kevin-burns/claude-skills
A small collection of MIT-licensed Claude Code skills that I build
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit kevin-burns/claude-skills/agents ./rig-claude-skills/agents MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit kevin-burns/claude-skills/.agents/skills/beads .claude/skills/beads $ curl -fsSL --create-dirs -o .claude/agents/azure-architect.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/azure-architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-builder.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/code-builder.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/coherence-checker.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/coherence-checker.md $ curl -fsSL --create-dirs -o .claude/agents/commit-pr.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/commit-pr.md $ curl -fsSL --create-dirs -o .claude/agents/commit-style.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/commit-style.md $ curl -fsSL --create-dirs -o .claude/agents/docs-reviewer.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/docs-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/fact-verifier.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/fact-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/ux-auditor.md https://raw.githubusercontent.com/kevin-burns/claude-skills/main/agents/ux-auditor.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (9)
| azure-architect model: opus | Use this agent when the user needs guidance on Azure landing zone design, Cloud Adoption Framework (CAF) implementation, Azure governance structures, subscription topology, management group hierarchie |
| code-builder model: sonnet | Use proactively to implement a well-scoped code change — a feature, bugfix, refactor, or test — against an agreed plan, in an isolated git worktree on a feature branch. It works test-first, runs the p |
| code-reviewer model: sonnet | Use proactively to review a diff, branch, or proposed change for correctness bugs and quality issues before it lands — logic errors, unhandled edge cases, race conditions, security slips, broken contr |
| coherence-checker model: sonnet | Use after code-builder and fact-verifier and BEFORE code-reviewer to check that the implementation structurally matches the plan, the spec it cites, and the verified facts — spec-to-code and plan-to-c |
| commit-pr model: haiku | Use to write git commit messages and PR/MR descriptions once a change is staged or ready for review. Produces clear, human-readable messages. Trigger before committing or before opening a PR/MR. |
| commit-style | — |
| docs-reviewer model: sonnet | Use this agent proactively when documentation has been written or updated and needs review for completeness, conciseness, clarity, typos, and readability. This includes READMEs, architecture docs, run |
| fact-verifier model: sonnet | Use proactively to verify factual claims, code, or proposed changes against authoritative sources before they are trusted, committed, or acted on — version numbers, API/CLI shapes, config values, reso |
| ux-auditor model: sonnet | Use proactively to audit a rendered web page for usability and accessibility problems and return prioritized, fix-ready findings — Nielsen heuristics, WCAG 2.2 (A/AA), responsive behavior, and whether |
Similar rigs
Dipen-Dedania/agent-pulse
Know what your agents are doing
Orchestrator 1.7k tok · · Q15
sodre90/mirador
A canvas for your coding agent. It draws what it means, asks you with pictures, and walks you through its changes and reviews, right beside the conversation. Desktop app for macOS, Linux and Windows.
Minimalist 2.2k tok · · Q20
ufna/zerus
Zerus is an ADE for working with a fleet of AI coding agents across your machines. Bring your own agents and subscriptions. Follow conversations, get notified and keep projects in sync over P2P, all from one workspace.
Pragmatist 6.2k tok · · Q25
thoreinstein/gemini-beads
A Gemini CLI extension for Beads (bd). Adds graph-based task management, dependency tracking, and context persistence to AI workflows.
Minimalist 457 tok · · Q0