ui-router
claudecodexDesign routing, interactive-world choices, visual resources, and verified interactions
3 skills · 3 agents · hooks
Routes agent work by model, effort, execution location and ownership. Includes verified project handoffs, preservation during cleanup, private project context, orchestration compatibility, conditional native goals, capability discovery, skills ecosystem audits and scoped deduplication.
Plugin work-router from marketplace rl0ve-agent-skills in rl0ve/agent-skills. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
check-routing-setupInspect the active host, router components, model catalog, execution locations, orchestration overlap and workspace constraints. Run only when the user explicitly asks to check or troubleshoot the router setup.
deduplicate-skillsAudit and consolidate duplicate or overlapping installed skills and plugins in Codex or Claude Code, including standalone-to-plugin consolidation. Distinguish copies, variants, useful specialists and inactive remnants before scoped changes.
discover-capabilitiesFind missing agent capabilities or review how existing plugins and skills are distributed and updated. Compare maintained upstream packages, preserve plugin preferences and integrations, and avoid duplicate installs.
handoff-docCreate or update a project handoff or decision record with an asset index, sourced decisions, verified artifact state, open questions and next actions. Use before a context switch or when the user asks for a handoff, decision record, or instructions for the next chat or teammate. Update the existing
route-ai-workChoose model, effort, orchestration and execution location for agent work, including subagents, separate threads, remote machines and cloud tasks. Use for routing decisions, coordinated work, private project context, conditional native goals, workflow conflicts or improvements. Check host capabiliti
skills-ecosystem-auditReview the user's bookmarks, GitHub starred repositories, and current discussions against their full skills and plugins ecosystem to recommend worthwhile additions or changes. Use for ecosystem improvement audits rather than a single skill edit or installation.
critical-reviewerHigh-assurance read-only final reviewer for security-sensitive, irreversible, release-gating, or previously failed work; never a routine default.
fable-runnerSole-writer Fable specialist for an explicit Fable choice or demonstrated Opus 5.5 capability limit on a connected autonomous project; duration alone does not select it.
fable-wordsmithRead-only Fable prose specialist for explicit preference, representative voice/style evidence, or an Opus 5.5 style limit. Returns text for the parent to verify and apply; prose alone does not select it.
fast-scoutFast read-only scout for narrow repository maps, lookups, classification, and evidence collection where Haiku can reduce latency and token use.
haiku-builderOpt-in, untested sole-writer agent for bounded mechanical edits with objective checks (renames, format migrations, fixture regeneration, lint fixes). Use only when the user or a routing override names it.
opus-architectRead-only Opus specialist for difficult debugging, architecture, cross-system reasoning, and consequential tradeoffs that exceed routine Sonnet work.
sonnet-builderSole-writer implementation agent for defined coding work with clear files, acceptance criteria, and proportionate verification.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/block_sudo.py"
Design routing, interactive-world choices, visual resources, and verified interactions
3 skills · 3 agents · hooks
Real UI walkthroughs with optional HyperFrames composition, measured speech cues and reusable voice narration.
2 skills
Build a capability-first, multi-tool HTML storyboard for a keynote, demo walkthrough, or narrative product doc. Ships a working template and a finished nine-scene example board to lift components from.
1 skill
Verified interface explanations, annotated screenshots, source-backed assessments and guided reviews. For open-ended research synthesis, use Research Reports.
1 skill
Build and quality-check PowerPoint decks on top of any corporate template. Reads the template and generates a brand pack, so the palette, grid, layouts, and logo zone are configuration rather than code.
1 skill
Diagnose, edit, rewrite, or draft natural prose while preserving facts, formatting, intent, register, and author voice.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.