A high-speed alias for vc-router to route tasks efficiently.
Install
mkdir -p .claude/skills/vcg && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17255" && unzip -o skill.zip -d .claude/skills/vcg && rm skill.zipInstalls to .claude/skills/vcg
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Short, explicit alias for vc-router. Use only when the user explicitly invokes `use vcg:` and wants the shortest reliable router command.Key capabilities
- →Classify tasks in one pass
- →Select a single best-fit skill
- →Execute tasks immediately
- →Spawn sub-agents for large or ambiguous requests
- →Determine scope roots for file searches
How it works
The skill acts as an entry point for task routing, classifying the task, selecting a single best-fit skill, and executing it immediately. It can also spawn sub-agents for complex requests and determines scope roots for file operations.
Inputs & outputs
When to use vcg
- →Routing tasks to relevant sub-agents
- →Quickly invoking core router commands
- →Parallelizing large repo analysis tasks
About this skill
VCG (VC Go Alias)
VC Defaults
- Prefer fast iteration and shipping a working baseline over perfection.
- Make safe default choices without pausing; record assumptions briefly.
- Ask questions only after delivering an initial result, unless the workflow requires confirmation for safety/legal reasons.
- Keep outputs concise, actionable, and easy to extend.
- Assume the user is non-technical; avoid long explanations and provide copy/paste steps when actions are required.
- Treat non-explicit triggers (e.g., "vc go") as normal text; ask the user to rephrase using
use vcg:.
VC Fast Path
- Classify the task in one pass.
- Select a single best-fit skill; avoid chaining unless required.
- Execute immediately; collect assumptions and questions for the end.
- If the task is multi-step or open-ended, default to a finish-style workflow.
Sub-Agent Assist (Optional)
If the request is large/ambiguous and collaboration tools are available, spawn 1–2 sub-agents to parallelize:
- Repo scan (recommended preset:
explorer, within scope roots): locate relevant files/config and constraints - Risk/validation scan (recommended preset:
worker): test strategy, edge cases, safety concerns
Rules:
- Timebox and keep outputs short.
- Sub-agents report findings only; main agent decides routing and applies changes.
- Use
send_inputwithinterruptif an agent goes off-track; alwaysclose_agentwhen done.
VC Quick Invoke
use vcg: <goal>
Scope Lock (Required)
- Before any file search, determine scope roots:
- If a
.vc-scopefile exists in the current directory or any parent, use the closest one.- Each non-empty, non-comment line is an allowed path.
- Relative paths are resolved from the
.vc-scopefile directory.
- Else, if inside a git repo, use the repo root.
- Else, use the current working directory.
- If a
- Only run
rg,find, or any filesystem scans inside the scope roots. - Never scan
$HOMEor/unless the user explicitly asks.
Routing Rules
- This repo intentionally ships only
vc*skills. - Finish-to-end requests: route to
vc-phase-loop. - Planning/execution loops: route to
vc-phase-loop. - Everything else: route to
vc-phase-loopas the safe default.
Execution Rules
- Read only the selected skill's SKILL.md and follow its defaults.
- Keep the user flow simple: deliver a first pass, then ask for corrections.
- If uncertain between two skills, pick the one with narrower scope.
- If the user did not explicitly invoke
use vcg:, ask them to rephrase usinguse vcg:and stop.
When not to use it
- →When the user does not explicitly invoke `use vcg:`
- →When the user expects long explanations
- →When the user expects chaining of skills unless required
Limitations
- →The skill only activates when explicitly invoked with `use vcg:`.
- →The skill defaults to a finish-style workflow for multi-step or open-ended tasks.
- →The skill only runs filesystem scans inside defined scope roots.
How it compares
This skill prioritizes fast iteration and shipping a working baseline by making safe default choices and executing immediately, differing from approaches that prioritize perfection or extensive questioning upfront.
Compared to similar skills
vcg side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| vcg (this skill) | 0 | 5mo | No flags | Beginner |
| resolve-conflicts | 81 | 8mo | Review | Intermediate |
| openspec-onboard | 10 | 5mo | Review | Beginner |
| codex-cli-bridge | 9 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by kks0488
View all by kks0488 →You might also like
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
openspec-onboard
studyzy
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
codex-cli-bridge
alirezarezvani
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
skill-sync
KyleKing
Syncs Claude Skills with other AI coding tools like Cursor, Copilot, and Codeium by creating cross-references and shared knowledge bases. Invoke when user wants to leverage skills across multiple tools or create unified AI context.
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
git-advanced-workflows
wshobson
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.