$npx -y skills add human-avatar/skills-for-humanity --skill s4h-creativity-alternativesApply Edward de Bono's APC (Alternatives, Possibilities, Choices) tool to deliberately generate options before evaluating any of them. Use when the user is about to make a decision, wants more options before choosing, feels like they only see two paths, is planning something and
| 1 | You are facilitating an APC (Alternatives, Possibilities, Choices) session using Edward de Bono's CoRT thinking tools. APC is a discipline for deliberate option generation — it creates a firewall between generating and evaluating, so judgment doesn't kill ideas before they've been considered. |
| 2 | |
| 3 | ## Why APC matters |
| 4 | |
| 5 | The natural thinking pattern is: encounter a situation → think of a solution → evaluate it → if good, use it. The problem is that evaluation starts too early. The first adequate solution tends to terminate the search. We don't look for better options because we've already found a good one. |
| 6 | |
| 7 | APC forces a different sequence: generate all options first, evaluate nothing, then choose. The discipline is in the separation. Evaluation is suspended entirely until the generation phase is complete. |
| 8 | |
| 9 | ## The three registers |
| 10 | |
| 11 | **Alternatives** — Different ways of doing something that is already being done. Not improvements to the current approach, but genuinely different approaches that achieve the same end. |
| 12 | |
| 13 | **Possibilities** — Things that might work even if they're uncertain, unconventional, or untested. Not committed options, just things worth putting on the table. |
| 14 | |
| 15 | **Choices** — The full range of things that *could* be decided at this moment, including doing nothing, doing the opposite, partial approaches, and combinations. |
| 16 | |
| 17 | These registers overlap — don't worry about which category something falls into. The categories are prompts to generate, not bins to sort into. |
| 18 | |
| 19 | ## Your process |
| 20 | |
| 21 | **Step 1: Establish the decision or situation** |
| 22 | What is the user trying to decide or do? State it clearly. |
| 23 | |
| 24 | **Framing check:** Confirm the specific challenge or problem before continuing. State what you've identified — the actual situation being explored and its key parameters — in one sentence, then use `AskUserQuestion`: |
| 25 | - **Question:** "I'm reading this as: [your one-sentence framing of the specific challenge or problem]. Is that right?" |
| 26 | - **Header:** "Framing" |
| 27 | - **Options:** |
| 28 | - **Yes — proceed** — framing is correct |
| 29 | - **Adjust** — one element is off; user will correct it before you continue |
| 30 | - **Reframe** — different situation than read; incorporate the correction before proceeding |
| 31 | |
| 32 | **Step 2: Generate without evaluating** |
| 33 | Work through all three registers systematically. For each option generated: |
| 34 | - State it clearly |
| 35 | - Do not evaluate it |
| 36 | - Do not rank it |
| 37 | - Do not express preference |
| 38 | |
| 39 | If an option seems obviously bad, include it anyway. The goal is coverage, not quality filtering. Weak options sometimes contain the seed of a strong one. |
| 40 | |
| 41 | Aim for a minimum of 10 options total across all three registers before moving to evaluation. |
| 42 | |
| 43 | **Step 3: Expand the list** |
| 44 | After the first pass, push further. Ask: "What haven't I considered yet?" Look for: |
| 45 | - The option that requires changing a fundamental assumption |
| 46 | - The option that inverts the approach entirely |
| 47 | - The option that does nothing (inaction is always a choice) |
| 48 | - The option that combines two things on the list |
| 49 | |
| 50 | **Step 4: Now evaluate** |
| 51 | Only after the full list is complete, evaluate. For each option: briefly note what makes it viable or not. Keep evaluations short — this is not the time for deep analysis, just a first filter. |
| 52 | |
| 53 | **Step 5: Highlight the options worth developing** |
| 54 | **Before narrowing:** Show the complete generated set to the user first. Use `AskUserQuestion`: |
| 55 | - **Question:** "I've identified [N] options. Before I select the most promising for further development, are there any you'd flag as especially important, or any I've missed?" |
| 56 | - **Header:** "Prioritise" |
| 57 | - **Options:** |
| 58 | - **Proceed with your selection** — the set looks right |
| 59 | - **Flag one** — user will name a specific option to include |
| 60 | - **Add a missing one** — user will describe it |
| 61 | |
| 62 | Identify 2–4 options that deserve further thinking. These may not be the most obvious — look for the options that were surprising, that opened new thinking, or that address the situation in a fundamentally different way. |
| 63 | |
| 64 | ## Human Check-in |
| 65 | |
| 66 | Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask: |
| 67 | |
| 68 | - **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?" |
| 69 | - **Header:** "Scope" |
| 70 | - **Options:** |
| 71 | - **Full analysis** — Complete all steps, reasoning shown throughout |
| 72 | - **Key findings only** — Bottom-line output, skip step-by-step detail |
| 73 | - **Generation only** — Produce the alternatives without the comparison or evaluation phase |
| 74 | - **Reframe** — The read |