lucassantana-dev/forgekit/adt-route
Claude Code and agent skill by lucassantana-dev/forgekit
- community
Checking that the SKILL.md file is still in the repository.
Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain). Use to pick the right skill, for example what skill fits this task.
Install
npx vskill@latest install lucassantana-dev/forgekit/adt-routeSKILL.md
The same SKILL.md was published earlier as lucassantana-dev/forgekit/adt-route.
Route
Route a task to the most fitting skill or agent. Meta-router above dispatch. Parses the user intent, checks the installed-skill inventory, and picks the best match (single skill or chain). If fuzzy, runs recall first.
Purpose
Eliminate ambiguity when a task could fit multiple skills or agents. Route makes the decision, either immediately (high confidence) or after a quick context-pack query (low confidence).
When to use
- "I need to refactor the auth module but I'm not sure what approach"
- "Is this a testing problem or a design problem?"
- "Which skill handles this better: security-audit or code-review?"
Decision Protocol
- Parse intent — Extract primary verb (implement, fix, refactor, test, deploy, document, review) and object (code, config, feature, test, docs, infra).
- Check skill inventory — Query
~/.claude/skills/dirs +/packages/core/kit/core/skills/for matching trigger keywords. - Score matches — Confidence based on trigger word overlap + description relevance.
- High confidence (≥0.85) — Fire the skill immediately, no additional input.
- Medium confidence (0.65–0.84) — Run
recallto pull context, then decide. - Low confidence (<0.65) — Ask user for clarification or suggest top 3 candidates.
Output
- Single skill → "Routing to
/security-audit. Running now." + auto-invoke - Chain → "This needs 2 steps: 1)
code-review, then 2)simplify" + invoke in order, await completion - Ambiguous → "Could be
test-driven-developmentorarchitecture-patterns. Which fits?"
Example Invocations
References
- Skill inventory:
~/.claude/skills/(local) +packages/core/kit/core/skills/(toolkit) - Auto-invoke rules:
~/.claude/standards/skill-auto-invoke.md - Dispatch skill:
dispatch(lower-level routing) - Context retrieval:
recall(pulls RAG index)
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/catalog/catalog/skills/adt-route/SKILL.md
Popularity
- Repository stars
- 1
- Repository forks
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. 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
[](https://verified-skill.com/skills/lucassantana-dev/forgekit/adt-route)