Canon — engineering principles and agent-driven build system. This is the single entry point for ALL interactions in a Canon-enabled project. Activates for every user message: build requests, questions, reviews, principle management, project discussions,…
Procedural skill for generating, evaluating, and shaping evolution proposals for Canon's trace-driven evolution loop (Phase 1 mutator pipeline, plus the Gap 3 Layer 3 retire/reinforce pass). Orchestrates select_mutation_targets → evaluate_candidate →…
Principle, convention, and agent-rule authoring. Covers creation, editing, and applying accepted learner proposals. Handles interview, examples, conflict detection, format validation, and save. Loaded by the writer agent.
Pattern mining and proposal generation for Canon's learning loop. Analyzes codebase patterns, review history, build execution data, and conventions to produce structured improvement proposals. Covers manual analysis and auto-trigger modes. Loaded by the…
Requirements sharpening for build requests. Classifies request fuzziness into tiers (trivial, clear, fuzzy) and applies proportionate PM effort -- from pass-through to full creative divergence. Produces a sharpened-request artifact for architect hand-off.…
Mechanical runbook synthesis from canonical step vocabulary. Composes a step-by-step runbook from the design using only canonical step IDs. Validates step composition, enforces mandatory tail, and emits per-signal confidence. Used by the architect agent.