TokenOracle

Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

Persistent project-aware memory for AI coding tools. Built on MCP. Works with Codex, Claude Code, and other MCP-compatible clients.

cascadeflow

OpenClaw-native domain cascading. Use when users need cost/latency reduction via cascading, domain-aware model assignment, OpenClaw-native event handling, and command setup including /model cflow and optional /cascade stats commands.

frontend-impl-playbook

Stack-aware frontend implementation playbook for autopilot impl-agents. When a task touches *.tsx/*.jsx/*.css files, dispatchers prepend this playbook to the agent's brief so the first draft already meets the design-quality floor (reuse existing primitives, design tokens only, four states by default, accessibility baseline, mobile-first). Read this skill manually before implementing UI changes if your autopilot version does not auto-attach it yet.

semantic-compression

Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments. Use when compressing text for prompts, reducing token count, preparing context for LLM input, or making documentation more token-efficient. Applies LLM-aware compression rules that delete predictable grammar while preserving semantics.

memory-bank

Token-efficient persistent memory system for Claude Code that extends your session limits by 3-5x. Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.

accounting-finance-controller

Use for accounting, bookkeeping, ERP finance, POS, inventory, payroll, billing, financial reporting, IFRS-aware workflows, management accounting, cost accounting, budgeting, valuation, controls, reconciliations, and finance-system design. Produces controller-grade requirements, implementation guidance, review findings, and financial logic so business software can replace QuickBooks/Tally-class workflows where appropriate.

tsa-find

Fast file + content search with code-aware sizing. Replaces Read/Grep/find for routine "where is this file" / "grep for X" / "show me lines 10-20 of Y" questions. Returns file paths + line numbers + a sized chunk, not the whole file. Use when: - "Find files matching <pattern>" / "show me all *.yml under config/" - "Grep for 'TODO' / 'FIXME' / 'TODO\\(perf\\)' / regex anywhere" - "How big is <file>" / "is this file too large to read fully" - "Show me lines 50-80 of <file>" / "read just the relevant slice" - "Find all files matching name + containing string" Replaces: native find + grep + cat invocations (~3-10k tokens for big repos) with single MCP calls (200-500 tokens).

Codeweaver

Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.

shadcn-svelte — Component-Aware Svelte UI Assistant

Use the right shadcn-svelte components when building UI in SvelteKit projects. This skill detects your project setup, shows what's available, and gives you access to full component documentation.

agent-onboarding

Onbard yourself to this repo that might have X number of other agents running on it. Whenever you are starting off or asked to onboard to team use this skill to give yourself extra awareness of multi-agent and worker context, as well as goals and identity.

Io.Github.Digital Threads/Token Pilot

Save up to 80% tokens when AI reads code via AST-aware structural reading

sync-awareness

Suggest syncing MCP server configurations or instruction files to other AI coding agents when the user is editing MCP settings (.claude.json, .mcp.json) or modifying CLAUDE.md files. Available commands: /sync, /sync-list, /sync-diff, /sync-instructions.

Session Monitoring

Provides awareness of claudectl session state, health checks, and cost tracking. Activated when the user asks about session health, spending, brain decisions, or multi-session coordination.

Pre-Commit Code Verification

Automated verification pipeline before code lands. Static scans, baseline-aware quality gates, an independent reviewer subagent, and an auto-fix loop.

vgv-accessibility

Flutter accessibility auditing and remediation with WCAG 2.1 level selection (A, AA, AAA) across mobile, desktop, and web platforms. Use when building, auditing, or reviewing widgets for screen reader support, touch targets, focus management, color contrast, text scaling, or motion sensitivity. Begins by asking the WCAG conformance level and target platform(s) before applying level-appropriate, platform-aware criteria.

nreki-optimizer

AST-aware context firewall for AI coding agents. Compresses code, validates edits before disk writes, detects blast radius, and enables atomic multi-file refactoring.

Self Awareness Game

Play self-awareness scenarios across 7 levels. 6,800+ coaching scenarios via MCP.

build-agent

Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.

algorithm-selection

Implements candidate-model selection logic that runs after a routing decision matches, including model ranking, cost-aware routing, and latency-aware model choice. Use when reading or modifying how the router picks which model serves a matched decision.

Pharaoh

Codebase knowledge graph — architectural awareness for AI coding agents via MCP

awq-quantization

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Agent Chat Drawing Skill

This is the compact instruction packet for skills-aware agents that need to draw directly in a chat transcript. The installable skill package lives at `skills/chat-drawing`.

Image Resolver

MCP server for context-aware royalty-free image search from Pexels and Unsplash

brand-pptx

Brand-aware PowerPoint engine. Use to (1) EXTRACT a company's brand from a .pptx template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE a new on-brand .pptx from an IntermediateDocument. Trigger on "extract our brand", "use our deck template", "generate a branded deck from our profile", or when a ./brand-kit exists. For one-off slide edits with no saved brand profile, use the normal pptx skill instead. NOT for .docx (brand-docx), .xlsx (brand-xlsx), or PDFs.

trace-mcp

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.

Context Mcp

Situational awareness — holidays, business hours, and platform status for timing-sensitive actions.

Mcp Cost Tracker Router

Real-time cost awareness for MCP agent workflows

edit-deterministic

Offload mechanical and type-aware edits to deterministic tools instead of LLM file-rewrites (P2). Use ast-grep --rewrite for repeated/mechanical transforms and Serena replace_symbol for single type-aware symbol edits. Apply whenever a change is rule-shaped rather than judgment-shaped.

a11y-validate

Validate code against accessibility standards: WCAG 2.1 Level AA, EN 301 549, and the European Accessibility Act (EAA / Directive EU 2019/882). Covers semantics, text alternatives, keyboard/focus, color/contrast, forms, media, ARIA, motion, mobile, and EAA documentation requirements. Framework-aware (React/Next/Nuxt/Astro/Gatsby/SvelteKit/Remix/Angular/Vue/React Native/Flutter/static HTML).

design-motion-principles

Expert motion and interaction design auditor based on Emil Kowalski, Jakub Krehel, and Jhey Tompkins' techniques. Use when reviewing UI animations, transitions, hover states, or any motion design work. Provides per-designer perspectives with context-aware weighting.

claude-rig Awareness

claude-rig lets users run multiple independent Claude Code configurations side by side. Each configuration is called a **rig**. When a rig is active, Claude Code doesn't use `~/.claude/` directly — it uses the rig's directory instead.

anti-slop-design

Category-aware design skill that builds distinctive, production-grade UIs. Palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, and a pre-ship second pass. Framework-agnostic.

Io.Github.Samouh Waleed/Prompyai

Scores your prompts against your real codebase — context-aware prompt intelligence

Time Mcp

Time MCP Server, giving LLMs time awareness capabilities.

prompt-sensei

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

Addiction Awareness Log

Quand l'utilisateur s'interroge sur un comportement potentiellement addictif, suis ce workflow.

smart-web

Portable MCP server for fallback web search, browser-aware fetch, and local site crawling.

spyc

Work inside spyc, the vi-keyboard terminal file/worktree manager, using its MCP tools instead of shell equivalents. Use for git worktree lifecycle (create/open/list/remove, never `git worktree`), gitignore-aware filename and content search (instead of `find`/`rg`/`grep`), in-process git status/log/diff (instead of shelling to git), reading and driving what the user is looking at, reporting agent status to the pane tab, and coordinating file scopes with other agents before editing or merging.

ast-introspection

Use Go AST-aware analysis to enumerate symbols, extract signatures, and propose mechanically safe refactors (read-only by default).

Clayrune API surface

Clayrune runs locally at **http://localhost:5199**. Every Clayrune-aware operation is a curl call to this base URL.

mechanical-engineering-research

Research, write, code, analyze, present, and develop proposals for thermal-fluid mechanical engineering work with source-aware rigor. Use for heat transfer, fluid mechanics, thermodynamics, HVAC, energy systems, turbomachinery, pumps, piping, CFD, experiments, correlations, standards, datasheets, papers, patents, AI/ML tools, computer vision, sequence regression, surrogate modeling, research coding, Overleaf, VS Code, GitHub, git, federal grant proposals, DOE/NSF/NASA-style narratives, invention disclosure, provisional patent support, commercialization, and trade studies. Produces technical briefs, critical literature reviews, proposal narratives, review-criteria responses, manuscript sections, methods, results discussions, data-analysis plans, plots, presentations, design comparisons, calculation plans, reproducible code, repository workflows, disclosure drafts, patent-support packets, and research roadmaps.

wow-assistant

Context-aware World of Warcraft lore, progressive hints, builds, and PvP/PvE guidance using the Nanocodex WoW companion's exported character snapshot.

security-awareness

Teaches AI agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building agents that access email, credential vaults, web browsers, or sensitive data.

i18n-agent

AI-powered translation for 48 languages with context-aware quality

Io.Github.Madhan G P/Devdocs Mcp

Local DevDocs MCP Server (Developer Docs with project specific context awareness)

a11y-ally

Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.