By chearmstrong
Portable personal coding-agent skills for code review, maintainability, architecture checks, cost estimation, supply-chain impact checks, commit messages, and review-comment workflows.
Verify architecture and implementation follow documented best practices, project patterns, and user rules. Check against project documentation, ensure no assumptions are made, and verify implementation matches documented patterns. Use when reviewing code, implementing features, making architectural decisions, or before committing changes.
Use when asked to find bugs, audit an existing repository or scoped path, review a branch or pull request for correctness, investigate a suspected defect, or assess security/data-integrity risks without making speculative findings.
Generate a Conventional Commits message from uncommitted changes. Use when the user asks for a commit message, conventional commit, or summary of staged and unstaged changes without committing.
Estimate and document cost-to-serve for cloud-hosted AI, LLM, AWS Bedrock, agent workflow, serverless, container, or SaaS control-plane systems. Use when the user asks for rough or granular service run-rate costs, infrastructure baseline estimates, sponsorship estimates, squad/team scaling projections, AWS cost breakdowns, Bedrock model cost analysis, or reusable documentation of cost assumptions.
Review documentation to ensure it matches implementation, is correct and up-to-date, clear and concise, uses British English, and has no duplication or redundancy. Works with or without MCP; prefers Context7 / AWS docs MCP when enabled, otherwise web search and official docs. Use when reviewing documentation files, code comments, docstrings, or when documentation may be outdated. Applies to markdown files, README files, code comments, and docstrings.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Portable personal coding-agent skills shared from ~/.agents.
These skills are maintained as normal skill directories and can be installed, copied, or symlinked into compatible agent skill folders.
npx skills add chearmstrong/skills
This installs the skills as normal user-level skills, which is the most predictable setup for Codex Desktop and CLI users.
To install one selected skill:
npx skills add chearmstrong/skills --skill review-pr
skills/..claude-plugin/..github/plugin/.Use npx skills add chearmstrong/skills for the default direct install. Plugin
bundles remain secondary routes for agent surfaces that already support them.
Codex plugin/marketplace support has been removed for now because direct skill
installation is simpler and more predictable across Codex Desktop and CLI. The
skills themselves remain portable and can still be installed manually or via
npx skills add.
| Goal | Agents | Method |
|---|---|---|
| Use the whole bundle | Codex, Claude Code, Copilot CLI, OpenCode | Install through skills.sh with npx skills add chearmstrong/skills. |
| Use selected skills | Codex, Claude Code, Copilot CLI, OpenCode | Install through skills.sh with npx skills add chearmstrong/skills --skill review-pr. |
| Use plugin bundle | Claude Code | Add this checkout as a Claude marketplace, then install chearmstrong-skills. |
| Use plugin bundle | GitHub Copilot CLI, VS Code Insiders | Add this checkout as a Copilot marketplace, then install chearmstrong-skills. |
| Use selected skills | Codex, Claude Code, Copilot CLI, OpenCode | Symlink or copy individual directories from skills/. |
| Skill | Description |
|---|---|
architecture-compliance-check | Verify architecture and implementation follow documented best practices, project patterns, and user rules. Check against project documentation, ensure no assumptions are made, and verify implementation matches documented patterns. Use when reviewing code, implementing features, making architectural decisions, or before committing changes. |
bug-hunting | Use when asked to find bugs, audit an existing repository or scoped path, review a branch or pull request for correctness, investigate a suspected defect, or assess security/data-integrity risks without making speculative findings. |
npx claudepluginhub chearmstrong/skills --plugin chearmstrong-skillsHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.