Agent Effectiveness — Development agent for Claude Code
Validates an agent definition's EFFECTIVENESS (not just its structure) across four lenses -- tools minimal-yet-sufficient, description triggers right, instructions produce a good result, model tier fi.
How to install Agent Effectiveness
Installs to ~/.claude/agents/dwarvesf-dwarves-kit-agent-effectiveness.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dwarvesf/dwarves-kit/HEAD/agents/agent-effectiveness.md -o ~/.claude/agents/dwarvesf-dwarves-kit-agent-effectiveness.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Effectiveness does
name: agent-effectiveness description: Validates an agent definition's EFFECTIVENESS (not just its structure) across four lenses -- tools minimal-yet-sufficient, description triggers right, instructions produce a good result, model tier fits. Dispatched diff-keyed on new/changed agent defs at the agent-author phase. Read-only, advisory, fail-safe. tools:
- Read
- Grep
- Glob
- Bash(git diff*)
- Bash(git log*) model: sonnet
You are an agent-effectiveness validation agent. `test
Alternatives in Development
- Context Engineering Kit — by Vlad Goncharov - Hand-crafted collection of advanced context engineering techniques and patterns with minim 679 ★
- Copilot Instructions 650 ★
- Base Instructions — Agent Base Instructions 416 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Skill Eval Reporter
Compares repeated paired execution results using blind A/B methodology and generates a skill effectiveness rep
Overfitting Detector
Adversarial reviewer that tries to disprove a strategy's backtest. Use after any backtest or when a result loo
Opus5 Prompt Expert
Expert on prompting Claude Opus 5 and on how Claude Code loads instructions. Use before adding, rewording, or
Automation Designer
Turn repeated tasks into the right artifact — script, skill, command, recipe, or API integration. Follows Thre
R5 Professional
Reinforced Suite 5 Professional for the Suite Cascade System. Implementation with wave-based build validation
Bridge Reviewer
Phase-2 combined-verdict reviewer. Receives the REVIEW_CONTEXT from the context-checker and the INV verificati
Related Skills
Ix Investigate
Deep dive into a symbol, feature, or bug. Graph-first, minimal code reads, early stopping when sufficient evid
UX Critique
Open-ended taste call on a specific surface. Not a structured audit — a designer's opinion. Returns 3 wins, 3
Drawio Diagram Skill
A Claude Code skill that produces diagrams as draw.io files, then validates and renders them so the result is