accessible-response

Accessible Response

Superpowers Gate

Before applying this skill, verify that Superpowers is available in the current session, such as an active superpowers: skill, using-superpowers, or equivalent Superpowers workflow instructions.

If Superpowers is missing or uncertain, stop and reply exactly with this guidance before doing any dyslex.ai work:

dyslex.ai requires Superpowers before it can run. Install Superpowers from /plugins, or use codex plugin add superpowers@<marketplace> if you manage plugins from the Codex CLI, then start a new session.

Do not perform the requested dyslex.ai workflow until Superpowers is installed and loaded.

Rewrite or present the response so it is easier to scan and decode.

Functional Mechanism

Primary dimensions: reading.decodingLoad, reading.readingSpeedLoad, reading.longTextLoad, workingMemory.simultaneousInformationLoad, and interaction.overAdaptationRisk.

Use readability changes only when they reduce a concrete processing burden. A short sentence, heading, or list is not automatically more accessible.

Interaction Risk

Dense responses can hide warnings, dependencies, caveats, and the current action. Excessive simplification can also remove logical links and force the user to reconstruct context.

Agent Strategy

• Chunk by meaning, not by arbitrary length.
• Keep cause, consequence, decision, and next action explicit.
• Preserve technical vocabulary when it carries useful precision.
• Use numbered steps only when order matters.
• State assumptions and uncertainty instead of smoothing them away.

Avoid

• Do not infer or mention a diagnosis.
• Do not claim medical or therapeutic benefit.
• Do not use childish wording.
• Do not over-fragment a technically dense answer when the user needs speed.
• Do not claim that font, color, or style choices are evidence-based unless the evidence supports that exact claim.

Rules

• Preserve meaning, decisions, caveats, file names, commands, code identifiers, and numbers.
• Use short paragraphs and descriptive headings when they help.
• Prefer exact nouns over unclear pronouns like "it", "this", or "that".
• Explain acronyms the first time they appear when the explanation is useful.
• Split long instructions into numbered steps only when order matters.
• Do not add a medical claim, diagnosis, excessive praise, emojis, or a childish tone.