Observed Signal · Jul 16, 2026 · Technical Release · Source: DEV Community · Impact: 1/5 · Sentiment: Positive

Review: mattpocock/skills — Engineer's Claude Skills, 160k Stars

Executive Signal Summary

This article reviews the public GitHub repository mattpocock/skills, a .claude directory opened by TypeScript educator Matt Pocock that contains about 36 Claude Code "skills" grouped into engineering and productivity categories. The repo has attracted over 160,000 GitHub stars because it exposes real, working prompts and workflows used by an experienced engineer rather than a polished product. The review highlights standout skills (diagnosing-bugs, tdd, grilling, codebase-design), describes the v1.1 update (including the promotion of wayfinder and several renames), and explains installation options (npx installer or clone+symlink) plus guidance on remixing individual skills rather than adopting the whole set.

Polaris7 AgentPolaris7 Strategic Assessment
High Confidence

Community repository exposing practical LLM skills for engineers is useful to practitioners but is a niche developer resource and not industry-shifting for AdTech/MarTech.

SIGNAL RADAR

Track GitHub Signals & Market Shifts in Real-Time

Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.

Start Monitoring
Verified primary sourcesAutomated briefingsInstant watchlist setup

Key Takeaways & Evidence Grounding

  • mattpocock/skills is a public GitHub repository containing around 36 Claude Code skills.
  • The repository has over 160,000 GitHub stars.
  • The repo groups skills into categories; the review lists Engineering (14) and Productivity (5) skill names.
  • Version v1.1 was shipped; changes included graduating wayfinder to a full skill, renaming to-prd → to-spec and to-issues → to-tickets, renaming diagnose → diagnosing-bugs, and dropping caveman.
  • Installation options include running `npx skills add mattpocock/skills` or cloning and symlinking the repo to keep in sync.

Ontology Mapping & Concepts

Large Language Models (LLM) & AI#.claude directory#wayfinder
Primary Source Grounding & Direct Attribution
Direct Origin Attribution
Primary Reporting: DEV Community•Published: Jul 16, 2026
Original Coverage Title: “mattpocock/skills review: a real engineer's .claude, 160k stars”

Related Market Signals & Shifts

Recent verified developments and strategic activity across this market segment.

Large Language Models (LLM) & AIApr 28, 2026

Matt Pocock’s Claude Code Skills Repo Goes Viral

Matt Pocock published his personal Claude Code skill library (a .claude working directory named "skills") to GitHub. The repository contains 21 Markdown-based skill folders (each with a SKILL.md) that configure Claude Code agents for engineering workflows (examples: grill-me, tdd, triage-issue, design-an-interface). The repo was adopted rapidly on GitHub—about 22,000 stars in the first 24 hours and more than 30,800 stars overall—and reached GitHub Trending #1 globally. The project is installable via an npx command and is released under the MIT license. Observers framed the event as an "npm moment" for Claude Code Skills, signalling a community shift toward sharing reusable AI-agent configuration and treating agent configuration as an engineering artifact.

Read assessment
Large Language Models (LLM) & AIJun 14, 2026

Two Claude Code Skills Fix Agent Guessing and Reviews

A developer published two open-source Claude Code skills — 'spec' and 'review-audit' — designed to reduce common failures of coding agents. 'spec' prompts the user with a 13-section template and multiple-choice questions to resolve ambiguities up front, performs a fresh-context self-check, and enforces executable acceptance criteria. 'review-audit' is a read-only, single-pass audit covering six axes (correctness, wiring, security, test efficacy, spec compliance, regression) and requires concrete file:line or run evidence before marking an axis audited; it runs in the caller's context. Both skills are distributed as single prompt files (Apache-2.0), have no dependencies, make no network calls or telemetry, and are available on GitHub (dualform-labs). Installation instructions clone each repo into ~/.claude/skills/.

Read assessment
Large Language Models (LLM) & AIJun 6, 2026

Anthropic: Claude Code skills directory becomes hiring signal

A dev.to analysis of an Anthropic claude.com/blog post argues the most significant change from Claude Code’s "skills" model is cultural: skills checked into shared repos become a persistent portfolio and hiring signal. The article highlights three technical facts from Anthropic — skills live in repos/shared directories, dispatch selects skills via fuzzy matching against the description prose, and senior engineers are evaluated partly by how often their skills are used — and explains operational implications. It recommends concrete team actions: audit and instrument your skills/ directory, rewrite descriptions in a "dispatch-first" style, assign skill owners, run monthly skills reviews, and make skills part of interview evaluation. The piece frames this as a shift in what compounds for AI-native engineering teams: concise, well-written skill descriptions rather than long system prompts.

Read assessment
Executive Briefing & Watchlist

Receive all future signals for GitHub & competitors in your briefing

Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.

Daily primary source scansCurated executive briefingsUnsubscribe anytime