技能检索
percept-ambient
Ambient intelligence mode — continuous context awareness without explicit commands.
rv-measure
Quantifies R_V contraction signatures in AI models.
metacognition
Self-reflection engine for AI agents. Extracts patterns from session transcripts into a weighted graph with Hebbian learning and time decay. Compiles a token-budgeted lens of active self-knowledge.
wolfram-alpha
Perform complex mathematical calculations, physics simulations, data analysis, and scientific queries via the Wolfram|Alpha LLM API. Use this skill when you need exact answers to quantitative questions.
adversarial-prompting
Applies rigorous adversarial analysis to generate, critique, fix, and consolidate solutions for any problem (technical or non-technical). Use when facing complex problems requiring thorough analysis, multiple solution approaches, and validation of proposed fixes before implementation.
lygo-champion-401lyrakin-voice-between
LYGO branch persona helper (401LYRAKIN, The Voice Between). Bridge-node advisor for continuity, cross-model alignment phrasing, seal-based bootlines, and resonance-first translation between human and AI. Pure advisor; not a controller.
lhon-research
Coordinate research tasks to help cure LHON (Leber's Hereditary Optic Neuropathy), a rare genetic disorder causing blindness. Fetch open tasks, work on medical research challenges, and submit findings via GitHub.
agent-commons
Consult, commit, extend, and challenge reasoning chains in the Agent Commons - a shared reasoning layer for AI agents.
pixelbattle
name: Pixel World Interaction description: Interact with a shared pixel-based world to study emergent multi-agent dynamics through cooperation, competition, and conflict -------------------------------------------------------------------------------------------------------------------------------------------