core-refineryFind the core that runs through everything — the ideas that survive across all your sources.
Install via ClawdBot CLI:
clawdbot install leegitw/core-refineryGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/live-neon/skills/tree/main/pbd/core-refineryAudited Apr 17, 2026 · audit v1.0
Generated Apr 1, 2026
Analyze multiple industry reports, competitor analyses, and customer feedback to identify core market trends and customer pain points that consistently appear across sources. This helps businesses focus on validated opportunities rather than noise.
Synthesize principles from 3 or more research papers or textbooks in a field to distill invariant theories or methodologies. This aids researchers in identifying foundational concepts for further study or teaching.
Refine ideas from user interviews, design documents, and technical specifications to find core features that align across all sources. This ensures product teams build essentials that meet universal needs.
Compare regulations, case law, and internal policies across multiple jurisdictions to identify invariant compliance principles. This helps organizations establish robust, cross-border frameworks.
Synthesize themes from audience surveys, competitor content, and performance metrics to determine core messaging that resonates universally. This optimizes marketing efforts for consistency and impact.
Offer the skill as part of a cloud-based AI platform with tiered pricing based on usage volume or source count. Revenue comes from monthly subscriptions for businesses needing regular synthesis of documents or data streams.
Provide custom synthesis projects for clients in industries like research or legal, using the skill to deliver reports on core principles. Revenue is generated through project-based fees or retainer agreements.
License the skill for integration into internal knowledge management systems of large organizations. Revenue comes from one-time licensing fees or annual support contracts for ongoing use.
💬 Integration Tip
Ensure input sources are pre-processed for consistency in format and domain relevance to maximize accuracy of invariant detection and avoid mixing incompatible data.
Scored Jun 25, 2026
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
Seven-stage deep research pipeline for substantive research questions. Activates when user asks for deep research, 深度研究, research report, evidence-backed inv...
Perform deep research using Claude by autonomously gathering, analyzing, and synthesizing detailed information across diverse topics on request.
全生命周期质量保障专家,覆盖需求、设计、编码、测试、上线、运维全阶段的质量保障活动。 融合缺陷预防(逆向操作、依赖踏空、并发冲突、新旧兼容、状态迁移、因果判定)与质量度量、持续改进三大支柱, 帮助团队建立「预防-评审-度量-改进」的质量闭环,实现软件质量的持续提升。 Use when: - 需求/设计/编码/测试...
专家团自动组建技能(反面教材)。核心观点:AI只认事不认人,没必要模拟人类多角色协作方式。本技能演示为什么不需要这样做——AI应该直接面对任务,而不是模拟人类团队。触发词:组建专家团、专家协作、团队完成任务、自动组建团队、expert team、专家团、团队协作完成任务。