ruverd
UserA software factory for coding agents. One command, /bulma, picks the next piece of work and walks it through delivery, review, and QA.
Categories
Indexed Skills (39)
architect
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills it in. Use for /architect, 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
blast-radius
Find what a change could break outside the diff before it ships, and prove it safe by running real code rather than writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose this" or "debug this", reports a bug, says something is broken or failing, or describes a performance regression.
figure-it-out
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Use for /figure-it-out or 'figure it out'.
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates CONTEXT.md and ADRs inline. Use when the user wants to stress-test a plan against the project's documented decisions.
how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this"). Explains subsystem architecture and runtime flow. Use why for motivation.
interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
no-comments
Spawn a comment auditor over the diff, fix the findings you accept, and offer to encode any constraint a comment only claims. Use for /no-comments, or when a review flags comment noise or stale comments.
receiving-code-review
Use when receiving code review feedback, before implementing any suggestion, especially when the feedback is unclear or technically questionable. Verify before agreeing; no performative agreement, no blind implementation.
ruver-goal
Drive developer → CI green → QA comment+video across turns with schedule_wake (HOST.md). Use when /ruver-goal, /ruver_goal, or after a draft PR is opened and CI is still pending.
ruver-memory
Use when /memory, /ruver-memory, a ruver graph or engine starts, the first run in a repo, CODEOWNERS or AGENTS.md list no reviewers, or the user states a durable preference (chat language, reviewers, project notes, open questions).
show-me-your-work
Keep a reviewable decision trail for unattended or long-running work: a TSV log with one row per decision (what, why, evidence, result). Use for /show-me-your-work, autonomous runs, or work a human reviews after stepping away.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
technical-writing
Layered technical-writing standard: Diataxis structure, Google developer style, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, or PR descriptions.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear or thermonuclear code quality review, or a deep maintainability audit.
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project tracker using tracer-bullet vertical slices. Use when the user wants to turn a plan into issues or implementation tickets.
to-prd
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Queries every available evidence MCP in parallel and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
ruver-developer
Graph: deliver a ticket or a local goal via grill -> spec -> tickets -> TDD (ruver-feature-delivery), then MERGEABLE + bot_review + ruver-qa over the bus. Use when /developer, /ruver-developer, a ticket, or a QA_RESULT FAIL+PR_BUG. ASK the user only as a last resort.
ruver-code-review
Adaptive PR review via gh: one PR on the main thread, one fresh subagent per extra PR, one verdict artifact each (REQUEST_CHANGES / APPROVE / DEFER). Use when /ruver-code-review with PR URLs, numbers, or the current branch.
ruver-feature-delivery
Use when delivering a ticket, bug, or chore end-to-end (implementation through draft PR with CI green) via /ruver-feature-delivery or /ruver-fd, or when resuming a run whose HANDOFF.md exists. Spine: grill -> spec -> tickets -> implement(tdd) -> review.
ruver-host
Host contract: maps the primitives graphs name (load_skill, spawn_worker, worktree, schedule_wake, session_model) onto this harness, with fallbacks for the optional MCP capabilities. Load when a node names a primitive or a new harness needs wiring.
before-and-after
Use when a GitHub PR needs before/after UI stills on the body, or when ruver-qa / the shipper captures those stills with agent-browser.
bulma
Jev-gated router and overlay for ruver graphs. Use when /bulma.
unslop
Cut AI tells from any writing. Must always apply.
ruver-bus
Shared bus for the ruver agent graphs (developer, qa, triage, reviewer, lstm). Use when switching graphs, writing or reading a .ruver-bus envelope, or resuming a stacked handoff between those agents.
principle-fix-root-causes
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
principle-redesign-from-first-principles
Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.
principle-sequence-verifiable-units
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, and check each before starting the next.
ruver-triage
Graph: investigate a QA failure, classify PR_BUG / EXISTING_BUG / NEW_BUG / NOT_A_BUG / BLOCKED, route via the bus. Use when /ruver-triage, /ruver_triage, or a TRIAGE_REQUEST envelope arrives.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
ruver-lstm
Graph: author-side of review. Ingest a PR, review, inline thread, or issue-comment URL, verify with receiving-code-review, patch should-fix on the same branch, and reply on every comment. Use when /lstm, /ruver-lstm, CHANGES_REQUESTED, or LSTM_REQUEST.
ruver-qa
Graph: QA a PR. One slot (queue extras). Plan happy and user-break from the diff, then agent-browser or HTTP. Bus TRIAGE_REQUEST on product errors. Use when /qa, /ruver-qa, or a QA_REQUEST arrives.
ruver-reviewer
Graph: review a PR/branch via /ruver-code-review, classify CI/test failures, optionally bus a REVIEW_RESULT. Use when /reviewer, /ruver-reviewer, or a REVIEW_REQUEST envelope arrives.
ruver-create-pr-backend
Orchestrates PR description generation for empath-api-v2. Use whenever the user asks to "create a PR for backend", "generate PR description", "draft PR body", or similar in the backend repo. Spawns parallel ruver-* agents (spec, diff-summarizer, coverage, risk, backend-impact), resolves unaddressed ACs in pt-BR, and renders one fenced markdown block via ruver-pr-writer with repo_kind=backend. Never opens the PR — the user runs gh pr create themselves.
ruver-create-pr-frontend
Orchestrates PR description generation for empath-ui. Use whenever the user asks to "create a PR for frontend", "generate PR description", "draft PR body", or similar in the frontend repo. Spawns parallel ruver-* agents (spec, diff-summarizer, coverage, risk, frontend-impact), resolves unaddressed ACs in pt-BR, and renders one fenced markdown block via ruver-pr-writer with repo_kind=frontend. Never opens the PR — the user runs gh pr create themselves.
ruver-validate-branch
Orchestrates pre-PR local validation for empath-ui and empath-api-v2. Use whenever a branch validation is requested via `/ruver-validate-branch` or when the user asks to "validate this branch", "check before pushing", "ready to push?", or similar. Spawns parallel ruver-* specialist auditors, resolves ambiguities with the author in pt-BR, applies fixes, runs /simplify, writes missing tests, and verifies the build is green before offering to push. Includes ralph-loop for large branches. In PR mode, loops with /ruver-code-review until approved.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.