skills/constraint-based-creativity/SKILL.md
Turns limitations into creative fuel by strategically imposing constraints that force novel thinking, break habitual patterns, and reveal unexpected solutions. Covers resource constraints (budget/time/tools), format constraints (length/medium), rule-based constraints, and perspective constraints. Use when brainstorming feels stuck or generates obvious ideas, working with limited resources, designing with specific limitations, or when user mentions "think outside the box", "we're stuck", "same old ideas", "tight constraints", or "limited budget/time".
npx skillsauth add lyndonkl/claude constraint-based-creativityInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Deliberately limiting freedom (resources, rules, materials, format) paradoxically boosts creativity by reducing decision paralysis, breaking habitual patterns, forcing novel combinations, and creating memorable differentiation.
Quick example: Twitter's original 140-character limit forced concise, punchy writing. Haiku's 5-7-5 syllable structure produces poetry. $10K budget forces guerrilla marketing over Super Bowl ads. Building with only CSS (no images) creates distinctive visual style.
Copy this checklist and track your progress:
Constraint-Based Creativity Progress:
- [ ] Step 1: Understand the problem and context
- [ ] Step 2: Choose or design strategic constraints
- [ ] Step 3: Generate ideas within constraints
- [ ] Step 4: Evaluate and refine solutions
- [ ] Step 5: Validate quality and deliver
Step 1: Understand the problem and context
Ask user for the creative challenge (what needs solving), current state (what's been tried, why it's not working), ideal outcome (success criteria), and any existing constraints (real limitations already in place). Understanding why ideas feel stale or stuck helps identify which constraints will unlock creativity. See Constraint Types for strategic options.
Step 2: Choose or design strategic constraints
If user has existing constraints (tight budget, short timeline, limited materials) → Use resources/template.md to work within them creatively. If no constraints exist and ideation is stuck → Study resources/methodology.md to design strategic constraints that force new thinking patterns. Choose 1-3 constraints maximum to avoid over-constraining.
Step 3: Generate ideas within constraints
Apply chosen constraints rigorously during ideation. Create constraint-based-creativity.md file documenting: problem statement, active constraints (what's forbidden/required/limited), idea generation process, and all ideas produced (including "failed" attempts that revealed insights). Quantity matters - aim for 20+ ideas before evaluating. See resources/template.md for structured generation process.
Step 4: Evaluate and refine solutions
Assess ideas using dual criteria: (1) Does it satisfy all constraints? (2) Does it solve the original problem? Select strongest 2-3 ideas. Refine by combining elements, removing unnecessary complexity, and strengthening the constraint-driven insight. Document why certain ideas stand out - often the constraint reveals an unexpected angle. See resources/methodology.md for evaluation frameworks.
Step 5: Validate quality and deliver
Self-assess using resources/evaluators/rubric_constraint_based_creativity.json. Verify: constraints were genuinely respected (not bent/broken), solutions are novel (not slight variations of existing), the constraint created the creativity (solution wouldn't exist without it), ideas are actionable (not just conceptual), and creative insight is explained (why this constraint unlocked this idea). Minimum standard: Average score ≥ 3.5. Present completed constraint-based-creativity.md file highlighting the constraint-driven breakthroughs.
Strategic constraints fall into categories. Choose based on what pattern you want to break:
Resource Constraints (force efficiency):
Format/Medium Constraints (force adaptation):
Rule-Based Constraints (force creative workarounds):
Technical Constraints (force optimization):
Audience/Perspective Constraints (force reframing):
Pattern: The Limitation Sprint When team is stuck, run 30-minute sprints with different constraints. Example: "10 ideas using only free tools" → "10 ideas in black/white only" → "10 ideas for $100 budget." Constraint rotation prevents pattern fixation.
Pattern: The Subtraction Game Remove assumed "essentials" one at a time. Example: "App without login" → "App without UI" (voice only) → "App without internet" (offline-first). Forces questioning assumptions.
Pattern: The Format Flip Change medium to force different thinking. Example: "Explain strategy as a recipe" or "Present roadmap as a movie trailer" or "Write documentation as a children's book."
Pattern: The Resource Inversion Make the assumed limitation the focus. Example: "We have no budget" → "Build guerrilla marketing campaign showcasing zero-budget creativity" or "Only 2-person team" → "Sell the 'small team, big care' advantage."
Pattern: The Historical Constraint Impose constraints from different eras. Example: "Design this as if it's 1995" (pre-smartphone) or "Build this with Victorian-era materials" or "Market this like 1960s Mad Men."
✓ Do:
✗ Don't:
Resources:
resources/template.md - Structured process for generating ideas within constraintsresources/methodology.md - Advanced techniques for designing strategic constraints, combining constraint types, and systematic explorationresources/examples/ - Worked examples showing constraint-driven breakthroughsresources/evaluators/rubric_constraint_based_creativity.json - Quality assessment before deliveryWhen to choose which resource:
Expected deliverable:
constraint-based-creativity.md file containing: problem statement, chosen constraints with rationale, idea generation process (including volume metrics), top 2-3 solutions with refinement notes, explanation of how constraints drove creativity, and next steps.
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.