jdrhyne/agent-skills

Auto Updater sets up a daily cron job to update OpenClaw and installed skills, then sends a summary of what changed. Use it to keep an agent environment current with minimal manual maintenance.

Autoresearch Loop runs a metric-driven propose, trial, keep-or-revert cycle for improving a project against a measurable objective. Use it when you want an agent to discover metrics, test changes, and record which ideas help or hurt.

Codex runs the Codex CLI for code analysis, refactoring, and automated edits. Use it when a user asks to execute Codex sessions or continue a previous Codex task.

Command Creator guides you in building Claude Code slash commands for reusable workflows. Use it when creating a new command to define the location, structure, arguments, and step-by-step instructions.

Context Recovery restores the smallest needed conversation history after compaction or truncation. Use it when prior work is missing and the current thread is not enough to continue safely.

Design Audit reviews existing UI screens and components for hierarchy, spacing, typography, color, responsiveness, and accessibility. Use it when you want a phased design plan before changing a product’s visual design.

Elegant Reports generates minimalist PDF reports with a Scandinavian editorial look from markdown or HTML. Use it for executive briefings, analysis reports, and presentation-style PDFs.

Frontend Design provides guidelines for planning layouts, themes, animations, and responsive implementation for UIs. Use it when building landing pages, dashboards, or other frontend interfaces.

GA4 Data API reads Google Analytics 4 metadata and bounded reports through the Data API. Use it for compatible metric/dimension queries, traffic analysis, key events, and quota-aware exports.

Gallery Scraper bulk downloads images from authenticated gallery pages using an attached browser session. Use it to scrape full-size images from thumbnails, follow pagination, and save selected galleries or profiles.

Gemini runs Gemini CLI for code review, plan review, and large-context analysis. Use it when you need to inspect many files or work with contexts over 200k tokens.

Gong reads call metadata, bounded transcript excerpts, users, and activity statistics from Gong. Use it when you need to inspect sales calls, transcripts, meeting data, or conversation analytics without modifying anything.

Google Ads analyzes campaigns, keywords, budgets, conversion tracking, and wasted spend in read-only mode by default. Use it for audits or for reviewed account changes that require a bounded preview and action-time approval.

Google Search Console reads Search Console properties, Search Analytics, URL Inspection, and sitemaps for SEO performance, indexing, and freshness analysis. Use it for explicit GSC investigations, not general web search.

Humanizer removes common AI writing patterns and rewrites text to sound more natural. Use it when editing or reviewing drafts that feel stiff, generic, or overprocessed.

Jira reads, searches, drafts, creates, and updates Jira work through an authenticated Jira backend. Use it only when you have explicit Jira context, a Jira URL, or a Jira-style issue key such as PROJ-123.

Knowledge Graph maintains an append-only entity store with atomic facts and short summaries. Use it to remember durable context about people, companies, and projects across sessions.

Munger Observer reviews a specific decision, plan, or artifact using bounded evidence, counterevidence, alternatives, and verifiable next checks. Use it for decision reviews, premortems, and blind-spot reviews without assessing a person’s character or mental state.

OpenClaw Docs helps navigate OpenClaw documentation, find relevant pages, and fetch config snippets or troubleshooting steps. Use it when answering setup, feature, automation, or version questions about OpenClaw.

OpenClaw Release Check checks GitHub for new OpenClaw releases and notifies once per version. Use it for scheduled update monitoring without repeated alerts.

Self-Improving Agent captures durable learnings, errors, and feature requests in a local knowledge base. Use it before major tasks or after failures and corrections so the same issue is less likely to repeat.

Senior Engineering Principles guides planning, implementation, and review for non-trivial software work. Use it when architecting systems, breaking down tasks, adding quality gates, or coordinating multi-agent builds.

Skill Sync manages skills between a local installation and a canonical source repository. Use it to list, install, update, or push skills through a GitHub-based workflow.

Todo Tracker maintains a portable Markdown task file for adding, listing, completing, removing, and summarizing tasks across sessions. It uses stable task IDs and exact matching, with optional count-only heartbeat reporting.

Web Interface Guidelines reviews UI code against the latest web interface rules and reports findings in terse file:line format. Use it for UI reviews, accessibility checks, design audits, and best-practice checks.