ravnhq/ravn-core

Audit and fix how well a coding agent can work in the current repository. Trigger for "is this repo agent-ready", "why do agents struggle here", "make this repo easier for agents". Skip for code review, a single failing test, or feature work.

Find the ravn-core skill or flow that fits your work.

Bring the supplied GitHub PR or stack of PRs to merge-ready, merged when the user asks for the merge, or an evidenced blocker. Discover repository gates; verify fixes before pushing; batch review work.

Find what a change could break outside its diff, and prove the one fact it is safe because of by running real code. Use for "blast radius of X", "what could this break", or a small diff you don't trust yet.

Reproduce a reported bug, find its cause with runtime evidence, and ship the smallest fix as a PR whose history shows the failure before the fix.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing a GLOSSARY.md or ADR, or choosing structures for stateful logic, scattered branches, or repeated shape assumptions.

A relentless interview to sharpen a plan or design.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

Pause work and leave a resumable checkpoint another agent, in any harness, can pick up cold. Use when the user asks to pause, stop for now, go offline, restart, or hand off. Requests to keep going and automatic context compaction are not pauses. Use session-pickup to resume.

Use when writing a PR body.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

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.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

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."

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Resume or take over work from a prior session: a handoff note, transcript, agent URL, or pushed branch. Recovers the resume point and continues the pending work without redoing what already landed. Use when the user says pick up, resume, continue where you left off, or take over. Use pause-safely to write a handoff.

Take a change from idea to a ready PR with passing CI, chaining research, grilling, domain-modeling, codebase-design, the verification skills, and pr.

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Use for autonomous or multi-phase runs, or work a human reviews after stepping away.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.