JordanGunn

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.

Growth-weighted complexity hotspots per file (Tornhill "Your Code as a Crime Scene", 2015). Composes `ccx` (complexity) with `git log --numstat` (LOC change volume) and ranks files by hotspot score = sum_ccx × max(0, loc_delta). Files are classified into four quadrants — hotspot, stable_complex, churning_simple, calm — based on 75th-percentile cutoffs on both axes. Default time window is 14 days — tuned for agentic code generation where architectural damage from file growth accumulates in days, not months. Read-only. Requires git. Language coverage inherits from ccx.

Meta-skill for agent discovery and skill routing. Returns the structured capability registry for all aux skills so agents can select the right skill, understand composition patterns, and bootstrap with no prior context.

Cyclomatic Complexity (McCabe 1976) and Cognitive Complexity (Campbell 2018) per function across a codebase, computed in a single tree-sitter AST traversal per file. Language-agnostic — supports Python, JavaScript, TypeScript, Go, Rust, and Java on day one. Classifies functions into zones: simple, moderate, complex, untestable. Read-only. No regex text-tier fallback — files that fail to parse are reported as errors and skipped.

Semantic git diff skill. Surfaces what has changed since a git ref — files modified, line counts, and symbols added/removed (requires tree-sitter). Attacks accumulated session drift: shows exactly what changed and what symbol-level API surface was affected. Read-only.

Module dependency graph skill. Builds an import graph from source files, computes per-file coupling metrics (afferent Ca, efferent Ce, instability), and detects import cycles. Read-only. AST extraction via tree-sitter is the default; a text-tier regex fallback runs when AST extraction is unavailable for a specific file.

Agent-assisted read-only structural search. Executes tree-sitter AST queries over a codebase and returns matched captures without modifying any files.

Tiered dead code candidate audit. Enumerates symbols and modules with zero detected external references and emits advisory output for human verification. Never acts autonomously — all candidates require deeper-dive investigation via `aux usages` before any action is taken.

Robert C. Martin package design metrics skill. Computes coupling (Ca/Ce/I), abstractness (Na/Nc/A), and distance from the main sequence (D') per package. Classifies packages into zones: pain, uselessness, warning, clean, ok. Read-only. AST abstractness detection via tree-sitter is the default; a text-tier regex fallback runs when AST extraction fails for a specific file.

Compile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, conciseness, and correctness.

Execute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after successful execution.

Shape, refine, and stabilize human intent into a canonical prompt artifact. Iteratively clarifies ambiguity until user confirms readiness.

Agentic code quality linter. Runs 10 structural analysis rules against a codebase and reports violations. Operates in passive mode (after changes, surface only if violations found) or active mode (on user request, report summary). Backed by tree-sitter, ripgrep, fd, and git.

Establish disk-backed repository context by reading ASI documentation entrypoints and recording a scoped context digest. Produces onboarding artifacts only (no kickoff, no plan, no execution).