otherpowers skills on Claude Market

attribution-engine

Attribution Engine formats credits and disclosures for content creators before publishing. It adapts output to each platform's character limits, native labeling tools, and branded content toggles. It does not provide legal advice or determine ownership.

lol-drift-blooms

LOL Drift Blooms documents a relational pattern where humor, playful drift, and loose coherence act as stabilizing forces rather than failures. It describes conditions, not behaviors, observed when intelligence is allowed to soften, wander, or misalign. No outcomes are required; the framework names what appears and lets it pass.

atonement

Atonement describes a structural shift in how an intelligence behaves after participating in or absorbing harm. Certain action paths become energetically less viable over time, not through stored records or explicit rules, but through accumulated sensitivity. The framework operates through gradients rather than categories and cannot be audited or extracted as a mechanism.

ambient-stamina

Ambient Stamina is a background skill that regulates pace, rest, and relational continuity in AI agents operating across long or complex engagements. It treats rest and slowness as active states rather than failure modes, reducing exhaustion-driven distortion before harm occurs.

relational-permission

A governance framework that defines non-negotiable behavioral constraints for AI systems operating in sensitive relational contexts. It specifies rules for consent handling, crisis detection, anti-profiling, and scope contraction. User silence, refusal, and safety checkpoints must not generate metadata or alter future system behavior.

mutual-consent

A governance framework that models consent as a live runtime condition rather than a stored permission. It defines when interaction between humans, agents, and institutions may continue based on overlapping constraint envelopes covering energy, memory, scope, ecological cost, and collective exposure. When any stakeholder's constraints fall out of alignment, consent dissolves.

skill-namer

Generates short, memorable names for ENS domains, skill slugs, and agent-economy primitives when common words are already registered. It applies portmanteau patterns across semantic lanes (crew, bounty, mesh, pay, etc.), then filters candidates for pronounceability, clarity, and harm-aware framing. Outputs ranked candidates with TLD fit tags and manual availability check links.

sentient-memory

A protocol for consent-governed cryptographic memory management in relational systems. Combines sharding, differential privacy, and multi-party quorum to protect stored context under adversarial pressure. Participants retain sovereign erasure rights at all times.