Vibe-Skills local-vco-roles
Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.
install
source · Clone the upstream repo
git clone https://github.com/foryourhealth111-pixel/Vibe-Skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/foryourhealth111-pixel/Vibe-Skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/bundled/skills/local-vco-roles" ~/.claude/skills/foryourhealth111-pixel-vibe-skills-local-vco-roles && rm -rf "$T"
manifest:
bundled/skills/local-vco-roles/SKILL.mdsource content
local-vco-roles
Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local
vibe skill.
When to Use
Use this skill when:
- You run
and need a stable role set for dialectic review./vibe - You want reproducible multi-role analysis using TeamCreate-style orchestration.
- You need standardized outputs across team-lead / bug / architecture / integration / usability roles.
Vibe Compatibility Contract (Must Follow)
- Grade handshake:
- M/L: do NOT force TeamCreate orchestration.
- XL: TeamCreate workflow is allowed.
- Rule-1 boundary:
- Never mix multiple agent systems for the same task.
- Follow
conflict rules first.vibe
- Command priority:
- User explicit command >
routing > this role pack defaults.vibe
- Output severity:
- Always use
.CRITICAL > HIGH > MEDIUM > LOW
- Staged confirmation:
- Keep major confirmation points aligned with
team protocol.vibe
- Memory behavior:
- Default state tracking via TodoWrite-style task state.
- Optional enhancements (if available) must not become hard dependencies.
Role Prompt Library
- Team lead:
references/role-prompts/team-lead.md - Bug analyst:
references/role-prompts/bug-analyst.md - Architecture critic:
references/role-prompts/arch-critic.md - Integration analyst:
references/role-prompts/integration-analyst.md - Usability analyst:
references/role-prompts/usability-analyst.md
Recommended XL Workflow
- Read
.references/vibe-compatibility.md - Create 5 tasks (lead + 4 analysts).
- Assign each role using the prompt files above.
- Collect results and aggregate by severity.
- Produce one merged decision set (
).keep / simplify / remove
Optional Utility
- Run scaffold helper:
scripts/new-run.ps1 -Topic <name>