GitHub collection
rune-kit/rune
Imported from GitHub — is this yours?
57 skills imported from this repository.
- Stars
- 94
- Forks
- 26
- License
- MIT
Skills (57)
adversary
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 pl
asset-creator
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.
audit
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 (se
autopsy
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,
ba
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
brainstorm
Creative ideation and solution exploration. Use when a task is vague or open-ended, several approaches are viable, or the current approach has fundamentally failed ('ideas', 'explore options', 'what are the ways to'). Generates multiple approaches with trade-offs using structured
completion-gate
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. Checks claims, not code (hal
constraint-check
Meta-validator for HARD-GATEs. Use when auditing whether a skill's mandatory constraints were actually followed during a workflow (not just claimed). Called by cook, team, and audit for discipline compliance. Checks process rules; output claims are completion-gate, phantom import
context-engine
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.
context-pack
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. Preven
converge
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 conver
cook
Feature implementation orchestrator — runs the TDD cycle understand → plan → test → implement → quality → verify → commit. Use when the user wants working code built or changed across more than a line or two: a new feature, a bug fix with an unknown blast radius, a refactor. Not
council
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 cl
debug
Root cause analysis for bugs and unexpected behavior. Use when something fails and the cause is unclear: a stack trace, a failing test, 'why is this broken', or an error during implementation. Traces errors through code with structured reasoning and hands off to fix once the caus
dependency-doctor
Dependency health management. Use when adding, upgrading, or auditing packages, after a dependency manifest changes, or when 'outdated' / vulnerability warnings appear. Detects the package manager, checks outdated packages and known vulnerabilities, and produces a prioritized upd
deploy
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
doc-processor
Generate and parse office documents — PDF, DOCX, XLSX, PPTX, CSV. Use when creating reports, exporting tabular data, or processing uploaded office files. NOT for project documentation (use docs).
docs
Generate and maintain project documentation. Use when a project needs a README, API docs, architecture docs, or a changelog, or when docs must be synced after a feature ships ('update the docs', 'write a README'). Creates the docs and keeps them in sync with code changes.
docs-seeker
Find documentation for APIs, libraries, and error messages. Use when you need the current, version-correct API of a library, the meaning of an error message, or a migration guide, instead of relying on memory. Looks up official docs, llms.txt, changelogs, and migration guides. No
fix
Apply code changes and fixes. Use when the change to make is already known: implementing code to pass written tests, applying a diagnosed bug fix, or addressing review findings. Writes the implementation and verifies it with tests. Core action hub in the development mesh; runs de
git
Specialized git operations: semantic commits, PR descriptions, branch naming, changelogs, and conflict-resolution guidance. Use when committing, opening a PR, creating a branch, tagging a release, or resolving a merge conflict. Replaces ad-hoc git commands with a convention-aware
graft
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 + opti
hallucination-guard
Verify AI-generated imports, API calls, and packages actually exist. Use when finishing AI-generated code that introduces new imports or external API calls — auto-fires after fix/cook to catch phantom functions, non-existent packages, and slopsquatting. Checks the code itself; ag
improve-architecture
Find architectural friction in a codebase and propose deepening opportunities. Use when user wants to improve architecture, find refactor candidates, consolidate shallow modules, or make a codebase more testable. Outputs scored proposals (depth/leverage/locality) that surgeon and
integrity-check
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.
logic-guardian
Protects complex business logic from accidental deletion or overwrite. Use when editing payment, trading, state-machine, or other load-bearing business logic where a single deleted line can cause silent data corruption. Maintains a logic manifest, enforces pre-edit gates, validat
mcp-builder
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).
onboard
Auto-generate project context for AI sessions. Use when starting on a new repo, when CLAUDE.md / AGENTS.md / .rune/ context is missing or stale, or to set up per-runtime agent config and hooks (Codex, Grok, Gemini, Cursor) in a multi-runtime repo. Scans the codebase so every futu
perf
Performance regression gate. Use before committing or deploying performance-sensitive code, or when something is slow, memory grows, or the bundle is large. Detects N+1 queries, sync-in-async, missing indexes, memory leaks, and bundle bloat, and ranks findings by Cost Impact Hier
plan
Create structured implementation plans from requirements. Use when a task touches more than one file, needs architecture decisions, or the user asks to 'plan', 'design', or 'break this down'. Produces a master plan (<80 lines) plus phase files (<200 lines each), one phase per ses
problem-solver
Structured reasoning frameworks for complex, ambiguous problems. Use when the hard part is choosing how to think: many competing factors, a non-technical question (strategy, prioritization, trade-offs), or suspected bias. 19 frameworks, 12 bias detectors, mental models, Cynefin c
research
Web search and external knowledge lookup. Use when an answer depends on facts outside the codebase: comparing technologies or libraries, current best practices, or how others solved a problem. Searches multiple sources and returns triangulated findings with citations. Not for one
retro
Engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with trend tracking. Per-person breakdowns, shipping streaks, and actionable improvements. Use when asked for "retro", "weekly review", "what did we ship", or "engineering retrospective".
review-intake
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
scaffold
Autonomous project bootstrapper. Use when starting a new project from scratch ('new project', 'bootstrap', 'create a new app/API/library'). Generates structure, code, tests, docs, and config by orchestrating ba, plan, design, fix, test, docs, and git in one pipeline.
scope-guard
Detects scope creep by quantifying drift percentage. Auto-triggered by L1 orchestrators when files exceed the original plan. Compares git changes against plan, classifies drift into 4 tiers: ON_TRACK, MINOR_DRIFT, SIGNIFICANT_DRIFT, OUT_OF_CONTROL.
sentinel
Automated security gatekeeper. Use before every commit or deploy, and whenever auth, secrets, .env files, permissions, or other security-critical code change. Blocks unsafe code: secret scanning, OWASP Top 10, dependency audit, permission checks. A GATE, not a suggestion.
sentinel-env
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 fo
sequential-thinking
Step-by-step reasoning for multi-variable problems. Use when the options are known but the decisions depend on each other, order matters, consequences are hard to reverse, or second-order effects need tracing. Ordered logical steps with reversibility classification and bias check
session-bridge
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.
skill-forge
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.
skill-router
Routing table that maps a request to the right Rune skill before acting. Use before starting a coding task to decide which skill applies (default for code changes: rune:cook), and whenever unsure which skill fits. Enforces check-before-act discipline and blocks rationalized short
trend-scout
Scan market trends, competitor activity, and emerging patterns. Use when evaluating a product idea, positioning against competitors, or picking what to build next. Monitors Product Hunt, GitHub Trending, Hacker News, and social platforms. Not for technical questions or library co
video-creator
Video content planning. Use when a launch, demo, or tutorial needs a video: narration script, storyboard, shot list, and asset checklist. Saves the plan to marketing/video-plan.md.