SunflowersLwtech's toolbox: Claude Code skills, agents, commands, and MCP servers in one plugin marketplace
-
Updated
Jul 17, 2026 - Python
SunflowersLwtech's toolbox: Claude Code skills, agents, commands, and MCP servers in one plugin marketplace
How experts think — the open, MIT-licensed collection of SOUL.md files: structured portraits of how experts in every field reason, decide, and work. Human- and AI-readable.
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Rust, Postgres + pgvector.
Practitioner-judgment skill for Claude Code, Codex, and AI agents under ambiguity, trade-offs, and incomplete information.
AI-native 科研工作台。Workbench for AI-native scientific research
A cognitive protocol for AI agents. Makes any LLM-based agent think like an experienced practitioner. Works with Claude Code, Codex, Gemini, and any agent framework.
A Claude skill for when you can see the destination but can't describe the path
经验萃取 Experience Extraction Skill:把高手头脑里的隐性经验,变成可训练、可验证的组织资产
Obtiene el conocimiento tácito generado al documentar los elementos de trabajo en Azure DevOps dentro de una organización y lo transforma en conocimiento explícito
Cross-harness skills for Tribal
A cognitive base that makes AI agents reason from verified foundations instead of inherited conventions. 让 AI agent 从第一性原理出发推理,而不是继承惯例。
The Polanyi stack for AI agents. Convert tacit knowledge, Polanyis paradox, and expert judgment into reusable agents and skills.
Convert tacit expert knowledge into reusable AI agents, skills, and training workflows to scale reliable performance.
删前 Skill:清醒状态下的低防御元认知提取 Skill
🛡️ Application interactive sur l'attrition de l'expertise en environnement BANI. Projet de recherche M2 MAE Cadre - EM Strasbourg / Laboratoire HuManiS.
hack26 is a collaborative hackathon-style event focused on rapidly exploring and prototyping practical data and AI solutions against a defined set of challenges. Teams work within clear challenge boundaries to test ideas, build proof‑of‑concepts and share learning in a short, intensive format.
The team built Jim‑E, an interactive AI‑assisted risk review tool that applies SME heuristics to project risk entries. Using a lightweight Streamlit interface and encoded heuristic rules, the solution helps users identify weak risks and mitigations, capture structured feedback, and generate clear audit‑ready reports.
Hledám funkční řešení v balastu . Moje zkušenosti z off-gridu, dílny, cnc, pobytů v cizině mě naučila že realita je pro mne nejdůležitějším měřítkem. Nástroje které tvořím s pomocí AI slouží k pomyslnému hledání jehly v kupce sena, nyní k datové analýze založené na filtraci vaty a balastu
Accepted manuscript of 'Interpretive Orchestration' (Strategic Organization, 2026) — a framework for human-AI collaboration in interpretive qualitative research
Open-source Python toolkit for capturing expert decision logic as structured, reviewable knowledge cards.
To associate your repository with the tacit-knowledge topic, visit your repo's landing page and select "manage topics."