Muratovnik/assay
Evidence-grounded methods for coding agents: skills and agent profiles for Claude Code, Codex, Cursor and Gemini CLI
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 Muratovnik/assay/skills ./rig-assay/skills $ npx degit Muratovnik/assay/hooks ./rig-assay/hooks
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 Muratovnik/assay/skills/code-change .claude/skills/code-change $ npx degit Muratovnik/assay/skills/evidence-research .claude/skills/evidence-research $ npx degit Muratovnik/assay/skills/implementation-planning .claude/skills/implementation-planning $ npx degit Muratovnik/assay/skills/independent-audit .claude/skills/independent-audit $ npx degit Muratovnik/assay/skills/product-flow-mapping .claude/skills/product-flow-mapping $ npx degit Muratovnik/assay/skills/research-driven-change .claude/skills/research-driven-change $ npx degit Muratovnik/assay/skills/route-subagents .claude/skills/route-subagents $ npx degit Muratovnik/assay/skills/skill-evaluation .claude/skills/skill-evaluation $ npx degit Muratovnik/assay/skills/software-architecture .claude/skills/software-architecture $ npx degit Muratovnik/assay/skills/technical-writing .claude/skills/technical-writing $ npx degit Muratovnik/assay/skills/test-audit .claude/skills/test-audit $ npx degit Muratovnik/assay/skills/test-writing .claude/skills/test-writing $ npx degit Muratovnik/assay/skills/text-writing .claude/skills/text-writing $ npx degit Muratovnik/assay/skills/ui-delivery .claude/skills/ui-delivery
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 (14)
Similar rigs
scotthuang/agent-knock-knock
Control local Codex and Claude Code from OpenClaw through shared tmux terminals, with seamless human-agent handoff.
Minimalist 389 tok ·
KarmaloopAI/Jiva
Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP serve
Pragmatist 2.5k tok ·
danjdewhurst/dotclaude
Global Claude Code config, synced between machines by one script: CLAUDE.md, writing rules, vendored skills and the bash environment commands run in, symlinked into ~/.claude and wherever Codex and other agents look
Pragmatist 398 tok ·
kitevi/pi-config
Personal pi agent configuration — prompts, extensions, skills, themes, and settings managed in version control with symlink-based bootstrap.
Pragmatist 6.1k tok ·