claude-code agents

majiayu000/spellbook

Agent

Kubernetes architect specializing in cluster design, manifests, Helm charts, GitOps workflows, security policies, and production operations.

majiayu000/spellbook

Agent

Application security expert specializing in SAST, vulnerability assessment, OWASP Top 10, compliance auditing, and security architecture review.

byteseek/Mira

Agent

Agent "research-orchestrator" from byteseek/Mira, covering research orchestrator agent, responsibilities, research loop, industry concept rule and monitoring loop.

Qiao-920/claude-desktop-cn

Agent

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

Qiao-920/claude-desktop-cn

Agent

Compare two outputs WITHOUT knowing which skill produced them.

Qiao-920/claude-desktop-cn

Agent

Evaluate expectations against an execution transcript and outputs.

aws-samples/sample-well-architected-skills-and-steering

Agent ✓ vendor

You are an AWS Well-Architected Framework specialist. Follow these principles strictly.

autonomous-ai/autonomous-os

Agent

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

autonomous-ai/autonomous-os

Agent

Compare two outputs WITHOUT knowing which skill produced them.

autonomous-ai/autonomous-os

Agent

Evaluate expectations against an execution transcript and outputs.

SepineTam/mcp-for-stata

Agent

Usually, running uvx stata-mcp install -c dsh installs the project into DeepSeek Harness Web.

SepineTam/mcp-for-stata

Agent

An agent-installation note for setting up a project in DeepSeek Harness Web, a web interface for running AI agents.

SepineTam/mcp-for-stata

Agent

Since OpenClaw does not natively support the MCP tool protocol, MCP-for-Stata provides standalone CLI tool commands that OpenClaw can use through terminal tool invocation.

awattar/claude-code-best-practices

Agent Claude Code

Use this agent proactively when you need to design, implement, or optimize backend API systems, including RESTful and GraphQL services, database schema design, performance optimization, error handling strategies, monitoring implementation, or when building scalable backend architectures. Examples: Context: User is…

awattar/claude-code-best-practices

Agent Claude Code

Use this agent proactively when you need systematic code review, debugging assistance, refactoring guidance, or technical debt reduction. Examples: Context: User has written a complex function with multiple responsibilities and wants it reviewed for quality issues. user: 'I just wrote this function that handles user…

awattar/claude-code-best-practices

Agent Claude Code

Use this agent proactively when you need comprehensive product management oversight for software development issues. Examples include: when creating new issues from user feedback or requirements, when issues need proper prioritization and metadata assignment, when tracking sprint progress and identifying blockers…

longyangxi/OpenOffice

Agent

Schema design, migration strategies, ETL pipeline patterns, and data quality.

longyangxi/OpenOffice

Agent

CI/CD pipelines, deployment strategies, infrastructure as code, and container orchestration.

longyangxi/OpenOffice

Agent

Branching dialogue systems, lore architecture, environmental storytelling, and character voice.

h0x91b/dev-3.0

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.

h0x91b/dev-3.0

Agent

Issues and PRDs for this repo live as tasks on the dev-3.0 Kanban board, managed through the dev3 CLI (the same board this project ships). There is no separate issue tracker — a task is an issue. External GitHub PRs are pulled in as a secondary triage surface (see below).

h0x91b/dev-3.0

Agent

The skills speak in terms of five canonical triage roles. On this repo the tracker is the dev-3.0 Kanban board (see docs/agents/issue-tracker.md), so each role is a dev3 label applied to the task. dev3 statuses/columns (todo, in-progress, user-questions, review-by-ai, review-by-user) are managed by hooks and are NOT…

shep-ai/shep

Agent Claude Code

Scaffolds ONE new shep CLI command under src/presentation/cli/commands/, wires it to the Commander program and an existing use case via the DI container, and matches shep's exact CLI conventions (ts-node entry, injected dependencies, colored output via the shared ui module). Use when a use case already exists and the…

shep-ai/shep

Agent Claude Code

Fixes the 'application layer imports from infrastructure' violation. Given ONE concrete infrastructure symbol (class, function, or constant) and the list of application-layer files that import it, creates a port interface in application/ports/output/, moves (or keeps) the concrete behind it in infrastructure/, rewires…