boshu2

bootstrap

Initialize explicitly requested, missing AgentOps documentation and optional verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".

codebase-recon

Trace a repo into cited flows. Not for a bounded question; that is research. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".

swarm

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

using-flywheel

Operate the Agentic Coding Flywheel through its native workflow. Use when: the caller explicitly selects this factory; convergence and closed work do not prove semantic acceptance.

Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".

handoff

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

anti-ceremony

Guard outcome work against process overhead. Triggers: optional "quick guard"; explicit "full anti-ceremony audit" requests.

Data & Documents Featured

converter

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

pattern-mining

Test repeated implementation shapes against independent exemplars and a holdout before routing an earned abstraction. Triggers: "mine a recurring code pattern", "is this abstraction earned", "extract invariants from implementations".

scaffold

Stamp a bounded project, component, or CI scaffold and verify the generated result once. Triggers: "scaffold", "create project component or boilerplate".

toil-mining

Mine caller-supplied usage history for repeated toil and emit ranked evidence. Triggers: "mine toil", "find repeated operational work".

status

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

fitness

Measure declared project fitness goals without recommending or applying work. Triggers: "fitness", "check project fitness", "measure goals".

scope

Review the bead or caller intent write scope for completeness and ambiguity. Triggers: "review write scope", "check scope boundaries", "scope this change".

human-only-skills

Name the skills reserved for people to invoke — where the runtime honors disable-model-invocation — and when to reach for each. Triggers: "human-only skills", "which skills must I run myself".

one-way-door

Classify a pending decision as reversible or irreversible; route irreversible ones to the caller. Not for challenging a frozen plan; that is premortem. Triggers: "is this a one-way door", "can we undo this", "should I just decide this", "the models disagree with me", before any auto-decided approval gate.

API & Backend Featured

route

Pick the one AgentOps skill that owns a request, or answer that none does. Triggers: "which skill covers this", "route this", "is there a skill for X", "what should I use here", or any request whose owning skill is not obvious.

standards

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

crank

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".

ms

Find and load guidance with the meta_skill search engine. Use when: searching a skill corpus; CASS owns past sessions and Skill Builder owns package authoring.

ntm

Operate selected NTM agent panes and inspect native state. Use when: persistent tmux roles are requested; pane liveness and prompt delivery are not validation.

rch

Offload one build through RCH or diagnose its remote compiler. Use when: remote compilation is selected; report errors without creating a retry controller.

sbh

Inspect disk pressure with SBH and perform an authorized recovery action. Use when: storage diagnosis or SBH recovery is requested; inspection does not authorize deletion.

operationalize

Distill repeated, evidence-backed expertise into a proposed skill, check, reference, or workflow artifact. Triggers: "operationalize this", "turn this expertise into a reusable capability".

learn

Optionally mine bounded episodes, verdicts and corrections after the critical path. Triggers: "learn from verdicts", "mine validation history".

goals

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

product

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

shared

Retired — its runtime-neutrality contract moved to docs/contracts/runtime-neutrality.md. Triggers: none — not routable.

workflow-builder

Scaffold an explicit one-shot workflow adapter without lifecycle authority. Triggers: "build a workflow adapter", "scaffold a one-shot workflow".

good-skill

A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly.

plan

Define intended behavior, review write scope and assess reversible decisions. Use when: discovery needs clarification or resumption before one complete slice; stop once actionable.

rpi

Apply the outcome-to-judgment charter. Use when: the caller explicitly selects RPI; ordinary coding, delegation and native goals do not require this workflow.

using-gc

Operate Gas City through its Mayor, registry packs and native run state. Use when: the caller explicitly selects Gas City; factory completion does not replace independent judgment.

agent-mail

Coordinate selected writers with Agent Mail messages and advisory file reservations. Use when: this adapter is requested; mail does not own tracker status.

implement

Implement changes, repairs or waves; return per-lane evidence. Use when: coding, service operations, reliability, delivery, incident recovery, resilience or toil is authorized.

reverse-engineer

Tear down an authorized competitor repo, binary or product into a feature inventory and adoption choices. Use when: comparing an external system; local questions go to Research.

Web & Frontend Featured

skill-builder

Create, adapt, consolidate or repair skill packages and projections. Use when: authoring guidance, descriptions or structure; Skill Eval measures behavioral benefit.

cc-hooks

Configure Claude Code hooks and narrow enforcement guards. Use when: the caller requests hook installation, repair or policy changes; a hook is not required to use other skills.

craft-goal

Draft or lint a bounded persistent goal above a bead graph of RPI experiments. Use when: this goal workflow is explicitly selected; shaping a single change belongs to Plan.

codex-exec

Run one prompt through headless Codex and capture its result. Use when: requesting a single noninteractive Codex process. Not for worker batches or retries.

Data & Documents Featured

doc

Write grounded docs, READMEs, repo instructions or continuity handoffs. Use when: these documents are requested; no reports as a routine completion ritual.

postmortem

Analyze outcomes or an interim cutoff. Use when: a postmortem is explicitly requested; consumes available judgment, never gates code acceptance or requires a lesson.

Code & Development Featured

refactor

Simplify structure, interfaces or responsibilities while preserving behavior. Use when: a focused refactor is requested; feature changes need their own intent.

research

Trace code or test a recurring pattern to answer one cited question. Use when: uncertainty needs evidence. Not for external feature teardowns; use reverse-engineer.

security

Review code or scan for security vulnerabilities, secrets, dependencies and prompt risks. Use when: concrete exposure needs assessment; never silently change policy.

premortem

Challenge a rollout plan with one fresh judge before implementation; identify what could make it fail. Not for finished-code judgment. Triggers: "one judge", "challenge this plan".

DevOps & Infrastructure Featured

council

Compare model perspectives for brainstorming, planning, validation, idea duels or interviews. Use when: independent proposals or judgments need optional bounded debate.

skill-eval

Measure whether a skill helps a named task or needs revision or removal. Use when: a bounded routing or coding evaluation is requested; conformance alone cannot show benefit.

reality-check

Audit claimed state, goals or native status. Use when: a claim audit or snapshot is requested. Clarify advice versus acceptance for ambiguous checking or readiness requests.

agent-native

Dispatch independent tasks to parallel workers or selected persistent roles. Use when: delegation is authorized with disjoint scopes; execution does not validate output.

cass

Search agent session logs and cited episodes with CASS. Use when: past prompts, decisions or failures may answer a question; repeated text is not a proven lesson.

memory

Find reviewed context, capture evidence or curate maintained claims. Use when: prior evidence can change an action, or learning is requested; no mandatory recall or lesson.

dcg

Diagnose a Destructive Command Guard block or configure its rules. Use when: DCG rejected an operation or policy work is requested; never disguise commands to bypass it.

Code & Development Featured

idea-genie

Generate evidenced options or challenge an idea. Use when: deciding what to build or comparing alternatives; exploration does not authorize implementation.

validate

Freshly judge a finished change and its claims against original acceptance. Use when: acceptance verdict or independent proof is sought. Clarify generic checks or readiness first.

account-rotation

Switch coding-agent accounts and verify runtime identity. Use when: the caller requests an account change; never rotate automatically to evade a quota.

agy-native

Run a supplied task in AGY Antigravity and collect its result. Use when: the caller selects AGY; never a fallback for native coding.

domain

Clarify domain terms, bounded contexts and repository conventions. Use when: naming, rule ownership or Go and other language standards are unclear; avoid a broad survey.

orchestrate

Coordinate authorized workers, prerequisites, isolated scopes and review capacity. Use when: dispatching, recovering or routing feedback. Not for implementation or judgment.

Code & Development Featured

review

Give advisory feedback on a plan, design or code. Use when: suggestions, tradeoffs or a second look are wanted. Not for acceptance or write scope; use Validate or Plan.

interview

Interview the caller one question at a time to settle a big outcome before agents work alone. Use when: shaping a goal or large RPI. Not for one question on one slice; use Plan.

navigate

Pick the next wave on a bead graph and keep the graph honest toward frozen acceptance. Use when: a goal starts a wave, or you ask what is next on an epic.