Claude Skills by the-hugin

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when reviewing academic papers, conducting literature reviews, formatting citations (APA/MLA/Chicago), or writing research summaries.

**Purpose:** Quick reconnaissance of API endpoint parameters before implementation — find what actually works (filters, pagination, limits, auth) via minimal test requests. **When:** Integrating with a new endpoint where unknown: which params it accepts, pagination type, whether it works without mandatory filters, actual response limit. **Output:** Table of "works / doesn't work" + recommended call pattern for implementation. ---

Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.

Configure notification integrations (Telegram, Discord, Slack) via natural language

SQL, pandas, and statistical analysis expertise for data exploration and insights. Use when: analyzing data, writing SQL queries, using pandas, performing statistical analysis, or when user mentions data analysis, SQL, pandas, statistics, or needs help exploring datasets.

Transform raw data into persuasive business narratives using Setup→Conflict→Resolution framework. Templates for problem-solution, trend analysis, and comparison stories. Use when presenting data to stakeholders or building data-driven reports.

Unified design mega-skill for all artifact types: web pages, landing pages, dashboards, UI components, posters, graphics, and interactive artifacts. Combines best practices from frontend-design, ui-ux-pro-max, canvas-design, and web-artifacts-builder with a built-in quality gate.

Security-focused review of code changes (PRs, commits, diffs) with blast radius estimation and adversarial modeling. Seven-phase workflow from triage to final report. Adapted from Trail of Bits methodology.

**Purpose:** Universal onboarding for creating any structured documents — portfolio guides, comparison tables, training materials, catalogs, reports, presentations. Output: HTML→PDF, DOCX, Slides. **When:** User wants to create a document, guide, or presentation from sources (docx, PDF, website, data). Any type. **Output:** Agreed document structure + chosen design + ready generator or file. ---

Full deploy cycle for Docker projects with baked images: sync files, rebuild image, start containers, verify new code, check app health.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-stage builds.

Electron desktop application development with React, TypeScript, and Vite. Use when building desktop apps, implementing IPC communication, managing windows/tray, handling PTY terminals, integrating WebRTC/audio, or packaging with electron-builder. Covers patterns from AudioBash, Yap, and Pisscord projects.

**Purpose:** Extract brand hex color palette from image-based PDF or PNG via pixel sampling (PyMuPDF). Used as utility inside `doc-creator` and standalone. **When:** Need exact brand colors from a PDF presentation, landing page, logo, or any raster source — and standard text parsing returns nothing. **Output:** List of hex values (Primary / Secondary / Accent) + ready CSS variables. ---

Use when adding new error messages to React, or seeing "unknown error code" warnings.

Systematic fact-verification framework for identifying misinformation. Evaluates claims against credible sources, rates accuracy with confidence levels, and exposes manipulation tactics (cherry-picking, false equivalences, logical fallacies).

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

**Purpose:** Update skills based on `~/.claude/reflection.md` and user's correction string. Closes the self-improving loop. **When:** After user has filled the correction string in `~/.claude/reflection.md`. **Output:** Updated skills (explicit approval per change) + updated `~/.claude/skills/index.md`. ---

Detects fail-open vulnerabilities where applications run insecurely with missing configuration. Finds hardcoded credentials, weak env var fallbacks, and insecure-by-default settings. Adapted from Trail of Bits methodology.

**Purpose:** Onboard a new project — asks 4 questions and generates a filled `CLAUDE.md` with Security Constraints. **When:** At the start of every new project, before writing any code. **Output:** Ready `CLAUDE.md` in project root. Not a template — concrete data. ---

KPI framework for business dashboards — metric selection, hierarchy (strategic/tactical/operational), SQL templates for MRR/retention, Streamlit examples. Use when designing or reviewing business dashboards and metrics.

**Purpose:** Bring existing CLAUDE.md to current intake standard without losing data. **When:** After validate-claude-md found issues; on standard change; onboarding old project. **Output:** Updated CLAUDE.md with added sections and fixed placeholders. Each change confirmed. ---

Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures

PostgreSQL best practices for query optimization, schema design, indexing, RLS, and connection management. Includes Drizzle ORM patterns for TypeScript — schema definition, type inference, query builder style. Based on Supabase and lobehub guidelines.

Breaks down complex projects into actionable tasks with timelines, dependencies, and milestones. Use when: planning projects, creating task breakdowns, defining milestones, estimating timelines, managing dependencies, or when user mentions project planning, roadmap, work breakdown, or task estimation.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

**Purpose:** Analyze completed session/project — creates `~/.claude/reflection.md` as input for Improve. **When:** At end of each significant session. Required at project end. **Output:** `~/.claude/reflection.md` (global, not in project folder) + entries in `~/.claude/memory/episodic/hard-problems.md` for hard cases. ---

**Purpose:** Collect local RSIm skill improvements (skills/ + commands/) and publish to GitHub as a PR. **When:** After improve cycles with accumulated skill changes. Auto-suggested after `/improve`. Reminded at session start if > 7 days since last export. **Requirements:** `gh` CLI installed and authorized (`gh auth login`), `git` installed. ---

**Purpose:** Pull RSIm skill updates from GitHub releases and apply locally — with security scan and per-change approval. Preserves local memory/. **When:** Periodically to receive improvements. Reminded at session start if > 14 days since last sync. **Requirements:** `gh` CLI installed and authorized, `git` installed. ---

**Purpose:** Onboarding and creation of product / portfolio guides from documents (docx, PDF, website). Fixed question checklist at start, vendor/product card template, final output as HTML/PDF. **When:** User wants to create a Sales Guide, Product Guide, Partner Catalog, or similar structured document from source materials. **Output:** Structured HTML/PDF guide with vendor/product cards, branded design, and contact information. ---

Search the internet and news using a local SearXNG instance. Use when the user wants to search the web, find current information, search for news, or research a topic without depending on third-party APIs.

**Purpose:** Add SECURITY section to project `CLAUDE.md`. Canary token, stop-ops, prompt injection signals — one command. **When:** - Starting a new project (after `intake`, before first work session) - Project works with external APIs or user data - On command `/security-baseline` **Output:** `SECURITY` section inserted at start of `CLAUDE.md` (right after the title). ---

**Purpose:** Create a new skill using the standard system template. **When:** Improve Skill proposes a new skill, or user wants to automate a recurring action. **Output:** Ready `~/.claude/skills/[name]/SKILL.md` + row in `~/.claude/skills/index.md`. ---

Create new Claude Code skills with proper structure and best practices. Use when the user wants to create a new skill, extend Claude's capabilities, or needs help structuring a SKILL.md file.

Manages context in long sessions by suggesting /compact at logical task boundaries — after research phases, debugging, or phase transitions. Prevents losing critical context mid-implementation.

**Purpose:** Analyze a service or project at phase transitions — identify what's working, what's broken, and what to build next. Produces a prioritized feature roadmap grounded in real metrics. **When:** At phase transitions in plan.md, when metrics degrade, or when the backlog needs re-prioritization. **Output:** Structured markdown report delivered in chat (no file written). ---

**Purpose:** Catalog of ready-to-use HTML/CSS/JS components for dashboard projects. Insert components directly — no reinventing each time. **When:** Building a dashboard, admin panel, or monitoring UI in plain HTML/CSS/Jinja2. **Output:** Ready CSS + HTML markup + formulas for each component. ---

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Style...

**Purpose:** Automatically check project CLAUDE.md for compliance with current intake standard. **When:** At session start when reading CLAUDE.md; after updating intake standard; before running reflect. **Output:** Report of issues found + offer to run migrate-claude-md if needed. ---

Post-deploy verification of a deployed web application. Reads credentials from update.py, fetches key pages, checks HTTP status and expected HTML elements, outputs a pass/fail table.

Scrape web pages, search the internet, and extract structured content using Python. Includes anti-bot/Cloudflare bypass via Scrapling. Use when the user wants to fetch a webpage, search for information online, extract links, crawl JS-rendered pages, or bypass bot protection.