Observed Signal · Apr 27, 2026 · Product Launch · Source: DEV Community · Impact: 2/5 · Sentiment: Neutral
skill-tree: Claude plugin finds avoided behaviors
skill-tree is a developer tool distributed as a Claude Code plugin that analyzes a user's Claude session history against Anthropic's AI Fluency Index (the 11 observable behaviors from the 4D AI Fluency Framework). It classifies user messages, assigns an archetype card, and generates a targeted growth quest that deliberately highlights behaviors the user has never triggered. Installation examples use the Claude plugin marketplace and an MCP server is available via npm for Cursor, VS Code, and Windsurf. The orchestration pipeline (session discovery → extraction → classification → rendering) runs in about 30–60 seconds and returns a hosted URL. The project is published on GitHub at github.com/robertnowell/skill-tree and references Anthropic’s February 2026 study of 9,830 conversations as the population baseline.
A niche developer tool for measuring and improving user behavior with a specific LLM (Claude); relevant to conversational AI best practices but not industry-shifting for AdTech/MarTech.
Track Anthropic Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- skill-tree installs as a Claude Code plugin and reads a user's Claude session history to classify messages against 11 behaviors.
- The classification uses the same 11 observable behaviors defined in the 4D AI Fluency Framework and used as Anthropic's AI Fluency Index baseline in a February 2026 study of 9,830 conversations.
- Output includes an archetype card (seven archetypes) and a growth quest that targets the behavior with the lowest occurrence in the user's history.
- The tool runs a 7-step orchestration pipeline in ~30–60 seconds and returns a hosted URL; a live fixture example is at skill-tree-ai.fly.dev/fixture/illuminator.
- An MCP server distribution is available via npm (npm install skill-tree-ai) for Cursor, VS Code, and Windsurf; source is at github.com/robertnowell/skill-tree.
Connected Companies & Entities
4 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Generate Claude Code Skills from Git History
A developer guide describing how to generate reliable, auto‑triggering Claude Code skills by mining your git history and conversation/correction artifacts. The post explains commands to surface frequent commit types and commonly touched files, argues that git logs reveal real task frequency while conversation history (memory files, CLAUDE.md commits, workflow/docs commits) reveals constraints and friction, and gives a minimal SKILL.md structure plus three concrete skill examples (blog-article, veille-debug, blog-fix). The author emphasizes precise trigger descriptions, one-skill-per-context, and encoding non-obvious rules to reduce false positives and repeated re-explanations across agent sessions.
Guide: How to Build and Optimize Claude Skills
This guide explains how to build, test and optimize Claude Skills — permanent, reusable instruction files that automate tasks for Anthropic's Claude models. A Skill is a local folder containing a case-sensitive SKILL.md (with YAML frontmatter) and optional references/scripts; folders use kebab-case and are placed in ~/.claude/skills/ so Claude can auto-detect them. The guide covers writing aggressive YAML trigger descriptions, defining precise triggers and quality standards, workflow structure, edge-case handling, using scripts for precise computation, and handover patterns for session continuity. It also describes Skills 2.0 capabilities — evaluation frameworks, A/B testing, and automated description optimization — plus a meta-skill called skill-creator that can generate, evaluate and benchmark Skills (including tests that compare a Skill against raw Claude). The piece emphasizes iterative testing and clear non-overlapping Skill territories.
Indexing 2,000 Claude Code Skills by Installs
A developer built orangebot.ai/skills, a ranked, filterable index of 1,998 public Claude Code skills sorted by weekly install volume, and describes the stack, SEO fixes, and what install data reveals about AI coding in 2026. The site uses a static JSON pipeline (skills_index.json) regenerated by a daily Python scraper, a Next.js 16 App Router front end with server-rendered top lists and client interactive islands, and Firebase hosting. The author published four commits (shipped 2026-05-23) to SSR key pages, clean the sitemap, add visible navigation, and create 50 skill detail pages. Install data shows a power-law distribution (top publishers: Microsoft, inferen-sh, Vercel) and the #1 skill—find-skills (vercel-labs)—at 753,732 weekly installs, suggesting discovery skills and curated publisher bundles are major distribution levers for agent ecosystems.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.