# AI for L&D and Corporate Training: 30 Claude Skills to Build Training That Changes Work AI for L&D and corporate training: 30 free Claude skills to build training programs, from needs analysis and e-learning to facilitator guides and evaluation. - Page: https://lantern.meet-polar-bear.com/skills/ai-for-training-pack - Download: https://lantern.meet-polar-bear.com/skills/ai-for-training-pack.zip - Source: https://github.com/polar-bear-org/claude-skills/tree/main/packs/ai-for-training-pack - Price: free ## Install in Claude Code ``` /plugin marketplace add polar-bear-org/claude-skills /plugin install ai-for-training-pack@polar-bear-skills ``` ## The 30 skills you get The set follows the work, in eight stages: finding the real need, getting it out of the experts, designing the programme, building the materials, delivering it live, making it stick, proving what changed, and running the L&D desk. ### 1 · Find the real need - **Training Request Intake** — use when: “We need a training by Friday” lands with the answer already chosen. Output: The intake questions, the business problem in one line, an “is it training?” triage, and a reply to the requester. - **Performance Gap Analysis** — use when: The manager, process or tools may be the cause, not a skill gap. Output: Desired versus actual performance, a cause table that separates skill and knowledge from information, tools, incentives and process, the non-training options, and a recommendation. - **Training Needs Assessment** — use when: You need what a team actually lacks, not a yearly wish list. Output: Needs by role and task with the evidence for each, a priority table, and a clear split of what training can and cannot fix. - **Action Map** — use when: The sponsor wants a course and you need “they will do”, not “they should know”. Output: One measurable goal, the observable actions, why they are not happening, the practice activities, and the minimum information people need. ### 2 · Get it out of the experts - **SME Interview Guide** — use when: The expert gives you the standard workflow but solves real cases by intuition. Output: An incident-based interview plan, then the notes structured into decision points, a common-mistakes list, exceptions and scenario seeds. - **Content Triage** — use when: The SME says learners need to know everything and sends the whole slide deck. Output: A must-do, must-know, look-up and cut table, the job aid candidates, and a cut list with reasons the SME can accept. - **SME Review Plan** — use when: Six departments review one course and the revisions never end. Output: Who reviews what at each gate, one named decider, the rounds and dates, a feedback log, and a change rule for late requests. ### 3 · Design the programme - **Learning Objectives** — use when: The only objective is “understand the topic”. Output: Observable verbs at the right Bloom's level, a condition and a criterion for each objective, and rewrites of “awareness only” goals. - **Instructional Design Document** — use when: Nobody sees the design decisions behind a course. Output: The audience and need, the strategy, practice and a check per objective, the evaluation, every design decision with its rationale, and a sign-off block. - **Curriculum Map** — use when: A programme has grown module by module and nothing connects. Output: Modules by objective, activity, check and format — live, e-learning, on the job — a sequence from simpler to harder whole tasks, and a learning path. ### 4 · Build the materials - **Scenario-Based Learning** — use when: People finished every module and still cannot make the call on the job. Output: Decision scenarios drawn from real mistakes, branches with their consequences, and feedback for every choice. - **E-Learning Storyboard** — use when: The build starts from slides and ends as a knowledge dump with voiceover. Output: Screen-by-screen text, visuals, interactions and narration, accessibility notes, and the objective each screen serves. - **Knowledge Check** — use when: An AI can answer your quiz from a screenshot and it proves nothing. Output: Scenario questions per objective, distractors built from real mistakes, feedback for every option, and low-stakes retake rules. - **Job Aid** — use when: People need the answer mid-task, not a 30-minute module. Output: A checklist, decision table or one-page flow, where it lives in the workflow, and who updates it and when. - **AI Content QA Checklist** — use when: AI drafted the course, AI reviewed it, and no human checked it teaches anything. Output: Accuracy traced to an approved source, objective alignment, accessibility checks, a myth and bias scan, the update owner, and the SME sign-off record. ### 5 · Deliver it live - **Session Plan** — use when: A virtual session competes with email and chat from minute one. Output: A timed flow — open, recall, show, practise, apply — activities and materials per segment, and a scripted first five minutes. - **Facilitator Guide** — use when: Trainers are told to read the SOP aloud from slides. Output: Cues and key points per segment, questions to ask with what a good answer sounds like, activity setup instructions, timing flex, and what-if notes. - **Role-Play Training** — use when: People sit through role-play, meet real customers, and you hope it stuck. Output: Learning points, role cards, a good and a poor model example, observer notes that go only to the learner, and debrief questions. - **Train-the-Trainer Kit** — use when: The programme depends on facilitators who each need to learn it first. Output: A teach-back plan, practice rounds that rise in difficulty, delivery notes per module, and a readiness conversation guide with no score. ### 6 · Make it stick - **70-20-10 Plan** — use when: The programme is all classroom and nothing happens back at work. Output: On-the-job assignments, coaching and peer learning, and the formal pieces, for a role or a programme. - **Spaced Repetition Plan** — use when: People forget a 60-minute course within weeks. Output: Retrieval prompts at widening gaps, 5-minute micro-units, and the schedule and channel. - **Manager Follow-Up Kit** — use when: Learners go back to a manager who never asks what they learned. Output: Before and after conversation guides, the first on-the-job task, check-in dates, and a barrier log. - **Onboarding Training Plan** — use when: Ramp-up drags on and stakeholders blame the talent. Output: A week-by-week learning path, the real tasks a new hire must handle, buddy sessions, and sign-off by doing the task with a person. ### 7 · Prove what changed - **Kirkpatrick Evaluation Plan** — use when: Leadership sees a high completion rate and moves on. Output: The targeted Level 4 result and its leading indicators, the critical behaviours and required drivers, the Level 2 and Level 1 checks, and a data source, owner and date for every measure. - **Training Evaluation Form** — use when: The smile sheet says everyone loved it and tells you nothing. Output: Questions on relevance, confidence to apply and after-training support, open prompts on barriers, and an aggregate summary that rates the programme, never the trainer. - **Success Case Study** — use when: You need evidence of use on the job, not more survey scores. Output: A short survey on where the training was used and where it stalled, an interview guide for volunteers, anonymous case write-ups with evidence, and a barrier list across cases. - **Training ROI Estimate** — use when: The budget holder asks what the programme returned. Output: The benefits and how the programme's effect was isolated, the money conversion with a source for every value, the full costs, and a conservative ROI range with caveats and intangibles. ### 8 · Run the L&D desk - **Training Plan** — use when: One person must build two programmes at once. Output: Programmes ranked against business goals, a capacity and budget check, a quarterly calendar, and a not-this-year list. - **ADDIE Project Plan** — use when: The brief lands Thursday and the programme is due Monday. Output: Phases with deliverables and owners, review gates, durations from your own past projects, SAM iterations where they fit, and a scope line for the deadline. - **Compliance Training** — use when: Compliance is a box to tick and quiz records are kept as evidence against people. Output: The few decisions that matter per rule, scenario checks with feedback, a refresh cadence, and a record-use statement, with legal points marked “check with a qualified adviser”. ## Workflows - **Find the real need** (Someone asked for a course by Friday.) Training Request Intake → Performance Gap Analysis → Action Map - **Get it out of the experts** (The know-how is in an expert's head, or in a slide deck.) SME Interview Guide → Content Triage → Learning Objectives → Instructional Design Document → Curriculum Map - **Build the materials** (The design is signed off and the materials come next.) Scenario-Based Learning → E-Learning Storyboard → Knowledge Check → Job Aid → AI Content QA Checklist - **Deliver it live** (It has to work in a room.) Session Plan → Facilitator Guide - **Make it stick** (The session is over and people are back at work.) 70-20-10 Plan → Spaced Repetition Plan → Manager Follow-Up Kit - **Prove what changed** (Plan it before launch, so you know what to look for.) Kirkpatrick Evaluation Plan → Training Evaluation Form → Success Case Study → Training ROI Estimate ## The quality bar - Every skill asks what you have first, and works from a minimum when you have little, marking the result as a first draft - Every method is named and attributed to its originator through a public source, and its real mechanics drive the steps - Every output has a fixed shape and ends with the decision a named person makes, and by when - No invented numbers: thresholds, costs and targets stay as [placeholders] until you set them - Needs are analysed at role and task level, never by rating named people, and survey results are reported in aggregate with small groups suppressed - Legal, regulatory and accessibility-compliance points are marked “check with a qualified adviser”, never stated as advice - The red line: Claude drafts the learning and an expert signs it off — people learn by practising with other people, and no quiz, survey or role-play is ever used to grade, rank or build a case against a person ## Questions people ask ### What is in the AI for L&D and Corporate Training pack? 30 Claude skills that follow the L&D job in eight stages: find the real need, get it out of the experts, design, build, deliver, make it stick, prove what changed, and run the L&D desk. Each skill is one named method or one artifact. ### How do I install these Claude skills? In Claude Code, two lines install all 30 at once. In Claude.ai or Claude Desktop, download the zip, open Settings, Skills, Add, and upload the skills you want. Either way it takes about five minutes. ### Do I need Claude Code to use them? No. The skills work in Claude.ai, Claude Desktop and Claude Code. In the app you upload them yourself; in Claude Code one command installs the whole pack. ### Do the skills work with ChatGPT or other assistants? They are built as Claude Skills, and installing them is a Claude feature. Each one is a plain Markdown file, so you can read it and reuse the method elsewhere, but it will not load and trigger by itself outside Claude. ### Will the quizzes be used to grade people? No. Claude drafts the learning and an expert signs it off. People learn by practising with other people, and no quiz, survey or role-play is ever used to grade, rank or build a case against a person. ### Is the pack free? Yes. It is free to use inside your company and in client work, and not for resale. There is no signup: the download and the install command are on this page. ## About Written by Polar Bear (https://meet-polar-bear.com/). Published on Lantern (https://lantern.meet-polar-bear.com/), which turns your notes, documents and call transcripts into social post drafts you review and publish.