zdenham/anvil/implementation

Claude Code and agent skill by zdenham/anvil

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install zdenham/anvil/implementation

SKILL.md

Route Skill

`agents/skills/route.md` - NEW

This skill is invoked liberally—on almost every request. It guides the agent through task routing decisions.

Skill Content

markdown
# /route - Task Routing
**Invoke this skill BEFORE doing any work.** The only exception is truly trivial questions.
## Your Task
You have workspace context injected via hook. Now decide how to route this request:
1.**Check existing tasks first** - Does this relate to an active or recent task?
2.**Associate if relevant** - Semantic match? Same feature area? Continuation?
3.**Create only when needed** - No existing task fits? Distinctly new work?
4.**Subtask for scoped work** - Part of a larger task? Bug found during other work?
## Decision Tree
\`\`\`
Is this a trivial question (greeting, one-liner)?
→ YES: Skip routing, answer directly
→ NO: Continue...
Does this relate to an ACTIVE task?
→ YES: Associate with that task
→ NO: Continue...
Does this relate to a RECENT task?
→ YES: Consider re-activating or associating
→ NO: Continue...
Is this scoped work under an existing task?
→ YES: Create subtask
→ NO: Create new task
\`\`\`
## Execute Routing
Once decided, run the appropriate CLI command:
\`\`\`bash
# Associate with existing task
anvil tasks associate --task=<slug>
# Create new task
anvil tasks create --title="<title>" --type=work|investigate
# Create subtask
anvil tasks create-subtask --parent=<slug> --title="<title>"
\`\`\`
## After Routing
The CLI will output the task context. Then:
1.Switch to the task's git branch (if different)
2.Acknowledge the task context to the user briefly
3.Proceed with the actual work
## Task Types
-**work**: Code changes, implementations, bug fixes, refactoring
-**investigate**: Research, understanding, explanations, debugging
## Guidelines
-**Default to association** when there's semantic overlap
-**Descriptive titles** that capture intent (not generic like "fix bug")
-**One task per distinct effort** - don't fragment related work
-**Check git state** before switching branches (warn if dirty)

Files to Modify

  • agents/skills/route.md - NEW - routing skill instructions

Security

  • Security scanPassed, 96 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/zdenham/anvil/implementation/badge)](https://verified-skill.com/skills/zdenham/anvil/implementation)

Something wrong with this skill or its page? Tell us.