Menu
Guide AI model selection based on task complexity, cost constraints, and latency requirements
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/vamseeachanta/workspace-hub --skill model-selectionThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
Based on SOC occupation classification
| name | model-selection |
| version | 1.0.0 |
| category | ai |
| description | Guide AI model selection based on task complexity, cost constraints, and latency requirements |
| type | reference |
| capabilities | [] |
| requires | [] |
| see_also | [] |
| tags | [] |
| scripts_exempt | true |
Version: 1.0.0 Category: Optimization Triggers: Starting tasks, choosing Claude model, usage optimization
NEW TASK
โ
โโโ WORK REPO + COMPLEX โ OPUS
โโโ WORK REPO + STANDARD โ SONNET
โโโ PERSONAL + SIMPLE โ HAIKU
โโโ DEFAULT โ SONNET
| Model | Target % | Use For |
|---|---|---|
| OPUS | 30% | Architecture, multi-file refactoring (>5 files), security review |
| SONNET | 40% | Standard implementations, code review, documentation |
| HAIKU | 30% | Quick queries, status checks, simple operations |
# Get model recommendation before each task
./scripts/monitoring/suggest_model.sh <repository> "<task description>"
# Examples:
./scripts/monitoring/suggest_model.sh digitalmodel "Design authentication architecture"
# โ Recommends: OPUS (complexity score: 4)
./scripts/monitoring/suggest_model.sh digitalmodel "Implement user login"
# โ Recommends: SONNET (complexity score: 1)
./scripts/monitoring/suggest_model.sh hobbies "Quick file check"
# โ Recommends: HAIKU (complexity score: -3)
Algorithm evaluates:
Score Mapping:
Tier 1 (Production): 60% Opus, 30% Sonnet, 10% Haiku
Tier 2 (Active): 30% Opus, 50% Sonnet, 20% Haiku
Tier 3 (Maintenance): 10% Opus, 30% Sonnet, 60% Haiku
Active: 20% Opus, 40% Sonnet, 40% Haiku Experimental: 5% Opus, 25% Sonnet, 70% Haiku Archive: 0% Opus, 20% Sonnet, 80% Haiku
Check before starting work: https://claude.ai/settings/usage
Alert Thresholds:
โ Multi-file refactoring (>5 files) โ Architecture decisions โ Complex algorithm design โ Security-critical code review โ Cross-repository coordination โ Performance optimization strategies
โ Standard feature implementation โ Code review (single PR) โ Documentation writing โ Test generation โ Bug fixing (standard complexity) โ Configuration updates
โ File existence checks โ Simple grep/search operations โ Quick status updates โ Log analysis (pattern matching) โ Template generation โ Format validation
โ STOP using Sonnet immediately
โ
Switch to Opus for critical work
โ
Switch to Haiku for everything else
๐
Defer non-urgent work to Tuesday
โธ๏ธ Pause AI tasks
โฐ Wait for session reset (~3-4 hours)
๐ฆ Batch work for next session
See: @docs/AI_MODEL_SELECTION_AUTOMATION.md See: @docs/CLAUDE_MODEL_SELECTION_QUICK_REFERENCE.md
Use this when starting tasks, selecting models, or optimizing AI usage.
Write outbound email and external messages in Vamsee Achanta's voice โ a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.