livepowers-role-finance
claude角色包：财务/口径。Role pack for finance: environment scan, ontology evolution, night loops and write-safety.
10 skills
0
claude
livepowers-delivery
交付与安全：独立验收门、现场交付、结果账本、操作安全与可审计通信。Delivery & safety: acceptance gates, FDE delivery, outcome ledger, action safety.
/
Plugin livepowers-delivery from marketplace livepowers-marketplace in zhanglunet/livepowers. Commands read from the repo's manifest — today.
What it installs
Skills (7)
acceptance-gatesUse when any candidate capability, ontology change, spec implementation or agent-produced result is about to enter production, or whenever an agent or person says "done" and that claim needs to be confirmed. 报表上线、注册前需要独立审查验收，候选能力进入生产、或任何"已完成"需要被确认时使用。
auditable-agent-commsUse whenever two or more agents (dispatcher / executor / reviewer, or agents across teams or organizations) exchange messages and the exchange must be logged, auditable, replayable or metered. 多个 Agent 互相通信时使用。
delivery-chainUse when a business request must be delivered end-to-end as one pipeline (scan the environment and ontology, ground a spec, explore with evidence, pass the acceptance gates, then record the outcome in the ledger), or when such a delivery stopped at the human acceptance gate and must be resumed. 一条业务
fde-deliveryUse when delivering a domain Live Product at a customer site as a forward-deployed engineer, for a brownfield retrofit or a greenfield build, or when field innovations must flow back into the product. 把领域产品交付到客户现场时使用。
oltp-action-safetyUse before exploring, crystallizing or executing any action that writes production state (create, update, transfer, approve, bill, push configuration), including on legacy systems without transactions. 任何写生产状态的动作之前使用。
outcome-ledgerUse when committing to a business outcome, choosing pilot scenarios, reporting value, comparing delivery approaches, or preparing outcome- or workflow-based pricing. 衡量业务结果、核算单位成本、论证价值时使用。
takeover-handlingUse when a task has been stopped by the loop or budget limit and moved to takeover, when an agent keeps failing on the same step, when a person is asked to take over from an agent, or when the morning report lists tasks in takeover. 任务被止损转入异常接管、Agent 反复失败、人要从 Agent 手里接手时使用。
More from zhanglunet/livepowers
All 11 plugins →livepowers-role-sales
claude角色包：销售/交付。Role pack for sales/delivery: system1-first lookup, evidence-based exploration, delivery chain, takeover handling and write-safety.
10 skills
0
livepowers-role-hr
claude角色包：人力/合规。Role pack for HR: digital role specs, auditable agent collaboration and the common method baseline.
8 skills
0
livepowers-core
claude核心工作流：先查固化能力（System 1 first）、带证据探索、把验证过的路径固化成可测试能力。Core workflow: System 1 first, explore with evidence, crystallize proven paths into tested capabilities.
5 skills · 1 command · hooks
0
livepowers-night
claude夜间循环：夜间计划与晨间固化评审。Night loops: nightly planning and morning crystallization review.
2 skills · 2 commands
0
livepowers-ontology
claude本体：环境扫描、知识演进、数字角色规约。Ontology: environment scan, knowledge evolution, digital role specs.
4 skills
0
Similar plugins
impeccable
claudeDesign fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
pbakaus/impeccable 109,099
ruflo-federation
claudeCross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
ruvnet/ruflo 81,589
academic-research-skills
claude5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Imbad0202/academic-research-skills 56,698
ifixai
claudecodexIndependent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
ifixai-ai/iFixAi 45,158
cicd-automation
claudecodexCI/CD pipeline configuration, GitHub Actions/GitLab CI workflow setup, and automated deployment pipeline orchestration
4 skills · 1 command · 5 agents
wshobson/agents 42,461
Statement Auditor
claudeAudits pre-generated LP statements before distribution
3 skills · 1 agent
anthropics/financial-services 41,259
Maintain livepowers-delivery?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins11 plugins