changelog-newsletter
Transform technical changelog entries into user-friendly newsletter content for email, blog posts, and release notes. Use when converting CHANGELOG.md files, git commit logs, or release notes into customer-facing communications.
Assess and reduce cognitive load in interfaces, flows, and content. Use when designing or reviewing any multi-step process, complex form, dashboard, decision flow, or information-dense screen. Triggers on: cognitive load, too complex, overwhelmed, too many steps, decision fatigue, confusing, info...
--- name: cognitive-load-assessment description: "Assess and reduce cognitive load in interfaces, flows, and content. Use when designing or reviewing any multi-step process, complex form, dashboard, decision flow, or information-dense screen. Triggers on: cognitive load, too complex, overwhelmed, too many steps, decision fatigue, confusing, information overload, simplify this flow. Applies to any interface where users must think, decide, or remember." --- # Cognitive Load Assessment Assess cognitive load across three dimensions and provide actionable recommendations to reduce unnecessary burden on users. ## The Three Types of Cognitive Load **Intrinsic load** — complexity inherent in the task itself. A tax return is intrinsically complex. You cannot simplify the tax code. Focus: break into manageable steps, provide context, explain terms. **Extraneous load** — complexity added by the design, not the task. Confusing navigation, unclear labels, inconsistent patterns, visual clutter. Focus: eliminate ruthlessly. Every instance is a fixable design failure. **Germane load** — effort invested in the actual task. This is the load you WANT. The user engaging with their real goal. Focus: maximise this by removing the other two. ## Assessment Framework For each screen or step, evaluate: | Dimension | Low (good) | Medium (review) | High (redesign) | |-----------|-----------|-----------------|-----------------| | Decisions required | 0–1 | 2–3 | 4+ | | Items to remember | None | 1–2 | 3+ | | New concepts to learn | None | 1 | 2+ | | Steps to complete | 1–2 | 3–5 | 6+ | | Reading complexity | Plain language | Some jargon | Dense/technical | | Visual complexity | Clean, focused | Moderate | Cluttered | **If any dimension rates High, that screen needs redesign before launch.** ## How to Assess 1. Walk through the flow as a user who is tired, stressed, and unfamiliar 2. At each screen, count: decisions, things to remember, new concepts 3. Note where you pause, re-read, or feel uncertain — those are load spikes 4. Map the load type: is the difficulty intrinsic or extraneous? 5. Recommend specific reductions for each extraneous load source ## Reduction Strategies - **Progressive disclosure:** show only what the current step needs - **Smart defaults:** pre-select the most common option - **Chunking:** group into sets of 3–5 related items - **Recognition over recall:** show options, don't make users remember - **Persistent context:** show key selections throughout a flow - **One primary action per screen:** de-emphasise secondary actions ## Output Format Present the assessment as a screen-by-screen table showing load ratings, followed by prioritised recommendations sorted by impact.--- name: cognitive-load-assessment description: "Assess and reduce cognitive load in interfaces, flows, and content. Use when designing or reviewing any multi-step process, complex form, dashboard, decision flow, or information-dense screen. Triggers on: cognitive load, too complex, overwhelmed, too many steps, decision fatigue, confusing, information overload, simplify this flow. Applies to any interface where users must think, decide, or remember." --- # Cognitive Load Assessment Assess cognitive load across three dimensions and provide actionable recommendations to reduce unnecessary burden on users. ## The Three Types of Cognitive Load **Intrinsic load** — complexity inherent in the task itself. A tax return is intrinsically complex. You cannot simplify the tax code. Focus: break into manageable steps, provide context, explain terms. **Extraneous load** — complexity added by the design, not the task. Confusing navigation, unclear labels, inconsistent patterns, visual clutter. Focus: eliminate ruthlessly. Every instance is a fixable design failure. **Germane load** — effort invested in the actual task. This is the load you WANT. The user engaging with their real goal. Focus: maximise this by removing the other two. ## Assessment Framework For each screen or step, evaluate: | Dimension | Low (good) | Medium (review) | High (redesign) | |-----------|-----------|-----------------|-----------------| | Decisions required | 0–1 | 2–3 | 4+ | | Items to remember | None | 1–2 | 3+ | | New concepts to learn | None | 1 | 2+ | | Steps to complete | 1–2 | 3–5 | 6+ | | Reading complexity | Plain language | Some jargon | Dense/technical | | Visual complexity | Clean, focused | Moderate | Cluttered | **If any dimension rates High, that screen needs redesign before launch.** ## How to Assess 1. Walk through the flow as a user who is tired, stressed, and unfamiliar 2. At each screen, count: decisions, things to remember, new concepts 3. Note where you pause, re-read, or feel uncertain — those are load spikes 4. Map the load type: is the difficulty intrinsic or extraneous? 5. Recommend specific reductions for each extraneous load source ## Reduction Strategies - **Progressive disclosure:** show only what the current step needs - **Smart defaults:** pre-select the most common option - **Chunking:** group into sets of 3–5 related items - **Recognition over recall:** show options, don't make users remember - **Persistent context:** show key selections throughout a flow - **One primary action per screen:** de-emphasise secondary actions ## Output Format Present the assessment as a screen-by-screen table showing load ratings, followed by prioritised recommendations sorted by impact.
Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.