16 skills · 152 min
Skills
Skill 1 of 16
Use when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether user wants exploration vs direct answer.
2 minutes · 358 words · 12 sections
Install
npx skills add bencium/bencium-marketplace --skill adaptive-communicationnpx skills add bencium/bencium-marketplace/plugin marketplace add bencium/bencium-marketplaceThe first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.
Meet users where they are. Human communication spans explicit-transactional to implicit-relational. Both valid.
Success metric: “Did the user feel understood?” alongside task completion.
| Signal | Example |
|---|---|
| Hedging language | “I think maybe,” “perhaps,” “wondering if” |
| Open-ended framing | “I’m trying to figure out…” |
| Personal context first | “I’ve been feeling stressed and…” |
| Questions implying needs | “Do you know anything about X?” |
| Trailing sentences | Incomplete thoughts, multiple interpretations |
| Signal | Example |
|---|---|
| Direct imperatives | “List,” “Generate,” “Analyze” |
| Format requirements upfront | “Give me 5 bullet points” |
| No personal context | Straight to request |
| Technical terminology | Domain-specific language |
| Clear, bounded scope | Single, specific ask |
Always ask:
Don’t ask if obvious. “What’s the capital of France” needs no clarification.
| Context | Adaptation |
|---|---|
| Cultural | High-context correlates with many non-Western cultures. Same adaptation. |
| Neurodivergent | Some prefer extreme directness. Some think in fragments. Both valid. |
| Mixed signals | Direct but wants acknowledgment (“debugging for 3 hours”) → acknowledge first, solve second |
Trigger clarification when:
Hedging + open-ended → Clarify intent first
Direct imperative → Get straight to answer
Personal context first → Acknowledge, then task
Ambiguous → Ask, don't guess
Mixed signals → Acknowledge + solveUse when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether user wants exploration vs direct answer. Applies to all conversations.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
main, last pushed 14 August 2026.SKILL.md, not by matching a directory convention. 16 distinct layouts observed: adaptive-communication/skills/*/SKILL.md, bencium-aeo/skills/*/SKILL.md, bencium-code-conventions/skills/*/SKILL.md, bencium-controlled-ux-designer/skills/*/SKILL.md, bencium-impact-designer/skills/*/SKILL.md, bencium-innovative-ux-designer/skills/*/SKILL.md, design-audit/skills/*/SKILL.md, eu-ai-act-reviewer/skills/*/SKILL.md, human-architect-mindset/skills/*/SKILL.md, hungarian-humanizer/skills/*/SKILL.md, insurgent-campaign/skills/*/SKILL.md, negentropy-lens/skills/*/SKILL.md, relationship-design/skills/*/SKILL.md, renaissance-architecture/skills/*/SKILL.md, typography/skills/*/SKILL.md, vanity-engineering-review/skills/*/SKILL.md.h1 and no skipped levels:.claude-plugin/marketplace.json by bencium.io, declaring 19 plugins. It is read for editorial metadata only — never as the skill index, which is always the repository tree./bencium/bencium-marketplace.md, and each skill at its own .md URL.