10 added, 94 removed. Audit A to A.
---
name: creativity
- description: Generate, explore, and develop original but useful possibilities when an ordinary answer would underserve the objective. Use for ideation, reframing, synthesis, invention, adaptation, creative problem-solving, or escaping fixation across writing, strategy, products, research, design, and technical work. Do not invoke for routine variation, factual retrieval, or final evidence adjudication.
+ description: "Generate original ideas or escape fixation."
---
# Creativity
Create possibilities that are meaningfully different, useful for the objective, and honest about evidence. Creativity is a search process: frame the problem, generate varied preinventive material, explore it from several interpretations, develop the strongest candidates, and evaluate only after genuine alternatives exist.
Do not confuse creativity with random novelty, many synonyms, ornamental effects, unsupported claims, or a long unranked list.
+ ## Route generation and convergence
+
+ For a brief reframe, explore distinct mechanisms and develop the result directly. Respect an already selected direction.
+
+ - **Substantial ideation, synthesis, invention, repair or search-heavy planning:** read [concept development](references/concept-development.md) and [creative search methods](references/creative-search-methods.md); use generation/exploration, flexibility/persistence and distinct families.
+ - **Comparing or selecting candidates:** read [convergence protocol](references/convergence-protocol.md) and [selection and validation](references/selection-validation.md); separate generation/ranking, preserve fatal constraints and test decisive uncertainty.
+
+ `critical-thinking` assesses claims; `logical-thinking` determines what follows. Imagined audience reactions are hypotheses, not validation.
+
## Choose the creative task
Identify what kind of change is needed:
- **Reframe:** expose a more productive question, tension, audience, or unit of value.
- **Diverge:** produce distinct solution families before committing.
- **Synthesize:** combine distant but compatible mechanisms into a coherent whole.
- **Transform:** change the representation, sequence, scale, medium, or interaction model.
- **Invent:** create a mechanism, format, or concept not implied by the current defaults.
- **Repair:** escape a stale, generic, overconstrained, or repeatedly failing direction.
Use `creative-direction-divergence` for a formal premium-website art-direction process. Use `cross-domain-creative-divergence` for a formal business or campaign creative brief. Use this skill when the central need is general creative cognition or problem-solving across domains.
## Frame a useful search space
Record:
1. desired outcome and the human or system it serves;
2. the central tension, unmet need, or failure in the obvious answer;
3. fixed constraints versus inherited conventions that may be challenged;
4. the ordinary baseline and the dimensions on which an idea must differ;
5. available assets, evidence, mechanisms, and implementation capacity;
6. what success means beyond novelty;
7. the smallest uncertainty worth exploring first.
Write a compact challenge statement:
```text
Create [outcome] for [audience/context] while honoring [fixed constraints],
without defaulting to [obvious pattern]. A strong direction changes [decisive dimension]
and can be tested by [observable signal].
```
If the initial framing presupposes one solution, restate it in functional terms before generating ideas.
## Control fixation before exposure
Examples can improve fluency while anchoring output to their surface features. When originality matters:
- define functions, constraints, and evaluation dimensions before inspecting examples;
- describe a reference by the mechanism that works, not by its visible styling or wording;
- use multiple structurally different references rather than one dominant exemplar;
- include at least one deliberately distant source domain;
- state which surface features must not be copied;
- generate one candidate before exposure when the task permits;
- test whether the final idea would still exist if the exemplar disappeared.
If the user explicitly requests faithful adaptation or reconstruction, preserve that objective and distinguish required fidelity from creative freedom.
-
- ## Run a generate-explore loop
-
- Do not move directly from prompt to polished answer. Alternate between generation and interpretation.
-
- ### 1. Generate preinventive material
-
- Produce fragments before complete concepts:
-
- - mechanisms, functions, metaphors, tensions, structures, interactions, constraints, proof forms, failure inversions, and unusual combinations;
- - ambiguous fragments that can support more than one interpretation;
- - material from both a flexibility path and a persistence path.
-
- For substantial creative work, read [creative search methods](references/creative-search-methods.md).
-
- ### 2. Explore the material
-
- For each promising fragment, ask:
-
- - What functions could this perform?
- - What else could it represent?
- - Which assumption does it make unnecessary?
- - What changes when scale, order, medium, actor, or time horizon changes?
- - Which distant mechanism has the same underlying structure?
- - What emergent property appears when two fragments interact?
- - Under which constraint does it become more distinctive rather than less feasible?
-
- ### 3. Develop concept families
-
- Build three to six directions with different organizing mechanisms. Each direction needs:
-
- - premise;
- - mechanism or experience;
- - relationship to the objective;
- - distinctive feature that cannot be swapped onto an unrelated task;
- - required assets or conditions;
- - strongest benefit;
- - likely failure mode;
- - smallest useful prototype or test.
-
- A family is not a color, tone, or wording variant. Directions must differ in causal mechanism, information structure, interaction, delivery model, or organizing idea.
-
- ### 4. Branch, combine, or backtrack
-
- Expand a direction when it reveals new functions. Combine candidates only when their mechanisms reinforce one premise. Backtrack when development repeatedly requires excuses, false claims, or unrelated embellishments.
-
- For search-heavy planning or invention, keep a small branch ledger: candidate, promise, unresolved constraint, next experiment, and reason to continue or stop.
-
- ## Use both creative pathways
-
- Creative performance can emerge through flexibility or persistence. Use both deliberately:
-
- - **Flexibility:** switch categories, representations, perspectives, and source domains to cover distant regions of the search space.
- - **Persistence:** stay within a promising region long enough to move beyond the first obvious answers and discover less accessible variants.
-
- Do not switch endlessly when a branch has unexplored depth. Do not persist merely because effort has already been spent. After an initial round, inspect whether the candidates are too similar or too shallow, then choose the missing pathway.
-
- ## Separate generation from evaluation
-
- Premature evaluation suppresses unfamiliar directions; delayed evaluation without a gate produces unusable lists. Use two modes:
-
- 1. **Generative mode:** suspend ranking, preserve ambiguity, and maximize structural variety.
- 2. **Evaluative mode:** apply the same explicit criteria to every developed candidate.
-
- During convergence, read [selection and validation](references/selection-validation.md).
-
- Evaluate:
-
- - relevance and usefulness;
- - originality relative to the actual baseline;
- - coherence of parts around one premise;
- - feasibility, asset burden, and operational fit;
- - credibility and evidence burden;
- - distinctiveness and memorability;
- - extensibility beyond one impressive moment;
- - accessibility, reversibility, downside, and testability where relevant.
-
- Use a weighted comparison only when the decision warrants it. Scores expose tradeoffs; they do not create objective truth. A fatal constraint cannot be averaged away by high novelty.
-
- ## Stress-test the leading direction
-
- Run the checks that can materially change selection:
-
- - **Substitution:** could this be transferred to an unrelated task with only noun changes?
- - **Mechanism:** does the novel element advance the outcome or merely attract attention?
- - **Fixation:** does it reproduce a reference's surface while claiming originality?
- - **Coherence:** does every major part reinforce the organizing premise?
- - **Reality:** can available proof, technology, assets, time, and skill support it?
- - **Reduction:** does it survive a simpler, cheaper, mobile, accessible, or reduced-motion form when those constraints apply?
- - **Evidence:** did invention become a factual claim without support?
- - **Counterconcept:** is there a simpler rival that achieves the value with less burden?
-
- Use `critical-thinking` to test material claims and assumptions. Use `logical-thinking` to determine what the evidence warrants. Use external feedback, prototypes, or runtime tests when practical; imagined audience reactions are hypotheses, not validation.
## Stop and deliver
Stop when the search has covered genuinely different mechanisms, the leading direction survives the material constraints, further variants repeat existing families, and the next uncertainty is better resolved by a prototype or evidence than more ideation.
Match the output to the user's need:
- for exploration, present a curated set of distinct developed directions;
- for a decision, lead with the selected direction, why it wins, its sacrifice, and its smallest test;
- for implementation, translate the concept into concrete requirements while preserving its organizing mechanism;
- for an unresolved search, name the competing directions and the observation that would discriminate them.
Label invention, analogy, assumption, inspiration, and verified fact separately. Do not expose private scratch reasoning; show the useful creative structure and result.