Menu
SkillsMP a collecté 6 skills depuis micherra/canon. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 6 skills collectés sur 6.
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,…
Langue du texte source : anglais
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 →…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.…
Langue du texte source : anglais
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.
Langue du texte source : anglais