Skills from daymade/claude-code-skills

This skill fetches Twitter/X post content via the jina.ai proxy and provides `scripts/fetch_tweet.py` and `scripts/fetch_tweets.sh` for single or batch retrieval. It executes shell `curl` calls (via `subprocess.run` and the shell script) and requires reading `JINA_API_KEY` to call `https://r.jina.ai/{url}`.

High-risk skill: executes local commands and installs packages (e.g., `python scripts/chartkit.py`, `marp slides.md -o presentation_marp.pptx`, `npm install -g @marp-team/marp-cli`), enabling runtime script execution. It automates slide/chart generation and writes outputs to `/output/`.

This skill transforms vague prompts into precise, testable requirements using EARS and domain-theory grounding. No security-relevant behaviors detected; it references local files `references/ears_syntax.md`, `references/domain_theories.md`, `references/examples.md`, and `references/advanced_techniques.md`.

This skill provides a complete QA framework and autonomous LLM-driven test execution for projects, including templates, scripts, and a master prompt. It instructs executing shell commands (`python scripts/init_qa_project.py`, `rm -rf ~/.claude/skills/<skill-name>`), accessing `https://github.com/your-org/project.git`, and handling `.env` / `PATH` configuration.

Create PDF documents from markdown with proper Chinese font support using weasyprint. This skill should be used when converting markdown to PDF, generating formal documents (legal, trademark filings, reports), or when Chinese typography is required. Triggers include "convert to PDF", "generate PDF", "markdown to PDF", or any request for creating printable documents.

This skill provides i18n setup and an audit tool for React/TS projects, including `scripts/i18n_audit.py` and example search commands. It instructs running local shell commands such as `python scripts/i18n_audit.py --src <src-root> --locale <path/to/en-US.json>` and `rg -n --glob '<src>/**/*.{ts,tsx,js,jsx}' ...`, which is normal for a code audit and presents low risk.

This skill converts documents to Markdown with multi-tool orchestration via scripts such as `scripts/convert.py` and `scripts/extract_pdf_images.py`. It runs local conversion binaries via subprocess (e.g., `markitdown`, `pandoc`, `pdftotext`) on user-supplied files and writes outputs to paths like `output.md` and `assets/images_metadata.json`.

Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.

High-risk skill: provides macOS disk analysis and interactive cleanup recommendations using `mo analyze`/`tmux`. It contains explicit destructive commands and deletion code (e.g., `rm -rf ~/Library/Caches/*`, `shutil.rmtree(path)`) and instructs network installs like `brew install tw93/tap/mole`.

Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.

This skill provides search and installation commands for the CCPM registry and wraps the `ccpm` CLI. It instructs running shell commands such as `ccpm install <skill-name>` and `npm install -g @daymade/ccpm`, which perform network operations (e.g., `https://ccpm.dev`) and install packages.

Optimize CLAUDE.md files using progressive disclosure. Goal: Maximize information efficiency, readability, and maintainability. Use when: User wants to optimize CLAUDE.md, information is duplicated across files, or LLM repeatedly fails to follow rules.

Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.

This skill is a template and guide for creating Claude skills, including helper scripts and packaging/validation tooling. It instructs running `python scripts/security_scan.py`, invoking `gitleaks` via `subprocess.run`, downloading `https://github.com/gitleaks/...`, retrieving `https://platform.claude.com/...`, and recommends `os.environ.get("API_KEY")`.

Consolidates redundant documentation while preserving all valuable content. This skill should be used when users want to clean up documentation bloat, merge redundant docs, reduce documentation sprawl, or consolidate multiple files covering the same topic. Triggers include "clean up docs", "consolidate documentation", "too many doc files", "merge these docs", or when documentation exceeds 500 lines across multiple files covering similar topics.

Finds and recovers content from Claude Code session history files. This skill should be used when searching for deleted files, tracking changes across sessions, analyzing conversation history, or recovering code from previous Claude interactions. Triggers include mentions of "session history", "recover deleted", "find in history", "previous conversation", or ".claude/projects".

This skill extracts Mermaid diagrams from markdown and generates high-quality PNGs using bundled scripts (`./extract-and-generate.sh`, `extract_diagrams.py`, `puppeteer-config.json`). It instructs executing shell commands (e.g., `./extract-and-generate.sh`, `chmod +x`, `npm install -g @mermaid-js/mermaid-cli`, `wget https://dl.google.com/linux/linux_signing_key.pub`) enabling shell execution and network installs.

This skill provides GitHub operations using the `gh` CLI and GitHub APIs for PRs, issues, repos, workflows, and automation. It contains explicit shell commands (`gh ...`), requests tokens via `GH_TOKEN` and related env vars, and calls API endpoints like `repos/{owner}/{repo}/pulls`.

This skill documents configuring and running Promptfoo evaluations, including `promptfooconfig.yaml`, test cases, and Python assertions. It instructs running `npx promptfoo@latest eval` and using providers like `openai:gpt-4.1`/`anthropic:messages:claude-sonnet-4-5-20250929` and env vars `OPENAI_API_KEY`/`ANTHROPIC_API_KEY`.