Skilled

Dashboard to find agent skills you no longer need

Vibe codingDeveloper ToolsArtificial IntelligenceGitHub

▲ 71 votes3 commentsLaunched May 20, 2026

Visit Website

Daily #20Weekly #70Monthly #7171

Your AI coding tools keep traces. Skilled reads them. Live TUI dashboard that aggregates skill usage across Claude Code, OpenCode, Codex, Grok, and Droid. Reads local history files only. Zero network, zero telemetry. Frequency counts, weekly trends, hourly distribution, per-project breakdowns, and audit heuristics (rising = 50%+ increase over 4 weeks, stale = unused 30+ days, etc.). No data leaves your machine. No accounts, no config files, no API keys.

AI Analysis

📝 Summary

Skilled is a privacy-first local TUI dashboard that aggregates AI coding agent skill usage across tools like Claude Code, OpenCode, Codex, Grok, and Droid. It reads only local history files to deliver frequency counts, weekly trends, hourly distributions, per-project breakdowns, and audit heuristics (e.g., rising skills with 50%+ increase, stale if unused 30+ days). Core USPs include zero network, zero telemetry, no accounts or API keys - ensuring no data leaves the machine. It solves the user pain of accumulating unnecessary skill traces from AI tools that clutter workflows and are hard to track. The value proposition is enabling developers to audit, optimize, and declutter their AI coding stack efficiently and privately.

📈 Market Timing

In 2025-2026, explosive growth in AI coding agents and multi-tool usage creates strong demand for usage analytics, while rising privacy concerns and local-first preferences align perfectly with Skilled's design. AI technology maturity enables reliable local parsing, and developer focus on efficiency makes it highly relevant. Excellent Timing.

✅ Feasibility

Technically low difficulty: involves parsing known local history files and building a lightweight TUI with no backend, network or cloud dependencies. Minimal dev/operation costs, no supply chain or data compliance risks due to zero telemetry. Excellent team fit for solo developers and high scalability for personal use. Rating: High.

🎯 Target Market

Primary segments: AI-powered software developers, indie hackers, and engineers using multiple coding agents (demographics: tech professionals aged 25-45). Industries: software development, open-source, AI tooling. Geographic: global with concentration in US, Europe. Estimated market size: large and expanding AI developer tools TAM, with SAM for agent analytics in millions of active users. Core pains: invisible skill bloat and inefficiency. High willingness to pay for productivity tools that respect privacy.

⚔️ Competition

Low. Direct competitors: 1. Helicone (helicone.ai), 2. LangSmith (smith.langchain.com), 3. Phoenix by Arize (arize.com/phoenix), 4. PromptLayer (promptlayer.com). Skilled's advantages: complete local/offline operation with zero data exfiltration, simple TUI focused specifically on skill auditing and cleanup vs broad cloud observability. Disadvantages: lacks team collaboration, advanced visualizations or cloud integrations offered by competitors.

Upgrade Pro to unlock full AI analysis