mryll/skills
Portable agent skills for AI coding agents — works with Claude Code, OpenAI Codex CLI, Gemini CLI, Cursor & GitHub Copilot: code review, vertical-slice architecture, Go testing strategy, low cognitive-complexity & AGENTS.md generation. Mark
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit mryll/skills/agents ./rig-skills/agents $ npx degit mryll/skills/skills ./rig-skills/skills
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 mryll/skills/skills/agent-context-auditor .claude/skills/agent-context-auditor $ npx degit mryll/skills/skills/agentmd .claude/skills/agentmd $ npx degit mryll/skills/skills/c4-model .claude/skills/c4-model $ npx degit mryll/skills/skills/claude-discuss .claude/skills/claude-discuss $ npx degit mryll/skills/skills/claude-review .claude/skills/claude-review $ npx degit mryll/skills/skills/codex-discuss .claude/skills/codex-discuss $ npx degit mryll/skills/skills/codex-review .claude/skills/codex-review $ npx degit mryll/skills/skills/como-si-fuera-de-boca .claude/skills/como-si-fuera-de-boca $ npx degit mryll/skills/skills/dual-testing .claude/skills/dual-testing $ npx degit mryll/skills/skills/explain-pr .claude/skills/explain-pr $ npx degit mryll/skills/skills/low-complexity .claude/skills/low-complexity $ npx degit mryll/skills/skills/pr-quiz .claude/skills/pr-quiz $ npx degit mryll/skills/skills/ste .claude/skills/ste $ npx degit mryll/skills/skills/study-session .claude/skills/study-session $ npx degit mryll/skills/skills/test-namer .claude/skills/test-namer $ npx degit mryll/skills/skills/vertical-slice-architecture .claude/skills/vertical-slice-architecture
$ curl -fsSL --create-dirs -o .claude/agents/ste-writer.md https://raw.githubusercontent.com/mryll/skills/main/agents/ste-writer.md This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (16)
agent-context-auditoragentmdc4-modelclaude-discussclaude-reviewcodex-discusscodex-reviewcomo-si-fuera-de-bocadual-testingexplain-prlow-complexitypr-quizstestudy-sessiontest-namervertical-slice-architecture
Subagents (1)
| ste-writer model: sonnet | Runs the ste skill's draft-check-fix loop (Steps 3-5) on a cheaper model tier when the ste skill delegates in economy mode. Receives the source text or request, the target language, and the compliance |
Similar rigs
rkiyanchuk/dotfiles
Personal configuration files
Minimalist 1.6k tok ·
iedayan/agentmd
CI/CD for AI agents — parse, validate, and execute AGENTS.md in GitHub Actions. Agent-readiness score, guardrails, and governed execution.
Pragmatist 3.8k tok ·
masutaka/dotfiles-public
masutaka public dot files
Fort Knox 503 tok ·
chaseai-yt/claudex-loop
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never gr
Minimalist 272 tok ·