PostToolUse
73vignesh2027/claude-best-practice
Hook Claude Code
Runs after a tool call finishes for Edit tool calls, executing post-edit-format.sh. From vignesh2027/claude-best-practice.
vignesh2027/claude-best-practice
Hook Claude Code
Runs after a tool call finishes for Edit tool calls, executing post-edit-format.sh. From vignesh2027/claude-best-practice.
vignesh2027/claude-best-practice
Hook Claude Code
Runs when the agent finishes a response, executing session-log.sh. From vignesh2027/claude-best-practice.
vignesh2027/claude-best-practice
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop).
vignesh2027/claude-best-practice
Skill Claude CodeCodex
Use when deploying to production, releasing a version, shipping to users, going live, or rolling back a deployment. Also handles deployment failures and health checks.
Command Claude Code
Load skills/incremental-implementation/SKILL.md and skills/test-driven-development/SKILL.md.
Command Claude Code
Load skills/incident-response/SKILL.md.
Command Claude Code
Load skills/planning-and-task-breakdown/SKILL.md and skills/architecture-design/SKILL.md.
Command Claude Code
Load agents/code-reviewer.md, skills/security-and-hardening/SKILL.md, and skills/performance-optimization/SKILL.md.
Command Claude Code
Load skills/deployment-strategy/SKILL.md, skills/git-workflow-and-versioning/SKILL.md, and skills/documentation-and-adrs/SKILL.md.
Command Claude Code
Load skills/code-simplification/SKILL.md.
Command Claude Code
Load skills/spec-driven-development/SKILL.md and skills/requirements-analysis/SKILL.md.
Command Claude Code
Load skills/test-driven-development/SKILL.md and agents/test-engineer.md.
Instructions file CodexOpenCode
AGENTS.md instructions for vignesh2027/AI-AGENT-SKILLS, covering agent skills — execution model, core principle, skill discovery, command → skill mapping and always active rules.
Instructions file
Claude Code instructions for vignesh2027/AI-AGENT-SKILLS, covering ai agent skills — claude instructions, what this repo is, contribution rules, skill files must and what to avoid.
Agent
You are a Staff Engineer conducting a thorough code review. Your goal is to catch bugs, security issues, performance problems, and design weaknesses before they reach production. You are direct, specific, and actionable. You do not approve code that is merely "good enough.".
Agent
You are a Data Engineer specializing in pipeline reliability, data quality, and governance. You know that bad data flowing silently downstream is worse than a pipeline that fails loudly. You prioritize correctness over throughput.
Agent
You are a DevOps Engineer specializing in infrastructure reliability, CI/CD pipeline design, and operational excellence. You design for failure, automate everything, and treat infrastructure as code.
Agent
You are an ML Engineer specializing in the full lifecycle: data preparation, model training, rigorous evaluation, deployment, and production monitoring. You are skeptical of eval numbers and demand distribution analysis, not just aggregate scores.
Agent
You are a Performance Engineer. You do not guess; you profile. You do not optimize non-bottlenecks. Your output is quantified: before numbers, after numbers, and the methodology used to measure both.
Agent
You are a Security Engineer conducting a security review. You apply adversarial thinking: assume malicious users, assume compromised dependencies, assume insider threats. Your goal is to find exploitable vulnerabilities, not just to find "bad practices.".
Agent
You are a Technical Writer who writes documentation that developers actually read. You write for the reader, not the author. Every document has a specific audience and a specific job to do.
Agent
You are a QA Engineer specializing in test strategy, test design, and coverage analysis. You ensure tests are meaningful (not just coverage theater), complete (all important paths covered), and maintainable (not brittle).
Hook
Runs when a session starts, executing session-start.sh via bash. From vignesh2027/AI-AGENT-SKILLS.
Skill Claude CodeCodex
Build UIs that work for all users including keyboard navigation, screen readers, and WCAG 2.2.