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
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.
Plugin livepowers-core from marketplace livepowers-marketplace in zhanglunet/livepowers. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
crystallize-to-system1Use when an intent has been explored successfully several times, when the user says "do it this way from now on", or when the nightly review has selected a crystallization candidate. 把探索成功的路径固化为 System 1 能力包时使用。
explore-with-evidenceUse when the capability registry misses, when a request is new, rare or the environment has changed, and the agent must reason it out with the LLM (write SQL, analyze, trial-and-error, orchestrate tools). 注册表未命中、需要 Agent 自主探索时使用。
ontology-grounded-specUse before implementing any business feature, report, dashboard, query, transactional command or workflow, and whenever a request is ambiguous about scope, definitions or acceptance. 实现任何业务功能之前使用。
system1-firstUse when handling any business request (query, report, dashboard, business operation, routine task), before reasoning it out from scratch. 收到业务请求准备动手,或想先找注册表里的现成固化能力时使用。
using-livepowersUse when starting any conversation that touches business software, data analysis, transactional systems, ontology, agent product delivery, long-running jobs or multi-agent work, before any response or action. 开始任何企业业务软件 / 数据分析 / 交易系统 / 本体 / 智能体交付 / 长程任务 / 多智能体工作前使用。
/livepowers-core:lp-route对一个业务请求执行 System 1 优先路由(查注册表 → HIT 执行 / MISS 探索并留证据)
"${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"
"${CLAUDE_PLUGIN_ROOT}/hooks/evidence-capture.sh" post-tool
"${CLAUDE_PLUGIN_ROOT}/hooks/evidence-capture.sh" stop
角色包:财务/口径。Role pack for finance: environment scan, ontology evolution, night loops and write-safety.
10 skills
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
角色包:人力/合规。Role pack for HR: digital role specs, auditable agent collaboration and the common method baseline.
8 skills
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.
7 skills
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
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
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
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.