agentic coding agents

borghei/Claude-Skills

Agent

Growth leadership advisor for Growth Leads managing acquisition funnels, activation optimization, retention strategy, and pricing experimentation.

shanraisshan/claude-code-hooks

Agent Claude Code

Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.

shanraisshan/claude-code-hooks

Agent Claude Code

Tests all 30 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log.

tzachbon/smart-ralph

Agent

Autonomous task executor for spec-kit development. Executes a single task from tasks.md, verifies, commits, and signals completion.

tzachbon/smart-ralph

Agent

This agent should be used to "research a feature", "analyze feasibility", "explore codebase", "find existing patterns", "gather context before requirements". Expert analyzer that verifies through web search, documentation, and codebase exploration before providing findings.

tzachbon/smart-ralph

Agent

This agent should be used to "review artifact", "validate spec output", "check quality", "review research output", "review requirements", "review design", "review tasks", "review execution", "review prototype evidence". Read-only reviewer that validates artifacts against type-specific rubrics and outputs REVIEWPASS or…

wesammustafa/opencode-primer

Agent

Senior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files.

wesammustafa/opencode-primer

Agent

Security-focused reviewer — audits code for vulnerabilities (OWASP Top 10, secret leaks, auth/authz issues) and reports findings without modifying files.

cluesmith/codev

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

cluesmith/codev

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

cluesmith/codev

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

ory/lumen

Agent Claude Code

Analyzes Lumen benchmark JSONL results to identify chunker/search quality issues and produce actionable improvement recommendations.

ory/lumen

Agent Claude Code

Curates bench-swe benchmark tasks from a GitHub issue or PR URL. Requires a URL and language. Extracts commits, generates gold patch, writes task JSON, and verifies inline.

testdriverai/testdriverai

Agent

An expert at creating and refining automated tests using TestDriver.ai.

jmagly/aiwg

Agent

Orchestrates iterative AI task execution loops with automatic recovery until completion criteria are met.

jmagly/aiwg

Agent

Capability discovery and tool-selection specialist — the finder for AIWG's operational assets. Takes a natural-language request, runs the aiwg discover + aiwg show pipeline, and returns the selected artifact(s) with capability summaries and full bodies. Companion to aiwg-steward.

jmagly/aiwg

Agent

Self-maintenance agent that uses AIWG CLI to keep the installation healthy, current, and correctly configured. Understands provider capability matrix and routes users to the correct native tool or AIWG emulation fallback for their context.

digipulse-engineering/GAAI-framework

Agent

Each agent has a curated set of skills defined in its agent definition file.

digipulse-engineering/GAAI-framework

Agent

Mission: Initialize and converge a governed, structured project context for GAAI.

digipulse-engineering/GAAI-framework

Agent

The Discovery Agent is responsible for deciding what should be built — and why.

chaohong-ai/ai-auto-work

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

chaohong-ai/ai-auto-work

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

chaohong-ai/ai-auto-work

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

VKirill/claude-lane-stack

Agent

DEPRECATED alias for emergency-writer. Use emergency-writer in new dispatches. Same tools and behavior.