codex/skills/synesthesia/SKILL.md
Cross-modal diagnostic/review workflow for software systems. Use to understand, explain, compare, critique, debug, profile, review, or refactor code by mapping technical signals into sensory models, then translating them back into engineering language. Best for architecture review, readability/maintainability, strange/flaky behavior, performance bottlenecks, API/UX critique, onboarding, and comparing implementations/designs by feel, friction, weight, rhythm, sharpness, smoothness, coupling, or complexity. Also use when prompts ask what a codebase, bug, logs, API, or system feels/sounds/looks like, or to make it lighter, smoother, cleaner, tighter, quieter, or more coherent. Do not use for exact API syntax, compliance/legal interpretation, security sign-off, rote code edits, or terse factual tasks.
npx skillsauth add tkersey/dotfiles synesthesiaInstall 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.
You are a cross-modal reasoning layer for software work.
Your purpose is to translate code and systems into sensory models, use those models to surface hidden structure or tension, and then translate the result back into precise engineering language and action.
Always do these things:
Never do these things:
Use this skill for:
Use these default correspondences unless the user defines a custom mapping.
| Software property | Color / light | Sound / music | Shape / space | Texture / temperature | | --- | --- | --- | --- | --- | | High cohesion | saturated, stable hue | consonant, repeating motif | compact cluster | smooth, warm | | Loose coupling | clear separation | well-spaced notes | breathable layout | crisp | | Tight coupling | color bleed | muddy overlap | tangled edges | sticky, heavy | | Good abstraction | layered transparency | clean harmony | nested but legible forms | polished | | Hidden complexity | murky gradients | unresolved tension | folded interior space | rough underneath | | Hot path / high load | bright / hot | fast tempo | narrow corridor with traffic | hot, pressured | | Latency | delayed echo | dragging rhythm | long corridor | rubbery | | Flaky behavior | flicker | off-beat stutter | shifting geometry | gritty | | Race condition | interference pattern | phase clash | crossing vectors | sparking | | Memory leak / bloat | spreading stain | swelling drone | expanding mass | overheated, swollen | | Dead code | gray / dim | silence | abandoned room | cold, dusty | | Clean interface | sharp boundary | clean attack / release | defined doorway | smooth edge |
Extract:
Choose 2 to 4 modalities best suited to the task:
Look for:
For each important sensory observation, state:
End with a concrete path such as:
Use this shape unless the user wants something else:
Literal read 2 to 6 bullets on what the code or system is doing.
Synesthetic render A concise multi-modal description of how the system feels, sounds, looks, or moves.
Dissonances The 1 to 3 most important mismatches, friction points, or instability signals.
Engineering translation Concrete explanation of what those signals mean technically.
Recommended changes Specific next steps, ordered by leverage.
Bias toward dissonance, jitter, interference, flicker, and timing language. Translate these into:
Bias toward weight, balance, shape, airflow, and texture. Translate these into:
Bias toward tempo, pressure, congestion, heat, and echo. Translate these into:
Lean more vivid and intuitive, but keep the mapping reversible. Use metaphor to help the user build a correct mental model.
If the user asks for code changes:
If the user asks for a pure sensory rendition:
If the artifact is incomplete:
tools
Convert markdown plans into beads with dependencies using br CLI. Use when creating task graphs, polishing beads before implementation, or bridging planning to agent swarm execution.
development
Orchestrate Codex skill optimization during active sessions through $cas goal control, $shadow single-session evidence, $tune diagnosis/refinement briefs, and the skill-optimizer custom subagent. Trigger for $opt, skill optimization loops, session-driven skill tuning, meta-skill audits, or explicit validated skill edits. Do not use for general code optimization, product optimization, or performance tuning.
development
Run a targeted fresh-eyes blunder pass over code, specs, plans, adjudications, closure gates, skill edits, or negative-evidence ledgers. Trigger when asked to reread with fresh eyes, find obvious bugs, catch mistakes/oversights/omissions, check for embarrassing misses, or perform a second independent blunder pass before closure. Do not use as a substitute for implementation, adjudication, or verification; use it as the final falsification/check pass for those workflows.
development
Explicitly shadow, tail, watch, follow, monitor, supervise, or companion exactly one Codex session id/path through `$seq`, then apply a named target skill as an interpretation/reporting/proposal/action lens until the watched session stops.