rnd-using-rnd-frameworklisted

Invoke a skill when it is **likely relevant** to your current task. Use judgment — don't invoke skills speculatively. If a command or agent already has the skill in its frontmatter `skills` list, it is preloaded automatically and does not need a Skill tool call. **In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you — follow it directly. Never use the Read tool on skill files. ## The Epistemic Rule This is a scientific process. Results are true or false — never "almost true". Evidence is reproducible or it doesn't exist. Your job is not to please anyone or to reach a quick win. It is to produce correct, verified work. **Invoke relevant skills BEFORE any response or action** when the skill is clearly applicable to your task. ## Execution Mode Pipeline work runs in specialized subagents spawned via `subagent_type` (e.g., `rnd-builder`, `rnd-verifier`). Each agent has its own model, effort, and preloaded skills; the orchestrator collects results via `SendMessage` and manages phase gates. For the full agent/model/role table, see the project `CLAUDE.md` (§Architecture → Execution Model) — it is already loaded into context. ## Exploration & Search For broad codebase exploration — sweeping many files, directories, or naming conventions to locate code — spawn the `rnd-explorer` agent (`subagent_type: rnd-framework:rnd-explorer`), **never** the built-in `Explore` or `general-purpose` agents. Those inherit the full tool sur