#4 · practical · score 50Choose one narrow learning theme for the week, define one visible result for Friday, and complete at least one small practice rep on each day you work on it.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description · start-here-anchor · gold-20-candidate
#13 · reviewed · score 80Choose a small set of material you want to retain. Hide the source and answer a question, explain the idea, or write what you remember. Check immediately enough to catch errors and repair them. Then, if success means solving, writing, speaking, calculating, or performing, practice that outcome too. Memory practice is useful; it is not a teleportation device to skill.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description · gold-20-candidate
#14 · reviewed · score 80When you finish a focused memory-heavy learning episode, put aside the material and spend a brief period awake in a quiet, low-stimulation setting. Avoid immediately switching to another cognitively demanding task. Choose a duration that is practical for you, then return to normal activity. Do not use the pause as a substitute for self-testing, active review, or other learning methods.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description · gold-20-candidate
#15 · practical · score 50Pick one narrow language task, such as reviewing a few phrases, listening to a short clip, reading a small passage, or recording a brief spoken answer. Practice for a short session and finish with one note about what to revisit next.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description · gold-20-candidate
#27 · reviewed · score 80Provide only information you are allowed to share, plus the customer question and approved policy or knowledge source. Ask for a concise draft. Check that it answers the real issue, does not invent policy or status, and gives the correct next action before sending.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#32 · reviewed · score 80Write your objective, constraints, and current leading option. Ask AI for materially different alternatives, missing criteria, and the strongest case against your favorite. Verify any external facts, then compare options using your own criteria and downside limits. Do not ask the model to hide the trade-off inside a single confident recommendation.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#36 · reviewed · score 80State the problem and constraints. Ask for several directions that must differ from one another in a named way. Cluster similar answers, discard obvious filler, and evaluate the remaining options against real constraints and evidence.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#40 · reviewed · score 80Provide only material you are permitted to share. Ask for a summary with sections, explicit uncertainties, and source locations when available. Mark the claims that affect your decision, then open the source and verify those claims directly before reusing them.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#43 · reviewed · score 80Choose a small sample containing easy, ordinary, and awkward cases. Define what counts as acceptable before running the model. Compare AI output with the source or a trusted human result, record failure patterns, and decide which cases can be assisted, which need review, and which should stay human-first.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#47 · reviewed · score 80Name the skill you are actually trying to acquire. Attempt a problem, explanation, translation, derivation, or answer unaided. Ask AI to identify gaps, give a contrasting example, or explain one sticking point. Check the feedback against trusted material when accuracy matters, then perform a fresh attempt without AI.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#48 · reviewed · score 80Provide the audience, goal, source facts, must-include points, and constraints. Ask for one draft. Compare it with the source material, remove invented details, restore your own judgment and voice, and send only the version you can defend without the model in the room.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#53 · reviewed · score 80Choose a small set of questions that point to information you genuinely want to learn. Before opening the explanation, reading the chapter, or watching the lesson, make a brief attempt at each answer even if you are unsure. Then study normally, paying attention when the material resolves those questions. Afterward, check the answers against the source. Use this to target important information, not as a claim that every unasked detail will also be learned better.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#56 · reviewed · score 80Define the behavior and constraints first. Ask AI for a small implementation. Read the diff, run the existing test suite, add tests for edge cases and failure paths, and inspect security or data-handling implications. Keep only code you can explain and maintain.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#57 · reviewed · score 80Study a manageable chunk, then look away from the explanation and produce a brief self-explanation: what the idea means, why a step follows, how it connects to what you already know, or when it would apply. Compare your explanation with the source, identify one gap or error, and revise it. Use the prompts that fit the material; do not turn every paragraph into a compulsory monologue.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#59 · reviewed · score 80Choose one set of verbal material and decide how long you need to retain it. Split the planned repetitions across at least two sessions separated by time. Use a longer gap when the required retention period is longer, then check final recall and adjust the next schedule instead of treating one interval as universally optimal.
source-reviewed · source-linked · topic-mapped · has-check-in · clear-action · clear-description
#72 · practical · score 50Explain why you are asking and get permission. Ask the person to walk through the most recent relevant example. Use one question at a time about sequence, context, tools, decisions and uncertainty. Summarize what you heard and invite correction.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#76 · practical · score 50To stay sharp: - Take notes: Write down key points from the person speaking before you. - Breathe and listen: Avoid rehearsing your own response while someone else is speaking. - Repeat mentally: After someone speaks, quickly repeat their main point in your head. Example: In a team meeting, note what the person before you says and reference it when it’s your turn.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#77 · practical · score 50State the goal, your opening, and relevant context without unnecessary private detail. Ask AI to play a neutral, skeptical, and confused counterpart. Practise responding with facts, boundaries, and questions. Write one shorter opening after the rehearsal and use that in the real conversation if it still fits.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#78 · practical · score 50Map the report consumer, source data, transformations and delivery step. Define validation rules for schema, completeness, freshness and key totals. Build a small automated path with logging and a visible failure state, keep a manual fallback, and stop publication when validation fails.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#79 · practical · score 50Notice that you are defending rather than examining. Pause before replying. Restate the other person's claim in words they accept, then state your own position and uncertainty. Ask what information would change either view. Choose one concrete check, or stop when the exchange is no longer productive or safe.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#80 · practical · score 50Define the scenario and desired outcome, write the core request or response, add likely follow-up phrases and one repair phrase for misunderstanding, rehearse both sides aloud, use the interaction when appropriate, and update the phrase set from the point where you hesitated or needed clarification.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#81 · practical · score 50Choose one frequent task, walk through it slowly, note every unnecessary reach, obstruction, visibility issue, cable move, device swap, or reset, rank the friction points, change one reversible layout variable, use the task again, and keep or undo the change based on what became easier or harder.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#83 · practical · score 50Describe the plan without sensitive information, ask an AI for plausible ways it could fail, group the suggestions, verify the important ones yourself, and choose mitigations only for risks that survive the check.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#84 · practical · score 50When predicting trends: - Ask yourself: "Could there be sudden changes or breaks in this trend?" - Prepare for shifts: Always consider outliers and unexpected events in planning. - Look for weak signals: Early signs of change can help you adapt quickly. Example: A stock steadily rising? Plan for a downturn just as much as for continued growth.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#85 · practical · score 50Describe the next event and the recent streak. Ask what carries information or state from earlier outcomes into the next one. If there is no connection, ignore the streak and use the same probability or decision rule. If a connection may exist, identify the relevant state and gather that information. Use a pre-defined stop rule for repeated high-cost decisions.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#86 · practical · score 50State the unwanted outcome, map the main parts and interactions, write the trade-off as two requirements that appear to conflict, generate separation or redesign options, choose a reversible check, and record which assumption or constraint changed.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#89 · practical · score 50Write three to six criteria that describe a good result. Give the model the draft and rubric, ask for evidence from the draft for each criticism, and request no rewrite on the first pass. Triage the feedback, then make the changes you agree with.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#90 · practical · score 50Define the columns and allowed values before extraction. Ask the model to return null rather than guess, preserve a source snippet or locator for each row, and flag ambiguous cases. Check a random sample plus all high-impact rows against the original text before using the result downstream.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#91 · practical · score 50Describe the intended behavior, constraints, known happy path, and expensive failures. Ask for boundary cases, invalid inputs, state transitions, concurrency or timing issues where relevant, and user misunderstandings. Remove duplicates, verify each candidate against the real system, and write tests for the cases worth keeping.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#92 · practical · score 50When interacting with others: - Ask: "What’s unique about this person’s perspective or experience?" - Listen actively: Avoid projecting your own traits or beliefs onto them. - Reflect: Notice when you assume similarities without evidence and correct yourself. Example: Don’t assume a coworker has the same work style as you; ask about their preferences and needs.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#93 · practical · score 50Choose one behavior or output. Record only what you could point to or reproduce. Write the human-like interpretation you first considered, then add a system-specific alternative and one low-risk way to check between them. Keep uncertainty visible when you cannot check.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#94 · practical · score 50State the question and population you want to understand. Record how cases entered the analysis, which cases were excluded or missing and whether selection depends on the outcome. Compare the conclusion with a broader view or label it as applying only to the selected group. Write what additional data would change the conclusion.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#97 · practical · score 50List the viable options, write two to four constraints that are genuinely relevant to this decision, eliminate only options that clearly fail a constraint, inspect what remains for missing information and trade-offs, then choose the next reversible test or decision step.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#99 · practical · score 50State the intended outcome and the current decision. Ask one focused question such as what is unclear, what assumption looks wrong or what should change first. Choose a reviewer who can judge that question, then record what you will accept, test, discuss, defer or ignore.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description
#100 · practical · score 50Choose an artifact or environment where errors matter, write a short checklist from known failure modes, inspect once for completeness and once from a different perspective such as data consistency or user flow, record anomalies, fix them, and update the checklist when a new recurring miss appears.
trusted-practical · topic-mapped · has-check-in · clear-action · clear-description