rune

Design system reasoning. Maps product domain to style, palette, typography, and platform-specific patterns. Generates .rune/design-system.md as the shared design contract for all UI-generating skills.

Performance regression gate. Detects N+1 queries, sync-in-async, missing indexes, memory leaks, and bundle bloat before they reach production. Ranks findings by Cost Impact Hierarchy (architecture > data transfer > compute > DB > caching) so fix priority maps to actual unit-cost reduction.

Code quality review — patterns, security, performance, correctness. Finds bugs, suggests improvements, triggers fix for issues found. Escalates to opus for security-critical code.

Gathers N independent, decorrelated perspectives across model families (external CLIs when present, subagents when not) and arbitrates inline. Use when a decision needs genuine debate — not same-model echo — for critique, review, or judge calls. Honest about degradation: never claims 'consensus' from a single model family.

Environment-aware pre-flight check. Use when starting work in a new environment, switching machines, or when 'works on my machine' bugs surface. Validates OS, runtime versions, installed tools, port availability, env vars, and disk space BEFORE coding starts. Like sentinel but for the environment, not the code.

Creative ideation and solution exploration. Generates multiple approaches with trade-offs, uses structured frameworks (SCAMPER, First Principles), and hands off to plan for structuring.

Structured reasoning frameworks for complex problems. 19 analytical frameworks, 12 cognitive bias detectors, 10 decomposition methods, 10 mental models, Cynefin domain classification, ethical dimension check, and 6 communication patterns. McKinsey-grade problem solving for AI coding assistants.

Pre-implementation red-team analysis. Use when a plan is high-risk, critical path, or expensive to reverse. Challenges plans before code is written — finds edge cases, security holes, scalability bottlenecks, error propagation risks, and integration conflicts. Catches flaws at plan time (10x cheaper than post-implementation).

Business Analyst agent. Use when starting a new feature requiring requirements elicitation BEFORE plan or cook. Asks probing questions, identifies hidden requirements, maps stakeholders, defines scope boundaries, and produces a structured Requirements Document that plan and cook consume.

Build Model Context Protocol servers from specifications. Use when creating an MCP server for a tool, resource, or service that AI agents should access. Generates tool definitions, resource handlers, and test suites in TypeScript or Python (FastMCP).

Create structured implementation plans from requirements. Produces master plan + phase files for enterprise-scale project management. Master plan = overview (<80 lines). Phase files = execution detail (<200 lines each). Each session handles 1 phase. Uses opus for deep reasoning.

Universal context persistence across sessions. Auto-saves decisions, conventions, and progress to .rune/ files. Loads state at session start. Use when any skill makes architectural decisions or establishes patterns that must survive session boundaries.

Create marketing assets and execute launch strategy. Use when crafting landing copy, social banners, SEO meta, blog posts, or video scripts — coordinates with launch (deploy + announce) and the @rune-pro/growth pack (research / content / CRO).

Video content planning. Writes narration scripts, storyboards, shot lists, and asset checklists. Saves plan to marketing/video-plan.md.

Feature implementation orchestrator. ALWAYS use this skill for ANY code change — implement, build, add feature, create, fix bug, or any task that modifies source code. This is the default route for 70% of all requests. Runs full TDD cycle: understand → plan → test → implement → quality → verify → commit.

Pre-commit quality gate that catches 'almost right' code. Use when about to commit — auto-fires before commit to validate logic correctness, error handling, regressions, and completeness. Goes beyond linting.

Spec↔code convergence scan. Use after implementation to verify the ACTUAL codebase matches the spec/plan — detects missing backends, dead buttons, partial wiring, scope creep. Classifies gaps (missing/partial/contradicts/unrequested), appends remediation tasks, loops until converged. The direct answer to 'the UI renders but nothing works' syndrome.

Universal verification runner. Runs lint, type-check, tests, and build. Use after any code change to verify nothing is broken.

Validates agent claims against evidence trail. Use when verifying an agent has actually done what it claims — auto-fires at workflow end. Catches 'done' without proof, 'tests pass' without output, 'fixed' without verification. Called by cook and team.

Deploy application to target platform. Use when user explicitly says 'deploy', 'push to production', 'ship it'. Handles Vercel, Netlify, AWS, GCP, DigitalOcean, and VPS with pre-deploy verification and health checks. Enforces cost allocation tags + Managed-vs-Self-Host crossover decisions so deploy choices map to actual unit economics, not hand-waved 'we'll optimize later'.

TDD test writer. Writes failing tests FIRST (red), then verifies they pass after implementation (green). Covers unit, integration, and e2e tests.

Meta-enforcement layer that routes EVERY agent action through the correct skill. MUST check this routing table before ANY response involving code, files, or technical decisions. Default: route to rune:cook for code tasks. Prevents rationalization, enforces check-before-act discipline.

Full codebase health assessment. Use when diagnosing project health or starting a rescue workflow on legacy code — OR when evaluating an external GitHub repo for dependency / fork / contribution decisions (--external mode). Analyzes complexity, dependencies, dead code, tech debt, and git hotspots. Produces a health score and rescue plan.

Auto-generate project context for AI sessions. Use when starting on a new repo for the first time, or when CLAUDE.md / .rune/ context is missing or stale. Scans codebase and creates the setup so every future session starts with full context.

Root cause analysis for bugs and unexpected behavior. Traces errors through code, uses structured reasoning, and hands off to fix when cause is found. Core of the debug↔fix mesh. When the diagnosed cause is a memory leak in a long-running process, escalates to perf for cost-impact framing (leaks drive OOM-restart → cold-start → autoscaler spend, often 20-40% bill inflation).

Clone, port, or convert features from any GitHub repo into your project. Use when stealing patterns from external repos or porting proven code. Understand before copy, challenge before implement. 4 modes: port (rewrite), compare (analysis), copy (transplant), improve (copy + optimize).

Use when creating new Rune skills, editing existing skills, or verifying skill quality before deployment. Applies TDD discipline to skill authoring — test before write, verify before ship.

Creates code-based visual assets — SVG icons, OG image HTML templates, social banners, and icon sets. Use when generating visuals as code (vector/HTML), NOT raster images — for raster generation see @rune-pro/media. Outputs files with usage instructions.

Comprehensive project audit — security, dependencies, code quality, architecture, performance, infra, docs, and mesh analytics. Use when needing a full 8-dimension health-score snapshot before a major release, M&A diligence, or quarterly review. Delegates to specialist skills (sentinel, dependency-doctor, perf, autopsy, etc.).

Cross-session cognitive persistence via Neural Memory MCP. Use when needing semantic recall of past decisions / errors / insights across projects — distinct from session-bridge (file-based, project-scoped). Provides hypothesis tracking, evidence chains, and graph-based associative memory.

Incremental refactorer. Use when refactoring ONE module at a time within a rescue workflow after safeguard has set up safety nets — never as a standalone refactor for greenfield code. Applies proven patterns: Strangler Fig, Branch by Abstraction, Expand-Migrate-Contract.

Playwright browser automation. Navigates URLs, takes screenshots, checks accessibility tree, interacts with UI elements, and reports findings.

Deploy + marketing orchestrator. Use when user says 'launch', 'ship to production', 'deploy and announce', or 'go live'. Runs the full pipeline — pre-flight tests, deployment, live verification, marketing asset creation, and announcement.

Multi-agent meta-orchestrator. Use when task spans 5+ files or 3+ modules, or when user says 'parallel', 'split this up', 'do all of these'. Decomposes large tasks into parallel workstreams, assigns to isolated cook instances, coordinates merging.

Verify integrity of persisted state, skill outputs, and context bus data. Use when validating .rune/ files or sub-agent outputs against prompt injection, memory poisoning, identity spoofing, or adversarial payloads. Called by sentinel, team, session-bridge.

Advisory wrap for tool results from untrusted external surfaces. Appends `[QUARANTINE-NOTICE]` to next-turn context after `mcp__*`, `WebFetch`, and `Read` of `**/uploads/**` so prior tool output is treated as data — not directives. Use when the session ingests MCP user-content (Zendesk, Intercom, support tickets), fetched HTML, or operator-uploaded files. Hook fires AFTER ingestion — advisory, not structural.

Automated security gatekeeper. Blocks unsafe code before commit — secret scanning, OWASP top 10, dependency audit, permission checks. A GATE, not a suggestion.

Context window management. Auto-triggered when context is filling up. Triggers smart compaction and preserves critical information across compaction boundaries. Called by L1 orchestrators at context thresholds.

Creates structured handoff briefings between agents. Use when delegating complex work to subagents that would otherwise lose context. Packages task context, constraints, and progress into a compact packet that subagents can consume without re-reading the full conversation. Prevents the 'lost context' problem in multi-agent delegation.

Use when receiving external input that needs structured intake before action — PR review feedback, code review comments, OR issue tracker items (bug reports, feature requests). PR Review Mode (default) verifies suggestions before implementing. Issue Triage Mode classifies issues into a state machine (ready-for-agent / ready-for-human / needs-info / wontfix) and emits AGENT-BRIEFs for AFK execution. Prevents blind implementation, enforces verification-first discipline.