletopology for existing adapters
researcherresearch-vendorcontract pin + drift
designer / authordesign / processorsurgical on drift
privacyprivacy-reviewhuman if new PII
integratorsource-edit-clientdirect production source edits
verifierdoctor + project testsquality
checkerchecker-assistread-only

Concurrency

  • Parallel research/integrate per vendor when files do not overlap
  • Single writer: integrator:registry
  • Human: privacy, checker approval, breaking drift

Forbidden

  • Two agents on the same registry file
  • Re-running full discover on heal when domain is known
  • Invented fields or guessed renames; self-approve
  • Treating generated plans as production source code
  • Relying on Layerkit runtime/route/strategy code instead of editing the client package

Success

  • Agent assignments match intent (heal vs full)
  • Specialists have explicit files/responsibilities
  • Production adapters updated
  • Project tests + quality green
  • Human checker handoff complete
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall