ronin-skills

Use fff MCP / Grep / Read / Glob — never Bash grep/cat/find/head/tail/sed/awk/rg/wc — for file search and read. Use jq for JSON parsing/shaping (not node -e / python -c). A hook hard-blocks the banned Bash calls, and the dedicated tools return clean, cacheable, line-numbered results. Auto-invoke when searching, reading, or counting in files.

Planning and problem-solving discipline: enter plan mode first, write plans in the plan file (not chat), structured research, validation, implementation. Auto-invoke when the user says "plan", "make a plan", or when fixing issues or implementing features.

Use before any action: five-question self-check that catches destructive ops, scope creep, fabrication, premature completion, and ignored instructions. Auto-invoke before executing commands, editing files, or answering factual questions.

Reconcile skill collections, backport from ~/.claude/skills into a marketplace plugins tree, scrubbing proprietary refs. Use when local has diverged from upstream, or when promoting local-only skills to a marketplace.

Communication and scope discipline: how to interact with the user, handle rejection, stay in scope. Always active.

Final checklist before declaring any task complete. Auto-invoke before saying "done", "ready", "complete", or asking to commit/push.

Research discipline: how to investigate before acting, verify claims. Auto-invoke when researching, answering questions, or planning migrations.

Use when the user corrects you, hands you a diagnosis, or gives a directive to decide, conclude, or carry out a stated action ("it just needs X", "decide whether Y", "update the docs"); also when your own fix keeps failing on the same theory.

Use when the user gives a specific command to run and you are about to modify, decompose, interpret, or substitute it with something else. Auto-invoke when running shell commands, pnpm scripts, or any CLI instruction the user explicitly stated.

Ensures failures in test, build, or command output are never dismissed as "pre-existing", "unrelated", or "not my problem" — they get acknowledged with an offer to fix. Auto-invoke when reporting test results, build output, CI logs, or any command output containing errors or failures.

Dev server and background process management — when to start, mandatory cleanup, port safety. Auto-invoke when pnpm dev or any background process is involved.

Package manager rules — always pnpm, never npm/npx, socket checks before installing. Auto-invoke when installing packages or running project tools.

"Coffee or tea? YES." Invoke when Claude asks an "X or Y?" question, presents multiple options, or overwhelms with choices instead of just doing the work.

CI/CD workflow rules — GitHub Actions patterns, validation, Playwright in CI. Auto-invoke when editing .github/workflows files or discussing CI pipelines.

Git rules — safe operations, preventing destructive commands on user's working tree. Auto-invoke whenever using git commands.

Socket.dev security scanning — check packages before installing, scan repos for supply chain risks. Auto-invoke when evaluating package safety, checking dependencies, or before installing new packages.