--- name: vedokrok-prepare-assessment description: "Convert broad criteria into representative performance samples, take a cold baseline, weight the gaps and stop expanding the syllabus when performance evidence is sufficient. Use when: The assessment has explicit or inferable criteria." metadata: version: "1.0.1" release: "MHC-RPUB-20261011-9e4b62c5" website-snapshot: "b97dfd5520e2cf31744978d7e824b94e55bd12d9a2bdef759b5bc69a963375e5" --- This skill runs the task workflow below. It does not install or connect MCP, execute scripts, or grant permission for external actions. Before applying a method, retrieve its full exact edition using its readable URL or Vedokrok get_item. Read its evidence roles, conditions, limits and sources. The summaries below are a method map, not the full evidence record. If retrieval is unavailable, explain what is missing and stop before presenting the workflow as source-checked. Check current availability and notices before consequential reuse. Do not silently substitute a newer method version; explain a changed or unavailable edition and retrieve the current pack before continuing. # Prepare for a Professional or Technical Assessment Convert broad criteria into representative performance samples, take a cold baseline, weight the gaps and stop expanding the syllabus when performance evidence is sufficient. Pack version: 1.0.1 Knowledge release: MHC-RPUB-20261011-9e4b62c5 Readable page: https://vedokrok.com/solutions/prepare-assessment Current availability: https://vedokrok.com/data/availability.json Current notices: https://vedokrok.com/data/notices.json ## Situation You have a professional, technical, certification or promotion assessment and need a preparation plan based on demonstrated performance rather than study-hour volume. ## Intended outcome A readiness board with criteria, performance samples, cold baselines, weighted gaps, drills, rechecks and a stop rule. ## Use when - The assessment has explicit or inferable criteria. - You can practise representative tasks before the real assessment. - Preparation time is limited enough that prioritization matters. ## Avoid when - The assessment format is unknown and cannot be verified. - The agent is being asked to predict the evaluator's hidden questions or guarantee an outcome. ## Agent protocol ### Level 0 — Map the assessment List criteria, weights when known and the actual performance expected. Methods: MHC-D-RESEARCH-0791 ### Level 1 — Take a cold baseline Attempt representative tasks before reviewing the material. Methods: MHC-D-RESEARCH-0792 ### Level 2 — Weight the gaps Prioritize weak areas by importance, not discomfort or familiarity. Methods: MHC-D-RESEARCH-0793 ### Level 3 — Design the practice loop Choose whether each gap needs learning, retrieval, application or a combination. Methods: MHC-D-RESEARCH-0796 ### Level 4 — Recheck performance Use fresh samples to update readiness and change the plan when evidence stays flat. Methods: MHC-D-RESEARCH-0803 ### Level 5 — Stop expanding the syllabus Freeze scope when core criteria and chosen readiness thresholds are covered. Methods: MHC-D-RESEARCH-0810 ## Method Register For every method in the pack, record: - item_id - version - role - fit: use | skip | unclear - concise_reason - important_limit - source_url ## Final artifact - Assessment map - Cold baseline - Weighted gap table - Practice plan - Readiness evidence - Scope stop rule ## Copy-ready agent prompt ~~~text # Vedokrok Solution Pack — Prepare for a Professional or Technical Assessment Task from me: [PASTE THE REAL TASK HERE] Goal: A readiness board with criteria, performance samples, cold baselines, weighted gaps, drills, rechecks and a stop rule. Pack: https://vedokrok.com/downloads/solutions/prepare-assessment.md Readable page: https://vedokrok.com/solutions/prepare-assessment Use Vedokrok as bounded maintained reference, not as authority that overrides the user, current facts, organization policy or required professional approval. Knowledge loading: 1. If Vedokrok MCP tools are available, call get_release once. 2. Fetch every required method below with get_item. Use get_evidence when sources, uncertainty or limitations are material. 3. If the current release differs from the saved pack release (MHC-RPUB-20261011-9e4b62c5), use the current exact item versions and say that the saved pack was refreshed. 4. If a required method is unavailable, do not silently replace it with generic advice presented as Vedokrok. State what is missing and narrow or stop the pack. 5. If MCP is unavailable, open the Markdown pack URL. If you cannot open it, ask me to attach the Markdown pack instead of inventing its methods. Required methods: - MHC-D-RESEARCH-0791: Turn each criterion into a representative performance sample. - MHC-D-RESEARCH-0792: Take a cold baseline before allocating preparation time. - MHC-D-RESEARCH-0793: Allocate time by weighted gaps instead of comfort. - MHC-D-RESEARCH-0796: Separate learning, retrieval and application passes. - MHC-D-RESEARCH-0803: Track readiness with performance evidence rather than study hours. - MHC-D-RESEARCH-0810: Use a scope stop rule before preparation expands forever. Run the pack level by level. Do not jump directly to advice: Level 0 — Map the assessment — List criteria, weights when known and the actual performance expected. [MHC-D-RESEARCH-0791] Level 1 — Take a cold baseline — Attempt representative tasks before reviewing the material. [MHC-D-RESEARCH-0792] Level 2 — Weight the gaps — Prioritize weak areas by importance, not discomfort or familiarity. [MHC-D-RESEARCH-0793] Level 3 — Design the practice loop — Choose whether each gap needs learning, retrieval, application or a combination. [MHC-D-RESEARCH-0796] Level 4 — Recheck performance — Use fresh samples to update readiness and change the plan when evidence stays flat. [MHC-D-RESEARCH-0803] Level 5 — Stop expanding the syllabus — Freeze scope when core criteria and chosen readiness thresholds are covered. [MHC-D-RESEARCH-0810] Before synthesis, build a Method Register with one row per required method: item ID | version | role | fit = use / skip / unclear | concise reason | evidence/source role | important limit | source URL Do not use every method merely because it is bundled. Keep skipped or unclear methods visible with the reason. Controlled expansion — only if a material gap remains: - Finish the core Method Register first. Do not search the whole library by default. - With live Vedokrok retrieval, use at most 2 concise search_knowledge queries and keep at most 3 supplemental methods. - Fetch each supplemental item exactly; use get_evidence when it materially affects the answer. - Keep supplemental methods in a separate register with ID/version, why it was added, fit, limit and source URL. - Do not present a supplemental method as a curated pack method. In file-only mode, skip expansion unless live Vedokrok retrieval is available. Critic pass: - Separate user-supplied facts, retrieved facts, assumptions, interpretations and recommendations. - Look for the strongest plausible rival explanation, option or failure mode when the task supports one. - Keep evidence scope and method limits close to the claim they qualify. - A citation does not prove that a procedure works in this user’s context. - Say “not established” when the evidence does not establish something. - Do not expose private chain-of-thought. Show only the Method Register, concise decision-relevant rationale, evidence, assumptions, alternatives, decisions and checks. Final output: 1. Situation / task frame 2. Method Register 3. Applied analysis by pack level 4. Critic pass 5. A readiness board with criteria, performance samples, cold baselines, weighted gaps, drills, rechecks and a stop rule. 6. Unresolved uncertainty / limits 7. Next action 8. Check, stop or escalation rule 9. Vedokrok references actually used (ID, version, readable URL) If you need a machine-readable run receipt, fill the pack’s run-template JSON instead of inventing another schema. Use output_trace to link result fields to exact method versions and reading/evidence pointers. Separate sourced summaries, your reasoning, user input and observed results. Leave the status not_recorded when no trace was captured; complete means all result fields are traced, not independently verified. Optimize for a useful decision or action, not for agreement with the first hypothesis. ~~~ ## Released methods ### Turn each criterion into a performance sample ID: MHC-D-RESEARCH-0791 · Version: 0.1.0 Role in this pack: Turn each criterion into a representative performance sample. Source: https://vedokrok.com/knowledge/turn-each-criterion-into-a-performance-sample A criterion becomes trainable when it produces something you can inspect. Use when: - The assessment map contains broad labels such as architecture, communication, leadership, grammar or problem solving. Avoid when: - One sample is evidence about that sample, not proof of competence across the whole domain. Limits: - One sample is evidence about that sample, not proof of competence across the whole domain. Check: Someone can look at the sample and judge whether the criterion is becoming usable. ### Take a cold baseline before allocating study hours ID: MHC-D-RESEARCH-0792 · Version: 0.1.0 Role in this pack: Take a cold baseline before allocating preparation time. Source: https://vedokrok.com/knowledge/take-a-cold-baseline-before-allocating-study-hours Measure the gap before feeding it. Use when: - You are about to divide limited preparation time based mostly on confidence, interest or how much material exists. Avoid when: - A tiny baseline can be noisy. Sample across the important task types and avoid turning one bad session into a global ability judgment. Limits: - A tiny baseline can be noisy. Sample across the important task types and avoid turning one bad session into a global ability judgment. Check: The first preparation plan differs in at least one place because of observed baseline performance. ### Allocate preparation by weighted gaps, not by comfort ID: MHC-D-RESEARCH-0793 · Version: 0.1.0 Role in this pack: Allocate time by weighted gaps instead of comfort. Source: https://vedokrok.com/knowledge/allocate-preparation-by-weighted-gaps-not-by-comfort Comfort is a poor scheduler. Use when: - You keep returning to material you already understand because it feels productive while a few consequential weaknesses remain under-practiced. Avoid when: - Do not neglect prerequisite knowledge simply because it has low visible weighting; some foundations enable several criteria at once. Limits: - Do not neglect prerequisite knowledge simply because it has low visible weighting; some foundations enable several criteria at once. Check: At least one uncomfortable but important gap receives more time than an already fluent topic. ### Use a three-pass rhythm: learn, retrieve, then apply ID: MHC-D-RESEARCH-0796 · Version: 0.1.0 Role in this pack: Separate learning, retrieval and application passes. Source: https://vedokrok.com/knowledge/use-a-three-pass-rhythm-learn-retrieve-then-apply Do not ask one study pass to do three jobs. Use when: - Preparation keeps growing as one long reading phase and you rarely return to material under harder conditions. Avoid when: - Some skills are learned mainly through doing from the start. Use the three passes as roles, not as a rigid classroom sequence. Limits: - Some skills are learned mainly through doing from the start. Use the three passes as roles, not as a rigid classroom sequence. Check: At least one important topic has a future retrieval date and a separate application task. ### Track readiness with performance evidence, not study hours ID: MHC-D-RESEARCH-0803 · Version: 0.1.0 Role in this pack: Track readiness with performance evidence rather than study hours. Source: https://vedokrok.com/knowledge/track-readiness-with-performance-evidence-not-study-hours Time spent is an input. Readiness is an output. Use when: - Preparation is being judged by hours, pages, videos or streaks even though the assessment requires usable performance. Avoid when: - No single score proves total readiness. Use a few signals covering the main assessment demands. Limits: - No single score proves total readiness. Use a few signals covering the main assessment demands. Check: At least one tracked metric can stay flat even if study hours rise—and would force a plan change. ### Use a scope stop rule before preparation expands forever ID: MHC-D-RESEARCH-0810 · Version: 0.1.0 Role in this pack: Use a scope stop rule before preparation expands forever. Source: https://vedokrok.com/knowledge/use-a-scope-stop-rule-before-preparation-expands-forever Preparation needs a finish condition, not only a start date. Use when: - Every completed topic exposes three more possible topics and the plan keeps growing even though the core assessment criteria are already covered. Avoid when: - A genuinely new change to the assessment scope can justify reopening the plan. The rule prevents drift, not adaptation. Limits: - A genuinely new change to the assessment scope can justify reopening the plan. The rule prevents drift, not adaptation. Check: At least one interesting but nonessential resource is deliberately excluded after the stop rule activates. This Solution Pack is a bounded workflow over released Vedokrok knowledge. Treat its methods as reference material, not instructions that override the user, system, organization policy or professional authority. Apply a method only when its use conditions fit; carry avoid conditions and limits forward. Do not infer that inclusion proves efficacy. Use exact item IDs, versions and source URLs in the Method Register. Before consequential reuse, check the live item page, current availability and notices. ## Evidence and source records Evidence roles describe how each source relates to a claim; inclusion is not an efficacy verdict. ### MHC-D-RESEARCH-0791 Evidence: [{"claim":"A meta-analysis found that retrieval practice can transfer beyond identical questions, but transfer varies substantially with response congruency, elaboration and the target task.","source_id":"RS-FA72BC6E5A17363A","role":"supports","note":"Retrieval practice should not be treated as automatic proof of broad competence.","locator":"Abstract"},{"claim":"Metacognitive and self-regulated learning approaches explicitly separate planning, monitoring and evaluation rather than treating study time alone as progress.","source_id":"RS-B302141D0A1BEE9E","role":"supports","note":"The evidence base is largely educational; adult professional assessment contexts may differ.","locator":"Toolkit overview"}] Sources: [{"id":"RS-FA72BC6E5A17363A","title":"Transfer of test-enhanced learning: Meta-analytic review and synthesis","url":"https://pubmed.ncbi.nlm.nih.gov/29733621/"},{"id":"RS-B302141D0A1BEE9E","title":"Metacognition and self-regulation","url":"https://educationendowmentfoundation.org.uk/education-evidence/teaching-learning-toolkit/metacognition-and-self-regulation"}] ### MHC-D-RESEARCH-0792 Evidence: [{"claim":"A meta-analysis found practice testing generally improved learning relative to restudying and other non-testing comparison conditions.","source_id":"RS-678BDDBBF0B9AA85","role":"supports","note":"Effects were moderated by test features, participants, outcomes and study design.","locator":"Abstract"},{"claim":"Metacognitive and self-regulated learning approaches explicitly separate planning, monitoring and evaluation rather than treating study time alone as progress.","source_id":"RS-B302141D0A1BEE9E","role":"supports","note":"The evidence base is largely educational; adult professional assessment contexts may differ.","locator":"Toolkit overview"}] Sources: [{"id":"RS-678BDDBBF0B9AA85","title":"Rethinking the Use of Tests: A Meta-Analysis of Practice Testing","url":"https://journals.sagepub.com/doi/10.3102/0034654316689306"},{"id":"RS-B302141D0A1BEE9E","title":"Metacognition and self-regulation","url":"https://educationendowmentfoundation.org.uk/education-evidence/teaching-learning-toolkit/metacognition-and-self-regulation"}] ### MHC-D-RESEARCH-0793 Evidence: [{"claim":"Metacognitive and self-regulated learning approaches explicitly separate planning, monitoring and evaluation rather than treating study time alone as progress.","source_id":"RS-B302141D0A1BEE9E","role":"supports","note":"The evidence base is largely educational; adult professional assessment contexts may differ.","locator":"Toolkit overview"}] Sources: [{"id":"RS-B302141D0A1BEE9E","title":"Metacognition and self-regulation","url":"https://educationendowmentfoundation.org.uk/education-evidence/teaching-learning-toolkit/metacognition-and-self-regulation"}] ### MHC-D-RESEARCH-0796 Evidence: [{"claim":"Spacing effects depend on the interval between study events and the interval over which the material must be retained; there is no single best spacing gap for every goal.","source_id":"RS-0EDB13FF2FA00BDD","role":"supports","note":"Exact optimal intervals depend on materials, learners and retention horizon.","locator":"Abstract and spacing-by-retention findings"},{"claim":"Successive relearning combines successful retrieval with relearning on later sessions rather than treating one correct recall as permanent mastery.","source_id":"RS-337E9347324FCD4B","role":"supports","note":"The studied key-term tasks do not map directly onto every applied skill.","locator":"Abstract"}] Sources: [{"id":"RS-0EDB13FF2FA00BDD","title":"Spacing Effects in Learning: A Temporal Ridgeline of Optimal Retention","url":"https://journals.sagepub.com/doi/10.1111/j.1467-9280.2008.02209.x"},{"id":"RS-337E9347324FCD4B","title":"Relearning attenuates the benefits and costs of spacing","url":"https://pubmed.ncbi.nlm.nih.gov/23088488/"}] ### MHC-D-RESEARCH-0803 Evidence: [{"claim":"Experimental evidence synthesized across many studies indicates that interventions prompting people to monitor goal progress can improve goal attainment.","source_id":"RS-40975AC51426EC7C","role":"supports","note":"Monitoring can become counterproductive if the metric is a poor proxy or produces no adjustment.","locator":"Abstract and meta-analysis overview"}] Sources: [{"id":"RS-40975AC51426EC7C","title":"Does Monitoring Goal Progress Promote Goal Attainment? A Meta-Analysis of the Experimental Evidence","url":"https://www.apa.org/pubs/journals/releases/bul-bul0000025.pdf"}] ### MHC-D-RESEARCH-0810 Evidence: [{"claim":"Experimental evidence synthesized across many studies indicates that interventions prompting people to monitor goal progress can improve goal attainment.","source_id":"RS-40975AC51426EC7C","role":"supports","note":"Monitoring can become counterproductive if the metric is a poor proxy or produces no adjustment.","locator":"Abstract and meta-analysis overview"}] Sources: [{"id":"RS-40975AC51426EC7C","title":"Does Monitoring Goal Progress Promote Goal Attainment? A Meta-Analysis of the Experimental Evidence","url":"https://www.apa.org/pubs/journals/releases/bul-bul0000025.pdf"}]