skills

Orchestrator skill for the `prompt` skillset. Dispatches to member skills in a safe, predictable order. Separates intent formation from execution to protect humans from premature or misaligned execution.

Conduct a focused, evidence-driven examination of ONE triaged suspect area. This is a test, not a verdict. Evidence may falsify the leading hypothesis.

Convert the user's raw description into a clinically precise intake note suitable for handoff to another agent or human. Captures symptoms, normalizes terminology, and separates observation from belief.

Orchestrator skill for the `doctor` skillset. A diagnostic protocol that models software failures as medical cases — preventing premature action, wrong-layer fixation, and false certainty in complex codebases.

Produce a treatment note that combines diagnosis, confidence, supporting evidence, alternative explanations, and proposed treatment options. Creates an artifact, not execution.

Perform breadth-first hypothesis surfacing and prioritization across all ownership zones, without commitment. This is not diagnosis and not investigation.

Display the execution status of a plan by parsing frontmatter metadata. Shows progress at-a-glance without requiring manual inspection of each file.

Audit dictionary usage against the Dictionary Usage Doctrine. Produces a severity-grouped report with minimal refactor suggestions.

Audit Python imports to preserve semantic context and prevent shadowing after refactors. Prefer namespace-first imports over direct symbol imports for generic identifiers.

Audit inline complexity and recommend variable extraction. Produces a report with flattening suggestions for nested expressions.

Audit identifiers and namespaces for lexical-semantic and ontological correctness. Detect semantic role misalignment (agent/tool/process/artifact), derivational misuse (e.g., -er agent nouns), and category errors between modules, packages, classes, functions, and data artifacts. Output a single Markdown report with actionable fixes.

Detect module/package name stutter in Python public APIs. Produces a Markdown report and optional CI gate.

Audit semantic noise and namespace integrity. Produces a severity-grouped report with namespace/rename suggestions.

Detect squatters: modules and packages that occupy namespace positions they do not semantically own. Identifies utility dumps, stuttery siblings, axis violations, layer bleeding, and semantic diffusion — common structural smells introduced by agentic programming.

Identify structurally duplicate logic (pipeline-spine duplication) across semantically distinct modules. Use when multiple implementations share the same orchestration skeleton (e.g., bounds→shape→chunking→reduction→wrap), and unification may require subtle abstraction. Produces a duplication map and a safe extraction/refactor plan.