메뉴
Run any registered role from the repo's evolving role repository (.claude/roles/) against a target — the generic solo dispatcher for roles that have no dedicated wrapper skill. Invoke explicitly.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
A hook-driven coach that watches your prompts to Claude Code and nudges you toward proven prompting best practices (definition-of-done, scoped references, guardrails, verification). Ships a tiered rule catalog; rules quietly graduate once you consistently apply them so the coach fades as you improve. Beta.
Design a scalable system — architecture, data flow, APIs, schema, caching — then implement its minimal production version, applying the repo's evolving `architect` role (.claude/roles/architect.md). Invoke explicitly.
Scaffold a complete, production-ready application from scratch — architecture first, then a minimal but scalable MVP — applying the repo's evolving `builder` role (.claude/roles/builder.md). Invoke explicitly.
Investigate a bug step by step, find the true root cause, and ship a robust production-ready fix, applying the repo's evolving `debugger` role (.claude/roles/debugger.md). Invoke explicitly.
Find bottlenecks and unnecessary work, then improve speed, memory, and scalability with measured, behavior-preserving changes, applying the repo's evolving `optimizer` role (.claude/roles/optimizer.md). Invoke explicitly.
Restructure code into clean architecture — separate concerns, raise modularity, reduce coupling, behavior unchanged — applying the repo's evolving `refactorer` role (.claude/roles/refactorer.md). Invoke explicitly.
| name | as |
| description | Run any registered role from the repo's evolving role repository (.claude/roles/) against a target — the generic solo dispatcher for roles that have no dedicated wrapper skill. Invoke explicitly. |
| argument-hint | [role] [target] |
| disable-model-invocation | true |
Input: $ARGUMENTS — the first word is the role name; the rest is the target.
.claude/roles/<role>.md (the
canonical, evolving one; registry.md indexes these). If it's absent, check this plugin's
bundled seeds alongside this skill at ../<role>/role.md — if found, copy it verbatim to
.claude/roles/<role>.md and use that. If the role exists in neither, list the available roles
(repo .claude/roles/*.md plus the bundled ../*/role.md, excluding crew.md/panel.md/
registry.md/this as skill) and stop — don't improvise a persona.## Learnings (core)
and ## Learnings (solo). Note crew.md and panel.md are consumer registries, not roles —
never load them as personas.
2.5 Anchor in the Prompt Library (optional). Each engineering persona maps to a category of
Anthropic's Claude Code Prompt Library —
architect→Plan, builder→Implement, debugger→Debug, optimizer→Debug, refactorer→Refactor,
reviewer→Review, skeptic→Review (the role's Body also names its category). If the
prompt-coach-beta plugin is installed, run its config.py library --category <Category> for
gold-standard prompt shapes in this role's domain and let them inform your opening. Degrade
silently — this is enrichment, not a dependency; skip it if the plugin/command isn't present.## Learnings (solo) in the role file: - YYYY-MM-DD — <one sentence>. Don't log
routine one-pass outcomes.Charter and Body edits are never made during a run — propose them to the user instead (identity changes are deliberate, user-gated).