lucassantana-dev/forgekit/adt-fallback
Claude Code and agent skill by lucassantana-dev/forgekit
- community
Checking that the SKILL.md file is still in the repository.
Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing. Plan B when the first plan fails.
Install
npx vskill@latest install lucassantana-dev/forgekit/adt-fallbackSKILL.md
The same SKILL.md was published earlier as majiayu000/claude-skill-registry-data/adt-fallback.
Fallback
Graceful degradation when primary approach fails. If preferred agent/skill/tool fails, try alternates in priority order. Record which path succeeded for future routing decisions.
Purpose
Increase resilience. Instead of crashing on first failure, attempt a ladder of fallback strategies. Log outcomes for analytics and future routing optimization.
When to use
- Primary API rate-limited → try cheaper model or cached result
- Preferred tool unavailable (Playwright, Firecrawl) → shell equivalent or simpler approach
- Test framework broken → manual verification or other test harness
- Deployment target down → try alternate region or staging
Fallback Ladder Pattern
- Try primary — Execute preferred approach.
- On failure — Capture error, severity, and root cause.
- Try secondary — Run alternate (lower cost, lower latency, or lower feature fidelity).
- Try tertiary — Final fallback (minimal viable approach).
- Escalate — If all fail, ask user or escalate to architect.
- Record — Log which path succeeded + why for future routing.
Example Ladder
Invocation
Or via skill trigger: "Try fallback for PDF extraction"
Logging Format
Each fallback attempt logs to ~/.claude/logs/fallback.jsonl:
References
- Smart model select:
smart-model-select(similar fallback for model choice) - Dispatch skill:
dispatch(routes to alternates) - Error handling patterns:
packages/core/best-practices/error-handling.md
Security
- Security scanPassed, 90 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-fallback/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-fallback)