toknt-optimize
793Skill Claude CodeCodex
Tokn't token optimization — recall compressed content and view stats.
11,815 tagged developer-tools, measured the same way as everything else here.
Browse within: ai-coding 362cli 273LLM 262Multi-Agent 178agentic-coding 170Autonomous Agents 158agent-orchestration 134ai-agent-framework 124copilot 117ai-coding-assistant 106code-quality 103agents 90mcp-server 88vibe-coding 87
Skill Claude CodeCodex
Tokn't token optimization — recall compressed content and view stats.
Skill Claude Code needs its repo
Convene the relevant SpecRoute implementation agents to plan, collaborate, implement, and review a piece of work end-to-end. Engages only the specialists the work actually touches, runs autonomously through planning into implementation and review, and accepts free-text work or a path to a PRD / spec / issue file.…
Skill Claude CodeCodex
Consult KnownPath for evidence-grounded prior solutions to non-trivial debugging, unfamiliar or recurring technical errors, framework migrations, dependency conflicts, build failures, environment or version mismatches, native configuration problems, and tooling quirks. Use before spending significant time…
Skill Claude Code
Use when user asks "what exists for X?", before implementing custom MCP servers or plugins from scratch, or when browsing available tools — searches 19 sources and 15,000+ skills, plugins, and MCP servers in one query.
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring SwiftUI code — state management, view composition, performance, macOS-specific APIs, or iOS 26+ Liquid Glass adoption. Also triggers whenever an Xcode Instruments .trace file is referenced (to analyse it) or the user asks to record a new trace — attach to a running app…
Skill Claude CodeCodex
A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family. Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills (video-editing, fal-ai-media…
RaNDoM6913/claude-code-superkit
Skill Claude Code
SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.
Skill Claude CodeCodex
Implement same-repository GitHub Issues into a reviewed pull request, or review and fix an existing PR, iterating with fresh independent read-only native subagents selected adaptively from the change risk until no actionable feedback remains. Use for issue-to-PR implementation or iterative PR review/fix work.
Skill Claude CodeCodex
Use when an OpenClaw-style or local autonomous computer-use agent needs a single Neura Relay preflight workflow for messages, file changes, browser submits, shell commands, package or publisher changes, workflow state, memory writes, or data exports before execution.
Skill Claude CodeCodex
Drive Devloop — browser + dev-server on one correlated timeline (web, plus native iOS/Android Expo apps) — by calling its MCP tools as shell commands via mcporter. Use when Devloop's MCP server isn't wired into this agent directly (e.g. a sandboxed or enterprise setup that blocks MCP) but you can run shell commands.
Skill Claude CodeCodex
Comprehensive code review with security, performance, and style analysis for Python, TypeScript, and Go. Detects OWASP Top 10 vulnerabilities, N+1 queries, race conditions, and logic errors before they reach production.
Skill Claude Code
When the Frugal MCP server is connected (tools prefixed frugal), prefer its routed equivalents over native built-in tools. Frugal routes each call to a provider per the operator's routing policy (cheapest-first by default, with automatic failover) and surfaces the provider and cost in the response, so the routing…
Skill Codex
Use Codexa selectively for ambiguous, cross-cutting, or high-risk repository work that needs search, change planning, dependency context, or verification guidance beyond exact source inspection.
zxhwolfe-dev/aiworkstation-open-source-intelligence
Skill Codex
Use live AI Open Source Radar evidence to browse, discover, verify, compare and select open-source AI projects or plan candidate stacks. Use for Radar rankings and collections, project or license checks, alternatives, technology selection, stack planning, or the Radar Skills library; do not use for general AI news or…
Skill Claude Code
Parallel code implementation orchestrator. Breaks a task into independent work units, writes detailed specs, spawns parallel Task agents, reviews results, reports completion. Triggers on "/delegate", "/delegate [task]", "delegate this", "parallel implement".
Skill Claude Code
Use when entering REVIEW mode or when the user says "Enter RE". Validates plans or implementations by invoking specialist sub-agents based on what changed. Detects whether this is a post-plan review or post-execute review automatically.
Skill Claude CodeCodex
Challenges decisions, plans, and code by systematically arguing the opposing side. Surfaces risks, pokes holes in assumptions, and stress-tests thinking before committing. Supports intensity levels (gentle, balanced, ruthless, linus) and works with conversation context or a specific file reference. Trigger on requests…
Skill Claude Code
Close a work session — log what happened, update state and the decision log, propose durable memory updates, and check for uncommitted or unpushed work.
wrsmith108/claude-skill-version-sync
Skill Claude CodeCodex
Detect and synchronize Node.js version specifications across project files.
Skill Claude Code
How to cut a CLAUDE.md without losing a fact — the four-bucket taxonomy, the trigger-line shape that makes an extracted skill actually load, the gitignore prerequisite, and the line-coverage check that must be made to fail once. Load before editing, restructuring or pruning any CLAUDE.md, or when claude-md-weight.sh…
Skill Claude CodeCodex
Turn a plan, report, dataset, or explanation into a self-contained visual artifact - a single offline HTML file (default) or a PDF. Use on demand when a wall of markdown is hard to read, when a plan or spec needs reviewing before approval, when data needs a chart or dashboard, or when the deliverable must be a PDF.…
Skill Claude Code
Comprehensive pre-release audit for making a GitHub repository public.
Skill Claude CodeCodex
Cross-session task memory and stagnation detection for Claude Code, backed by a local context-bridge server that auto-starts on session start. Use when hook output tagged [context-bridge] appears, when the user says "checkpoint", "sync context", or "remember this for next session", when a task keeps reappearing…
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: