boshu2

Convert AgentOps skill formats.

Run multi-judge consensus.

Validate OpenShift Grafana dashboards.

Scaffolds a new Claude Workflow script for deterministic multi-agent orchestration. This skill is triggered by phrases like 'build a workflow' or 'create a workflow'.

Run post-implementation validation.

Load relevant .agents context.

Use official OpenAI docs.

Create or refine the PRODUCT.md file.

Research an upstream repo.

Validate PR scope and quality.

Stress-test plans before work.

Reverse-engineer product specs.

Scaffold a new SKILL.md.

Provides repository coding standards.

Dispatch parallel agents.

Find focused refactor hotspots.

Execute epics through waves.

Generate and validate repo docs (default), READMEs (--mode=readme), and OSS doc packs (--mode=oss).

Canonical vocabulary for human-AI software work.

Use official OpenAI docs.

Run discovery, crank, validation.

Create project, component, or boilerplate scaffolds.

'Audit an existing SKILL.md against the unified AgentOps template (15

Implement a scoped OSS PR.

Run release validation.

Explore and write findings.

Compile .agents knowledge wiki.

Load relevant .agents context.

Review completed work and learn.

Recover session context.

Run discovery, crank, validation.

Provide repo coding standards.

Canonical vocabulary for human-AI software work.

Mine transcripts, .agents, bd, and git for skill diffs, bd updates, or

Run autonomous improvement loops.

Shared AgentOps skill contracts.

Deep codebase exploration with multi-angle analysis for Codex agents. Output: .agents/research/*.md. Triggers: "research", "investigate", "explore codebase", "how does X work".

Validate product fit before discovery.

Check knowledge flywheel health.

Mine transcripts into learnings.

Create project, component, or boilerplate scaffolds.

Run repository security scans.

Explain AgentOps workflows.

Run multi-judge consensus.

Execute epics through waves.

Create dense execution packets.

Maintain AgentOps goals.

Write compact session handoffs.