[{"data":1,"prerenderedAt":608},["ShallowReactive",2],{"page:index-navigation":3,"home:service-page:footer":9,"page:help-pages":244,"page:service-page":268,"technical-blog-page-content":314,"technical-blog-post-building-and-maintaining-an-ai-resource-library":341,"technical-blog-author-building-and-maintaining-an-ai-resource-library":581},{"helpBlocks":4},[5,6,7,8],"advice","projects","people","support",{"groupedServices":10},[11],{"title":12,"groups":13},"Services",[14,55,96,135,172,208],{"title":15,"slug":16,"icon":17,"subtitle":18,"services":19},"Strategy","strategy","lucide:compass","Shaping AI and digital transformation strategies that help organisations prioritise investment, define practical roadmaps, strengthen governance, and build the operating models needed to adopt change with confidence.",[20,27,34,41,48],{"slug":21,"title":22,"subtitle":23,"description":24,"image":25,"icon":26},"ai-digital-strategy","AI & Digital Strategy","Supporting organisations through AI adoption and digital transformation","Assessing where AI and digital can deliver the greatest value, building the business case for investment and developing a prioritised roadmap grounded in what your organisation can deliver at pace and at scale.","\u002Fimg\u002Fservice-page\u002Fgen-ai.jpg","lucide:sparkles",{"slug":28,"title":29,"subtitle":30,"description":31,"image":32,"icon":33},"ai-digital-delivery","AI & Digital Delivery","Delivering strategic roadmaps to for digital and AI-enabled change","Providing the engineering, data science and AI capability needed to take complex AI and digital programmes from validated strategy through to successful delivery, for organisations that need both the technical depth and the delivery structure to execute consistently.","\u002Fimg\u002Fservice-page\u002Freporting.jpg","lucide:map",{"slug":35,"title":36,"subtitle":37,"description":38,"image":39,"icon":40},"ai-native-operating-models","AI Native Operating Models","Designing operating models that embed AI into teams, services and delivery","Designing and delivering AI-native operating model transformations across organisational structure, processes, workforce and technology, combining hands-on AI delivery experience with consulting expertise to deliver transformations focused on operational reality.","\u002Fimg\u002Fservice-page\u002Fcloud-design.jpg","lucide:building-2",{"slug":42,"title":43,"subtitle":44,"description":45,"image":46,"icon":47},"ai-data-maturity","AI & Data Maturity","Assessing organisational readiness and capability across AI and data","Delivering independent, evidence-based assessments of AI and data capability across people, process, technology and governance, identifying the most significant capability gaps and building a structured, prioritised plan to address them.","\u002Fimg\u002Fservice-page\u002Fanalytics.jpg","lucide:bar-chart-3",{"slug":49,"title":50,"subtitle":51,"description":52,"image":53,"icon":54},"governance-risk-security","Governance, Risk & Security","Establishing controls and frameworks for responsible, secure AI adoption","Helping organisations manage governance, risk and security across AI and digital programmes, from establishing AI governance frameworks and responsible AI policies to regulatory compliance and cyber security advisory.","\u002Fimg\u002Fservice-page\u002Fcloud-security.jpg","lucide:shield-check",{"title":56,"slug":57,"icon":58,"subtitle":59,"services":60},"Engineering","engineering","lucide:cog","Building large-scale, complex software platforms - from enterprise legacy modernisation, to greenfield projects, we deliver solutions that automate, streamline and simplify processes, meeting the needs of today and the future.",[61,68,75,82,89],{"slug":62,"title":63,"subtitle":64,"description":65,"image":66,"icon":67},"software-development-company-uk","Software Development","Engineering complex, mission critical software platforms","Designing and delivering large-scale, complex software platforms for enterprise and public sector organisations across industries, from initial discovery and design through to deployment and long-term support.","\u002Fimg\u002Fservice-page\u002Fsoftware-development.jpg","lucide:code",{"slug":69,"title":70,"subtitle":71,"description":72,"image":73,"icon":74},"ai-assisted-engineering","AI-Assisted Engineering","Accelerating software delivery with AI-enabled engineering practices","Embedding AI tools and practices across engineering teams to accelerate delivery, improve code quality and build lasting AI capability, from AI-assisted code generation and review to AI-powered testing and deployment automation.","\u002Fimg\u002Fservice-page\u002Fai-assisted-software-development.jpg","lucide:cpu",{"slug":76,"title":77,"subtitle":78,"description":79,"image":80,"icon":81},"systems-integration","Systems Integration","Integrating systems to operate as a single framework","Connecting core business systems so they operate as a single, coherent framework, covering ERP, CRM, finance and reporting platforms, with real-time data accuracy and the audit trails needed to manage complex enterprise environments reliably.","\u002Fimg\u002Fservice-page\u002Fsystem-intergration.jpg","lucide:git-merge",{"slug":83,"title":84,"subtitle":85,"description":86,"image":87,"icon":88},"mobile-development","Mobile Development","Delivering performant, scalable and robust user-driven mobile applications","Delivering performant, scalable and user-driven mobile applications for enterprise and public sector organisations, from cross-platform apps and PWAs to native iOS and Android solutions built for complex operational environments.","\u002Fimg\u002Fservice-page\u002Fmobile-development.jpg","lucide:smartphone",{"slug":90,"title":91,"subtitle":92,"description":93,"image":94,"icon":95},"front-end-development-company","Front End Development","Building intuitive and scalable user-focused digital experiences","Designing and building intuitive, accessible and performant front end applications, from UX strategy and prototyping through to full delivery, for organisations where digital experience is central to how they serve customers and teams.","\u002Fimg\u002Fservice-page\u002Ffront-end-software-development.jpg","lucide:layout",{"title":97,"slug":98,"icon":99,"subtitle":100,"services":101},"Testing","testing","lucide:check-circle","Helping organisations assure quality across platforms, products and services - from defining test approaches to automating validation, performance assurance and security-focused testing.",[102,108,115,122,129],{"slug":103,"title":104,"subtitle":105,"description":106,"image":32,"icon":107},"testing-strategy","Test Strategy","Defining scalable test approaches aligned to delivery goals and risk","Defining, auditing and improving software testing strategies for enterprise and public sector organisations, covering functional and non-functional testing, automation, tooling and team capability in a single coherent framework.","lucide:clipboard-check",{"slug":109,"title":110,"subtitle":111,"description":112,"image":113,"icon":114},"automated-testing","Automated Testing","Building automated test suites to improve quality, speed and confidence","Designing and delivering automated testing frameworks across end-to-end, API and performance testing, built around your technology stack and embedded directly into delivery pipelines for reliable, maintainable coverage at pace.","\u002Fimg\u002Fservice-page\u002Fdevops.jpg","lucide:bot",{"slug":116,"title":117,"subtitle":118,"description":119,"image":120,"icon":121},"performance-load-testing","Performance & Load Testing","Validating system performance, resilience and scalability under demand","Validating system performance under real-world demand for organisations where reliability, scalability and speed are business-critical, from pre-release testing and bottleneck identification through to continuous performance testing in delivery pipelines.","\u002Fimg\u002Fservice-page\u002Fcloud-native.jpg","lucide:gauge",{"slug":123,"title":124,"subtitle":125,"description":126,"image":127,"icon":128},"ai-testing-and-validation","AI Testing & Validation","Testing AI systems for quality, safety, reliability and expected outcomes","Validating AI models and systems across accuracy, reliability and deployment readiness, from pre-deployment model evaluation and independent AI assurance through to production monitoring and LLM red teaming.","\u002Fimg\u002Fservice-page\u002Fprototype.jpg","lucide:flask-conical",{"slug":130,"title":131,"subtitle":132,"description":133,"image":53,"icon":134},"security-testing","Security Testing","Identifying vulnerabilities and strengthening confidence in system security","Identifying and addressing security vulnerabilities across software systems, infrastructure, development practices and AI systems, covering penetration testing, threat modelling, vulnerability assessment and LLM red teaming.","lucide:shield",{"title":136,"slug":137,"icon":138,"subtitle":139,"services":140},"Data","data","lucide:database","Turning data into a valuable asset - from building centralised data platforms to delivering clear, accessible reporting and analytics, we enable teams to make faster, more informed decisions based on trusted data.",[141,146,152,159,165],{"slug":142,"title":143,"subtitle":144,"description":145,"image":32,"icon":47},"data-visualisation-consultancy","Data Visualisation & Reporting","Delivering custom reporting for data-driven decision making","Designing and delivering interactive dashboards, custom reports and real-time analytics aligned to your KPIs, giving operational and strategic teams the visibility they need to make informed, data-driven decisions.",{"slug":147,"title":148,"subtitle":149,"description":150,"image":46,"icon":151},"data-analytics-company","Data Analytics","Uncovering actionable insights for data-driven transformation","Analysing large-scale, complex datasets to surface trends, correlations and forecasts that inform decisions across sales, supply chain, operations and strategic planning, from predictive analytics to big data analysis.","lucide:line-chart",{"slug":153,"title":154,"subtitle":155,"description":156,"image":157,"icon":158},"data-migration-services","Data Migration","Delivering large migrations across architectures and environments","Delivering large-scale, complex data migrations across cloud, database and application systems, ensuring data is clean, accurate and reliable throughout transition with no disruption to operations or loss of data fidelity.","\u002Fimg\u002Fservice-page\u002Fmigration.jpg","lucide:database-backup",{"slug":160,"title":161,"subtitle":162,"description":163,"image":164,"icon":138},"data-engineering-services","Data Engineering","Engineering pipelines to consolidate, process and aggregate data","Building the scalable data pipelines, storage architectures and integration frameworks that consolidate, process and aggregate data across the organisation, providing the foundations for effective analytics and decision making.","\u002Fimg\u002Fservice-page\u002Fdata-engineering.jpg",{"slug":166,"title":167,"subtitle":168,"description":169,"image":170,"icon":171},"data-platform-consulting","Enterprise Data Products","Designing, delivering and optimising enterprise data platforms to provide unified data foundations","Designing, implementing and optimising enterprise data platforms using Snowflake, Databricks and Apache Spark, delivering unified, governed data foundations that support analytics, self-service insights and AI capability at scale.","\u002Fimg\u002Fservice-page\u002Fenterprise-data-products.jpg","lucide:layers",{"title":173,"slug":174,"icon":175,"subtitle":176,"services":177},"AI","ai","lucide:brain","Guiding organisations through the practical application of AI - from early experimentation to production-grade systems, we create solutions that improve services and enable organisations to make decisions better, faster and at scale.",[178,183,190,195,202],{"slug":179,"title":180,"subtitle":181,"description":182,"image":127,"icon":128},"ai-consultancy","Prototypes and PoCs","Validating AI opportunities through rapid experimentation and prototyping","Validating AI concepts through rapid prototyping and proof of concept delivery across language and conversation, vision and detection, and prediction and optimisation use cases, helping organisations de-risk AI investment before committing to full development.",{"slug":184,"title":185,"subtitle":186,"description":187,"image":188,"icon":189},"ai-machine-learning-company","Production AI","Designing and delivering production-ready AI solutions at scale","Taking validated AI models into production for enterprise and public sector organisations, addressing model performance, integration, MLOps and ongoing monitoring to ensure AI systems perform consistently in live environments over the long term.","\u002Fimg\u002Fservice-page\u002Fconcept-to-delivery.jpg","lucide:rocket",{"slug":191,"title":192,"subtitle":193,"description":194,"image":25,"icon":114},"agentic-ai","Agentic AI","Building agent-based AI systems that can reason, act and automate","Building, running and supporting agentic AI systems for enterprise and public sector organisations, executing multi-step workflows, coordinating across systems and completing complex tasks with minimal human intervention.",{"slug":196,"title":197,"subtitle":198,"description":199,"image":200,"icon":201},"ai-machine-learning-operations-consulting","AI Cloud Platforms\u002FServices","Providing platforms and services to build, deploy and scale trusted AI","Building, deploying and scaling AI solutions across Azure, AWS and Google Cloud, from developing solutions using pre-built APIs and managed AI services through to foundation model customisation and cloud AI optimisation.","\u002Fimg\u002Fservice-page\u002Fai-cloud.jpg","lucide:cloud-cog",{"slug":203,"title":204,"subtitle":205,"description":206,"image":207,"icon":175},"ai-machine-learning-consulting","Data Science and ML","Building data science and machine learning solutions tailored to real-world challenges","Delivering data science and machine learning solutions for enterprise and public sector organisations across forecasting and prediction, insight and discovery, and optimisation and recommendation use cases.","\u002Fimg\u002Fservice-page\u002Fml.jpg",{"title":209,"slug":210,"icon":211,"subtitle":212,"services":213},"Cloud","cloud","lucide:cloud","Supporting organisations in building secure, scalable cloud environments - whether migrating systems, modernising platforms, or optimising existing infrastructure, we focus on delivering cloud solutions that improve performance, resilience, and cost-efficiency.",[214,220,227,233,239],{"slug":215,"title":216,"subtitle":217,"description":218,"image":39,"icon":219},"cloud-architecture-consulting","Cloud Architecture & Design","Designing cloud solutions optimised for resilience and scale","Designing and architecting robust, scalable cloud solutions across public and hybrid cloud environments, from cloud strategy and planning through to implementation and ongoing optimisation, using Well-Architected Frameworks and infrastructure-as-code techniques.","lucide:network",{"slug":221,"title":222,"subtitle":223,"description":224,"image":225,"icon":226},"cloud-migration-consulting","Cloud Adoption & Migration","Migrating to cloud infrastructures to enhance accessibility, performance and scalability","Delivering seamless migration of systems, data and workloads to optimal cloud platforms with minimal disruption to operations, across Azure, AWS and Google Cloud, from initial assessment and adoption planning through to post-migration optimisation and support.","\u002Fimg\u002Fservice-page\u002Fcloud-adoption.jpg","lucide:cloud-upload",{"slug":228,"title":229,"subtitle":230,"description":231,"image":120,"icon":232},"cloud-application-development","Cloud Native Solutions","Building scalable and resilient cloud native solutions rapidly","Designing and building highly scalable, resilient cloud native applications that fully harness the advantages of dynamic cloud environments, from microservices architecture and containerisation through to automated CI\u002FCD pipelines and continuous delivery.","lucide:boxes",{"slug":234,"title":235,"subtitle":236,"description":237,"image":113,"icon":238},"devops-consulting-services","DevOps & Pipelines","Embedding automation through DevOps for continuous integration, delivery and deployment","Transforming how software is delivered and released through optimised CI\u002FCD pipelines, infrastructure-as-code and DevOps culture, enabling teams to ship updates frequently, reliably and at pace across complex enterprise and public sector programmes.","lucide:workflow",{"slug":240,"title":241,"subtitle":242,"description":243,"image":53,"icon":54},"cloud-security-consulting","Cloud Security","Securing cloud environments through architecture, automation and optimisation","Securing cloud environments and workloads through risk-based security architecture, automated controls and continuous monitoring, helping organisations adopt cloud securely while meeting compliance obligations across Azure, AWS and Google Cloud.",[245,250,256,262],{"path":246,"title":247,"blockDescription":248,"icon":74,"bgColour":249},"\u002Fhelp\u002Fadvice","Advise","Offering strategic advice, technology consultancy and support on end-to-end digital transformation.","#1174d6",{"path":251,"title":252,"blockDescription":253,"icon":254,"bgColour":255},"\u002Fhelp\u002Fpeople","Collaborate","Augment your internal teams with skilled, experienced specialists to accelerate delivery and reduce risk.","lucide:users","#F4743B",{"path":257,"title":258,"blockDescription":259,"icon":260,"bgColour":261},"\u002Fhelp\u002Fprojects","Deliver","Combining domain and technology expertise to build digital products and services at speed and scale.","lucide:kanban-square","#348d69",{"path":263,"title":264,"blockDescription":265,"icon":266,"bgColour":267},"\u002Fhelp\u002Fsupport","Maintain","Managed support and hosting services to keep business-critical platforms secure, resilient and scalable.","mdi:gauge","#A93F55",{"groupedServices":269},[270],{"title":12,"groups":271},[272,279,286,293,300,307],{"title":15,"slug":16,"icon":17,"subtitle":18,"services":273},[274,275,276,277,278],{"slug":21,"title":22,"subtitle":23,"description":24,"image":25,"icon":26},{"slug":28,"title":29,"subtitle":30,"description":31,"image":32,"icon":33},{"slug":35,"title":36,"subtitle":37,"description":38,"image":39,"icon":40},{"slug":42,"title":43,"subtitle":44,"description":45,"image":46,"icon":47},{"slug":49,"title":50,"subtitle":51,"description":52,"image":53,"icon":54},{"title":56,"slug":57,"icon":58,"subtitle":59,"services":280},[281,282,283,284,285],{"slug":62,"title":63,"subtitle":64,"description":65,"image":66,"icon":67},{"slug":69,"title":70,"subtitle":71,"description":72,"image":73,"icon":74},{"slug":76,"title":77,"subtitle":78,"description":79,"image":80,"icon":81},{"slug":83,"title":84,"subtitle":85,"description":86,"image":87,"icon":88},{"slug":90,"title":91,"subtitle":92,"description":93,"image":94,"icon":95},{"title":97,"slug":98,"icon":99,"subtitle":100,"services":287},[288,289,290,291,292],{"slug":103,"title":104,"subtitle":105,"description":106,"image":32,"icon":107},{"slug":109,"title":110,"subtitle":111,"description":112,"image":113,"icon":114},{"slug":116,"title":117,"subtitle":118,"description":119,"image":120,"icon":121},{"slug":123,"title":124,"subtitle":125,"description":126,"image":127,"icon":128},{"slug":130,"title":131,"subtitle":132,"description":133,"image":53,"icon":134},{"title":136,"slug":137,"icon":138,"subtitle":139,"services":294},[295,296,297,298,299],{"slug":142,"title":143,"subtitle":144,"description":145,"image":32,"icon":47},{"slug":147,"title":148,"subtitle":149,"description":150,"image":46,"icon":151},{"slug":153,"title":154,"subtitle":155,"description":156,"image":157,"icon":158},{"slug":160,"title":161,"subtitle":162,"description":163,"image":164,"icon":138},{"slug":166,"title":167,"subtitle":168,"description":169,"image":170,"icon":171},{"title":173,"slug":174,"icon":175,"subtitle":176,"services":301},[302,303,304,305,306],{"slug":179,"title":180,"subtitle":181,"description":182,"image":127,"icon":128},{"slug":184,"title":185,"subtitle":186,"description":187,"image":188,"icon":189},{"slug":191,"title":192,"subtitle":193,"description":194,"image":25,"icon":114},{"slug":196,"title":197,"subtitle":198,"description":199,"image":200,"icon":201},{"slug":203,"title":204,"subtitle":205,"description":206,"image":207,"icon":175},{"title":209,"slug":210,"icon":211,"subtitle":212,"services":308},[309,310,311,312,313],{"slug":215,"title":216,"subtitle":217,"description":218,"image":39,"icon":219},{"slug":221,"title":222,"subtitle":223,"description":224,"image":225,"icon":226},{"slug":228,"title":229,"subtitle":230,"description":231,"image":120,"icon":232},{"slug":234,"title":235,"subtitle":236,"description":237,"image":113,"icon":238},{"slug":240,"title":241,"subtitle":242,"description":243,"image":53,"icon":54},{"id":315,"title":316,"author":317,"blogTags":317,"body":318,"customExcerpt":317,"date":317,"description":322,"excerpt":317,"extension":325,"h1":326,"image":317,"meta":327,"navigation":328,"path":329,"readingStats":330,"seo":335,"stem":339,"__hash__":340},"technicalBlogPage\u002Ftechnical-blog-page.md","Technical Blog Page",null,{"type":319,"value":320,"toc":321},"minimark",[],{"title":322,"searchDepth":323,"depth":323,"links":324},"",2,[],"md","Technical insights, stories and opinions from our team of consultants, analysts, developers and testers.",{},true,"\u002Ftechnical-blog-page",{"text":331,"minutes":332,"time":333,"words":334},"1 min read",0.29,17400,58,{"title":336,"description":337,"keywords":338},"Technology Insights | Audacia Digital Transformation","Technical insights, stories and opinions from leading software development company Audacia's teams of consultants, analysts, developers and testers.","Digital transformation technology, Technology blog, Technology insights, software development blog, software engineering blog","technical-blog-page","XD1gWfEur9Mu64WptQ5pF-e7Ej60LGiq7sRC58wOAeQ",{"id":342,"title":343,"author":322,"authors":344,"blogTags":347,"body":348,"customExcerpt":563,"date":564,"description":353,"excerpt":317,"extension":325,"h1":317,"image":565,"isDraft":566,"meta":567,"navigation":328,"path":568,"readingStats":569,"seo":574,"stem":579,"__hash__":580},"technicalBlog\u002Ftechnical-blog\u002Fbuilding-and-maintaining-an-ai-resource-library.md","Building, Maintaining and Sharing an AI Resource Library",[345,346],"harry-turner-burns","edward-carr",[173],{"type":319,"value":349,"toc":551},[350,354,357,362,365,368,372,375,379,382,390,397,403,437,443,447,450,453,456,459,462,465,468,475,479,482,485,488,492,495,504,508,511,514,517,521,524,527,530,533,537,540,543,546,549],[351,352,353],"p",{},"AI coding tools are now part of most development workflows. The problem is that the work of making them useful tends to happen individually. Someone figures out how to do something well, moves to the next project, and that knowledge disappears with them. At Audacia, we built a shared library to fix that. What started a year ago as a prompt library has grown into a centralised place where prompts, agent configurations, skills, hooks and MCP server guidance live, ready for anyone in the organisation to find and use.",[351,355,356],{},"This post covers what the library contains, how we decide what type of resource to reach for, what it takes to make the contents discoverable, and whether the ongoing effort is worth it.",[358,359,361],"h2",{"id":360},"what-is-an-ai-resource-library","What is an AI resource library?",[351,363,364],{},"An AI resource library is a centralised, shared repository where prompts, agent configurations, skills, hooks and instructions are collected, organised and made available for others to use. Rather than living in a developer's local files or a chat window, that work is stored somewhere the whole team can find it, contribute to it and build on it over time.",[351,366,367],{},"Ours started as a prompt library. It now also holds agent instruction files, skills, hooks and MCP server configuration, because those turned out to be the other things worth sharing, or that people were writing once and losing.",[358,369,371],{"id":370},"why-individual-ai-tooling-doesnt-scale","Why individual AI tooling doesn't scale",[351,373,374],{},"Getting the most out of AI coding tools is a time-intensive exercise that relies on multiple rounds of iteration and fine-tuning, whether that’s refining a prompt, configuring an agent or writing a skill. When every developer does that work privately, the team doesn’t benefit from it. Someone writes a useful prompt for generating mock data to a particular schema, moves to the next project and it’s lost and someone else solves the same problem from scratch months later. The same happens with agent configurations, skills and hooks. Getting the most out of these tools means treating them with the same discipline already afforded to code, documentation and standards.",[358,376,378],{"id":377},"what-does-an-ai-resource-library-contain","What does an AI resource library contain?",[351,380,381],{},"The contents will vary depending on the organisation. It's important to assess the tools being used in your organisation and meet people where they are. Ours ended up with the following categories, expanding beyond just prompts:",[351,383,384],{},[385,386],"img",{"alt":387,"src":388,"title":389},"AI Resource Library Hierarchy; Concepts: Agent Files, AI Project Onboarding, Hooks, MCP Servers, Skills; SDLC: Architecture & Design, Code Understanding, Feature Development, Project Setup, Requirements; Other Disciplines: Marketing, Consultancy","\u002Fimg\u002Ftechnical-blog\u002FAI%20Resource%20library.jpg","AI Resource Library Layout",[351,391,392,396],{},[393,394,395],"strong",{},"Concepts:"," Foundational guidance on working with AI assistants. This is where the explanatory material lives: what agent instruction files, hooks, skills and MCP server configurations are, how each one works and when to reach for it. The MCP pages also signpost the vetted servers, so developers aren’t evaluating every available option themselves.",[351,398,399,402],{},[393,400,401],{},"Software Development Lifecycle:"," The section that has grown fastest, and the one most people now go to first.",[404,405,406,413,419,425,431],"ul",{},[407,408,409,412],"li",{},[393,410,411],{},"Architecture & Design",", for the work you commit to before any code exists: solution and API design, data design, integration and security design, impact assessment, decision records and diagrams.",[407,414,415,418],{},[393,416,417],{},"Code Understanding",", for building context in unfamiliar code: execution flow tracing, UI action flow tracing, dependency mapping, pattern extraction and impact mapping.",[407,420,421,424],{},[393,422,423],{},"Feature Development",", one page per implementation task: API endpoints, UI components, domain logic, migrations, integrations, feature toggles and configuration.",[407,426,427,430],{},[393,428,429],{},"Project Setup",", for scaffolding a new repository.",[407,432,433,436],{},[393,434,435],{},"Requirements",", for instructions for turning PBIs and their acceptance criteria into the artefacts the team needs to deliver and verify them.",[351,438,439,442],{},[393,440,441],{},"Other disciplines:"," The library isn't limited to engineering. Sections exist for other teams across the business, covering prompts relevant to their workflows.",[358,444,446],{"id":445},"prompts-skills-agents-or-hooks-how-do-you-decide","Prompts, skills, agents or hooks: how do you decide?",[351,448,449],{},"The original version of this library held prompts, and the only real decision was whether something was a prompt or an agent configuration. There are now five options, and matching the option to the job is important.",[351,451,452],{},"A prompt is something you invoke deliberately to run at a specific moment for a specific task. A good example is a prompt for generating faker data for a test suite. You trigger it when you need it, it asks any clarifying questions and it produces the output.",[351,454,455],{},"An agent instruction file (AGENTS.md, or CLAUDE.md for Claude Code) holds the facts that are true for every task in a repository: the build and test commands, the definition of done, the rules that shouldn’t change. It loads on every turn, which makes it the highest-leverage file in the repository. Keeping this accurate means the per-task prompts stay short.",[351,457,458],{},"A skill is a folder of instructions the agent loads only when the task in front of it matches. It's where a procedure or process goes. Because the agent only reads the name and description up front, a skill costs almost nothing until it's needed, which is why the Software Development Lifecycle section is built from them. It also means the agent can reach for one without the developer knowing it exists, so a new joiner asking \"how do I add an endpoint here?\" gets the team's procedure without being told to ask for it.",[351,460,461],{},"A hook is a command the tool itself runs at a lifecycle point, such as after a file edit or before a shell command. Instructions are guidance the model may or may not follow on a given turn; a hook is enforcement. If a rule genuinely must hold every time (formatter applied, protected files never touched), it belongs in a hook.",[351,463,464],{},"An MCP server gives the agent access to data or systems outside the repository, and a subagent handles work that should run in its own context and report back.",[351,466,467],{},"Two questions settle most cases. Is it a fact or a procedure? A fact that shapes every task belongs in the instruction file; a procedure that applies to one kind of task belongs in a skill. Does it need the model's judgement? If the requirement is that something happens whether the model agrees or not, that's a hook.",[351,469,470],{},[385,471],{"alt":472,"src":473,"title":474},"A flowchart guiding decision-makers through whether something is an Agent Instruction file, a Skill or a Hook - based on whether it's a fact or a procedure, and whether it need the model's judgement.","\u002Fimg\u002Ftechnical-blog\u002FPrompt%20Library-1.jpg","Flowchart - Agent, Skill or Hook?",[358,476,478],{"id":477},"what-makes-a-good-prompt-or-skill","What makes a good prompt or skill?",[351,480,481],{},"Regarding prompts, the most important part is precision; specific, directive instructions produce more reliable results than vague instructions. If a prompt isn't doing what you want, the fix is almost always to be more explicit about what you're asking for, not to adjust anything else.",[351,483,484],{},"Skills have a second thing to watch. A skill that never fires is normally failing at discovery: perfectly good instructions the agent never loads, because the description didn't match the way someone phrased the request. Write the description for matching rather than for people. Say what it does and, explicitly, when to use it, including the words someone would type.",[351,486,487],{},"Beyond that, prompts, skills and hooks should go through the same review process as code. Ours are added to the library via pull request, which means they're reviewed before they're merged. As a rule, we encourage people submitting to the library to ask a specialist in that area to review the output. This matters more for skills and hooks than for prompts, because both run on everyone's machine once merged, and a hook runs with the developer's own permissions.",[358,489,491],{"id":490},"how-do-you-get-people-to-know-the-library-exists","How do you get people to know the library exists?",[351,493,494],{},"Internal awareness is the first hurdle. To introduce the library and answer questions, a lunchtime session was run as part of the technical community, with follow-up announcements through the technical newsletter and internal channels. Getting it in front of people once isn't enough, it needs to come up repeatedly before it becomes something people reach for naturally.",[351,496,497,498,503],{},"The library has also been embedded into the places developers already go. It now sits alongside our ",[499,500,502],"a",{"href":501},"\u002Ftechnical-blog\u002Fbuilding-a-tech-radar-a-practical-guide-for-technology-leaders","tech radar",", technical newsletter, engineering standards and project delivery standards as part of a centralised technical knowledge base. When someone is looking for guidance on how to approach a task, the library is in the same place as everything else they’d reach for.",[358,505,507],{"id":506},"how-do-you-make-the-contents-discoverable","How do you make the contents discoverable?",[351,509,510],{},"Awareness of the library is important, but it doesn’t guarantee individuals automatically reach for what’s in it. There are a few ways we’ve approached making sure the library’s contents surface when they’re relevant.",[351,512,513],{},"The most direct is a one-line pointer in a project's own AGENTS.md, such as \"to add an endpoint, use the implement-api-endpoint skill\". It tells the agent the skill exists, and it tells the next developer to open the file as well.",[351,515,516],{},"Frontmatter descriptions work differently but towards the same goal. Each skill and custom agent in Claude Code has a short description that Claude reads to decide whether to invoke it automatically. A security reviewer agent described as “use when modifying authentication logic or reviewing security-sensitive code” is more likely to be picked up at the right moment than one described vaguely as “reviews code for security issues.” The description also tells a developer browsing the library when to invoke something manually.",[358,518,520],{"id":519},"how-do-you-get-people-to-contribute","How do you get people to contribute?",[351,522,523],{},"Shared resources tend to stall unless contributing to them feels easy and worth doing. The most common concern raised was time. Writing something that works takes iteration and generalising it for the library is an added step on top.",[351,525,526],{},"The answer we landed on is to contribute as you go. If something has worked well on a project - a prompt, a skill, an agent configuration - take five minutes at the end to make it generic before you move on. Remove the project-specific context, make the variables explicit and add it to the library. It not only benefits the wider organisation, but you can also use it again on different projects or use cases.",[351,528,529],{},"To help with the genericising step, you can use an LLM directly: paste in what you’ve written and ask it to rewrite it as a reusable, context-neutral template. It's a fast step and produces something immediately usable by others.",[351,531,532],{},"The library also needs clear scope. Contributors should know what belongs in it and what doesn't, and how to structure an addition. Ours does this with a naming convention (*.prompt.md, *.instructions.md, *.agent.md, and a .skill folder for skills), a guidance page in every directory explaining when to use what's in it, and a placeholder syntax for the values a user is expected to replace. Without that, you get inconsistency and then people stop trusting it.",[358,534,536],{"id":535},"is-it-worth-the-effort","Is it worth the effort?",[351,538,539],{},"An AI resources library needs ongoing maintenance and updates. One reason is that model behaviour changes between versions. For example, a prompt written six months ago for one model may produce noticeably different results on a newer one. Tracking when each resource was last updated, and which model it was written for, gives a user the context they need to spot that it that might be drifting. Tooling is also changing rapidly - hooks, skills and MCP all arrived after we started the library, and each one changed what belonged in the library.",[351,541,542],{},"There's a related decision worth making early: whether the library is tied to one tool or not. Teams rarely standardise on a single agent, so ours documents each concept once and then covers where Claude Code, GitHub Copilot and Codex differ. That costs a little on every page and saves rewriting the library each time someone adopts something new.",[351,544,545],{},"On the other hand, the infrastructure required is minimal: version-controlled markdown files, a contribution process built on top of the existing PR workflow, and some structure around what goes where.",[351,547,548],{},"What you get in return is compounding: resources improve over time, onboarding is faster because the guidance exists, and the team stops solving and re-solving the same problems independently. It won't fix everything about how your team uses AI tooling, but it's one of the more concrete things you can do to raise the baseline.",[358,550],{"id":322},{"title":322,"searchDepth":323,"depth":323,"links":552},[553,554,555,556,557,558,559,560,561,562],{"id":360,"depth":323,"text":361},{"id":370,"depth":323,"text":371},{"id":377,"depth":323,"text":378},{"id":445,"depth":323,"text":446},{"id":477,"depth":323,"text":478},{"id":490,"depth":323,"text":491},{"id":506,"depth":323,"text":507},{"id":519,"depth":323,"text":520},{"id":535,"depth":323,"text":536},{"id":322,"depth":323,"text":322},"AI coding tools are now part of most development workflows. The problem is that the work of making them useful - refining a prompt, writing a skill, configuring an agent - tends to happen individually. At Audacia, we built a shared AI resource library to fix that. This post covers what the library contains, what it takes to make the contents discoverable, and whether the ongoing effort is worth it.","2026-11-18T16:22:00","\u002Fimg\u002Ftechnical-blog\u002FPrompt Library Cover.jpg",false,{},"\u002Ftechnical-blog\u002Fbuilding-and-maintaining-an-ai-resource-library",{"text":570,"minutes":571,"time":572,"words":573},"11 min read",10.975,658500,2195,{"title":575,"description":576,"image":322,"keywords":577,"noindex":566,"nofollow":566,"jsonSchema":578},"Building, Maintaining and Sharing an AI Resource Library | Audacia","AI consultancy Audacia explores how a shared AI resource library stops work being lost, and what it takes to build and maintain one.","prompt library, AI resource library, shared AI resources, AI coding tools, Claude Code skills, agent configuration, AI development workflow, how to build an AI resource library, agent instruction files, skills and hooks AI, how to organise AI prompts",[],"technical-blog\u002Fbuilding-and-maintaining-an-ai-resource-library","iFkqy1F56UmVBA31Y-2Hr7Foy602A9fAn_kYDsjV9Cs",[582,595],{"id":583,"title":584,"bio":585,"extension":325,"image":586,"meta":587,"role":592,"stem":593,"__hash__":594,"personPath":-1},"author\u002Fauthors\u002Fharry-turner-burns.md","Harry Turner-Burns","Harry is a Senior Software Engineer at Audacia, where he helps design and build complex software platforms for enterprise organisations. Outside of client projects, he has contributed to standardising Audacia’s approach to AI, including the tools used across the business.","\u002Fimg\u002Fauthors\u002FHeadshot - Harry TB.png",{"body":588},{"type":319,"value":589,"toc":590},[],{"title":322,"searchDepth":323,"depth":323,"links":591},[],"Senior Software Engineer","authors\u002Fharry-turner-burns","z-HpuRpOTZhrVOUdPeOKuvzztOr6m5Z6s7XN5J94mfU",{"id":596,"title":597,"bio":598,"extension":325,"image":599,"meta":600,"role":605,"stem":606,"__hash__":607,"personPath":-1},"author\u002Fauthors\u002Fedward-carr.md","Edward Carr","Eddie is a Principal Software Engineer at Audacia, leading the design and delivery of large-scale, business-critical software platforms. He also plays a key role in shaping technical approaches across projects including Audacia's approach to AI.","\u002Fimg\u002Fauthors\u002FEddie.png",{"body":601},{"type":319,"value":602,"toc":603},[],{"title":322,"searchDepth":323,"depth":323,"links":604},[],"Principal Software Engineer","authors\u002Fedward-carr","TaaeWylWf39G6ro1LHBdwNfZXOTe4cMDkXwXzkS9254",1795020355873]