boshu2

Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.

Write source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.

Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.

Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.

Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.

Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

Change or repair code, config or services without weakening tests; report what ran and what did not. Use when: implementing a change or fixing a defect.

Write compact caller-authored session evidence without choosing continuation. Triggers: "handoff", "write compact session handoff".

Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.

Create or refine PRODUCT.md while separating evidence, aspiration, users, value, and non-goals. Triggers: "product", "create PRODUCT.md", "product boundary".

Report observable AgentOps evidence without selecting work. Triggers: "status", "show AgentOps status".

Compatibility alias — renamed to fitness. Use fitness to measure declared project fitness goals. Triggers: "goals" (deprecated).

Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

Load only the standards relevant to a caller-supplied change, then report concrete findings. Triggers: "check standards", "which standards apply".

Run autonomous improvement loops. Triggers: "evolve", "improve everything", "autonomous improvement".

Compatibility pointer for the canonical premortem skill.

Execute one caller-selected wave by invoking RPI once per lane and return the wave evidence, then stop. Triggers: "crank", "execute the next wave", "run this wave".

Compatibility pointer for the canonical postmortem skill.

Run release validation. Triggers: "run release validation", "cut a release", "check release readiness".

Check or repair structural hygiene in AgentOps skill packages. Triggers: "heal skill", "repair skill hygiene", "audit skill structure", "check skill package".

Prepare PR commits and body. Triggers: "pr-prep", "pr prep", "prepare pr commits and body.".

Recover session context. Triggers: "recover", "recover session context.", "recover skill".

Check knowledge flywheel health. Triggers: "flywheel", "check knowledge flywheel health.", "flywheel skill".

Mine transcripts into learnings. Triggers: "forge", "mine transcripts into learnings.", "forge skill".

Load relevant .agents context. Triggers: "inject context", "load .agents context", "pull decay-ranked prior knowledge".

Investigate bugs and root causes.

Coordinate multiple Codex agents.

Find focused refactor hotspots.

Validate code readiness. Use when: doing a quick readiness or sanity check that code is ready to commit or ship, short of a full review.

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

Show AgentOps next action.

Capture a session learning.

Trace decisions through artifacts.

Reverse-engineer product specs.

Separate goals from implementation.

Explain AgentOps workflows.

Record Brownian Ratchet gates.

Research an upstream repo.

Trace artifact provenance.

Draft or improve README docs.

Implement a scoped OSS PR.

Use official OpenAI docs.

Validate PR scope and quality.

Run composable security analysis.

Learn from PR outcomes.

Scaffold or audit OSS docs.

Plan an open source PR.