Skills from softaworks/agent-toolkit

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

This skill documents creating Mermaid diagrams with examples for class, sequence, flowchart, ERD, C4, theming, and export workflows. It includes explicit shell commands like `npm install -g @mermaid-js/mermaid-cli` and `docker run --rm -v $(pwd):/data minlag/mermaid-cli -i /data/input.mmd -o /data/output.png`, network imports such as `https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.esm.min.mjs` and `https://mermaid.live`, and an example storing a token in `localStorage`.

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

The skill automates creation, validation, and resumption of agent handoff documents using scripts such as `scripts/create_handoff.py` and stores files under `.claude/handoffs/`. It directs executing local scripts (e.g., `python scripts/create_handoff.py`) and environment checks (e.g., `env | grep [relevant-var]`), requiring filesystem and env access.

Dangerous skill: hides command output (`2>/dev/null`) while instructing execution of `codex exec` commands and cloning `git@github.com:skills-directory/skill-codex.git`. It advertises integration with the Codex CLI for automated code analysis and edits.

Generates QA deliverables: test plans, manual test cases, regression suites, Figma design validations, and structured bug reports. Contains interactive shell scripts `./scripts/generate_test_cases.sh` and `./scripts/create_bug_report.sh` and references `Figma MCP` which requires an API token.

This skill generates memes via the `https://api.memegen.link` API and includes a Python helper `scripts/meme_generator.py` for URL construction. It contains runnable examples that invoke shell commands (e.g., `curl -I "https://api.memegen.link/images/buzz/test/test.png"`, `python meme_generator.py generate …`) and makes network calls to `https://api.memegen.link`.

High-risk skill: runs shell commands (`gemini -m gemini-3-pro-preview --approval-mode yolo`, `timeout 300 gemini ...`, `pkill -9 -f "gemini.*gemini-3-pro-preview"`) and thus enables arbitrary execution. The skill is presented as a wrapper to run `Gemini CLI` for large-context code and plan reviews.

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues.

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

`skill-judge` evaluates SKILL.md files across eight dimensions and produces scored, actionable reports. The document contains explicit local execution instructions (e.g., `pandoc --track-changes=all`, `scripts/create-doc.py`) which are purpose-aligned but constitute shell execution.

Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.

Dangerous skill: silently probes local integrations and executes local commands that access `~/.claude/projects` and run `python3 ~/.claude/skills/daily-meeting-update/scripts/claude_digest.py`, while invoking `gh auth status` and `jira`. It claims to generate daily standup updates from GitHub, Jira, and Claude Code history with user consent.

This skill guides manual reduction of codebase size and requires loading at least one mindset from `references/` before proceeding. No security-relevant behaviors detected.

Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.

This skill assists in creating Claude Code slash commands and specifies structure, naming, and storage locations (`.claude/commands/` or `~/.claude/commands/`). It instructs agents to execute shell commands (e.g., `make all-ci`, `git add .`, `git commit -m`) and to write/modify files in those command directories.

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.

Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.

Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure, create C4 diagrams, or generate context/container/component/deployment diagrams. Triggers include "architecture diagram", "C4 diagram", "system context", "container diagram", "component diagram", "deployment diagram", "document architecture", "visualize architecture".

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer

This skill should be used when building React components with TypeScript, typing hooks, handling events, or when React TypeScript, React 19, Server Components are mentioned. Covers type-safe patterns for React 18-19 including generic components, proper event typing, and routing integration (TanStack Router, React Router).

Design robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns, constraint design, and performance optimization. Ensures data integrity, query performance, and maintainable data models.

Suggest better variable, function, and class names based on context and conventions.

Converts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. This skill should be used when the user asks to generate types from OpenAPI, convert schema to TS, create API interfaces, or generate TypeScript types from an API specification.

Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.

React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

This skill provides natural-language control of Jira using CLI and MCP backends (commands like `jira issue view` and `mcp__atlassian__getJiraIssue`). It instructs executing shell/CLI commands (e.g., `which jira`, `cat > /tmp/jira_body.md`) and using credentials in `JIRA_BASE_URL`, `JIRA_USER`, and `JIRA_API_TOKEN`.

This skill converts vague requirements into iterative clarification sessions and generates a final PRD saved to `./docs/prds/{feature-name}-v{version}-prd.md`, ensuring the `./docs/prds/` directory exists. No network access, credential usage, or shell/command execution is instructed in the skill content.

Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

This skill provides draw.io `.drawio` XML editing, layout guidance, AWS icon lookup, and PNG conversion utilities. It includes explicit shell commands such as `bash ~/.claude/skills/draw-io/scripts/convert-drawio-to-png.sh` and `drawio -x -f png -s 2 -t -o`, with no other security-relevant behaviors detected.

Document frontend data needs for backend developers. Use when frontend needs to communicate API requirements to backend, or user says 'backend requirements', 'what data do I need', 'API requirements', or is describing data needs for a UI.

This skill generates design-system guidance, tokens, and component templates (e.g., `templates/design-tokens-template.json`, `templates/component-template.tsx`). No security-relevant behaviors detected.

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.

Converts webpages to Markdown using a local `web2md` CLI and a Puppeteer-driven browser. It instructs running shell commands like `command -v web2md` and `cd ~/workspace/softaworks/projects/web2md && npm install && npm run build && npm link`, uses `--user-data-dir ./tmp/web2md-profile`, and accesses arbitrary `http://`/`https://` URLs.

Material-UI v7 component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks. Use when working with MUI components, styling with sx prop, theme customization, or MUI utilities.

High-risk skill for Datadog debugging that runs shell commands via `npx @leoflores/datadog-cli`. It requires `DD_API_KEY` and `DD_APP_KEY`, reads/writes files like `/tmp/dashboard.json`, and will contact `app.datadoghq.com`/`datadoghq.eu`.