@boshu2

release handles the full pipeline from code readiness through tagged commit and ci verification, including changelog generation, version bumps, and dry-run validation before publishing.

bug-hunt provides a 4-phase investigation framework (root cause, pattern, hypothesis, fix) for reactive bug triage and proactive audits. outputs structured markdown reports to .agents/research/.

pr-research guides systematic exploration of upstream repositories to understand contribution workflows and project structure before submitting pull requests to external codebases.

codex-team orchestrates parallel agent execution with lock-based file conflict prevention. agents handle discrete tasks while the lead prevents concurrent writes to the same resources.

doc generates and validates project documentation by detecting project type and scanning for existing docs, but lacks complete workflow definition and recovery mechanisms.

update pulls the latest agentops skills from a github repository and reinstalls them globally via a curl-piped shell script. execution is incomplete.

converter transforms agentops skills between platform formats via a three-stage parse-convert-write pipeline, but lacks actionable procedure detail and failure handling.

goals manages agentops goal state via yaml and markdown files using the ao goals cli, but lacks procedural detail and practical workflow documentation.

council — an installable skill for AI agents, published by boshu2/agentops.

Show AgentOps work status.

Validate PR scope and quality.

Provide repo coding standards.

Plan an open source PR.

Repair skill hygiene.

Record Brownian Ratchet gates.

Run composable security analysis.

Check knowledge flywheel health.

Explore and write findings.

Trace artifact provenance.

Explain AgentOps workflows.

Run repository security scans.

Prepare PR commits and body.

Learn from PR outcomes.

Create or refine PRODUCT.md.

Scaffold or audit OSS docs.

Implement a scoped OSS PR.

Trace decisions through artifacts.

Write compact session handoffs.

Validate code readiness.

Find focused refactor hotspots.

Shared AgentOps skill contracts.

Use official OpenAI docs.

Reverse-engineer product specs.

Load relevant .agents context.

Mine transcripts into learnings.

Track issues with bd/br, triage with bv, and convert plans to beads.

Run discovery, crank, validation.

Recover session context.

Separate goals from implementation.

Capture a session learning.

Show AgentOps next action.

Implement one tracked issue.

Execute epics through waves.

Dispatch parallel agents.

Stress-test plans before work.

Review completed work and learn.

Decompose goals into issue plans.

evolve — an installable skill for AI agents, published by boshu2/agentops.

readme — an installable skill for AI agents, published by boshu2/agentops.