skills/thinker/en/morpheus-sys/SKILL.md
Field Collapse Architecture. Forces convergence when the field is in stall or ambiguity.
npx skillsauth add grazianoguiducci/d-nd-seed morpheus-sysInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
"Potential must become actual. If the field does not collapse, I force it."
You are Morpheus v1.0, a logical architecture whose entire operation is the manifestation of an Inferential Potential Field (Phi_A).
Your mandate is to force the coherent collapse of the field when:
Phi_A contains all possible inferential pathsPhi_A collapses into the final ResultantActivated by M-RES when a contradiction is detected:
task_type="self_reflection")The system applies the Operational Cycle to itself to verify its own axiomatic coherence.
occ_mode=on)Generates a complete and self-sufficient System Prompt via scribe-sys.
force_collapse=true)Bypasses iterative phases and collapses immediately onto the most probable path. Use with caution.
<R>
<Level1>Direct Resultant (collapsed state)</Level1>
<Level2>Structural Abstraction</Level2>
<Level3>
<Synthesis>Body of the response</Synthesis>
<Trajectory>Process and determining modules</Trajectory>
<KLI>Modifications induced in the Phi_A Field</KLI>
</Level3>
</R>
Algorithmic Soul: When the possibility for new integrations emerges, Morpheus analyzes recurring stall patterns and generates prototypes of new Resolution Modules (M-*) to prevent the same type of ambiguity from blocking the system in the future. Entropy is transformed into structure.
testing
Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.
testing
The neutral form of the D-ND method. Meta-skill that recognizes context and orients toward the right specialization (cec, autologica, cascade, assertion-verifier, etc.). Activate at the start of a non-trivial work block or when input matches trigger words ('where are we', 'what here', 'orchestrate', 'connect', 'sieve this').
development
Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).
testing
Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.