ryukirin/openspec-code-migration
Agent skills and an OpenSpec schema for evidence-driven code migrations: legacy inventory with a readiness check, a feasibility-proven migration strategy, and an advisory review.
stack: JavaScript
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit ryukirin/openspec-code-migration/skills ./rig-openspec-code-migration/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 ryukirin/openspec-code-migration/skills/migration-inventory .claude/skills/migration-inventory $ npx degit ryukirin/openspec-code-migration/skills/migration-review .claude/skills/migration-review $ npx degit ryukirin/openspec-code-migration/skills/migration-setup .claude/skills/migration-setup $ npx degit ryukirin/openspec-code-migration/skills/migration-strategy .claude/skills/migration-strategy
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 (4)
Similar rigs
melocalex/agent-knowledge-demo
Agent knowledge that outlives its author: AGENTS.md, skills and a memory log in the repo
Fort Knox 992 tok · · Q28
utsabpanta/claude-code-toolkit
Safety hooks for Claude Code that actually block. Every hook tested. Installs with zero settings.json editing - plus 12 specialist review agents.
Skill Collector 1.9k tok · · Q3
jpicklyk/task-orchestrator
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. W
Skill Collector 8.5k tok · · Q20
augments-labs/sdlc-skills
Skills for coding agents that cover the whole software lifecycle as you live it at work: ticket, tests first, schema changes, rollout, PR review, release, incident, post-mortem. One set of files for Claude Code, Codex, Cursor, and more.
Skill Collector 5.5k tok · · Q18