Splits a project's full claude-mem timeline into ISO weeks and writes one serialized narrative chapter per week, each inheriting the previous week's carry-forward.
Makes the AI critique its own first draft in a 'mirror' pass so the final reply sounds like a real person, not an assistant.
Writes competitive research proposals tailored to NSF, NIH, DOE, DARPA, and Taiwan NSTC review criteria, formats, and budget rules.
Official Anthropic skill that drafts internal communications — 3P updates, newsletters, FAQs, incident and leadership reports — in your company's preferred formats.
Turns vague requests into precise, testable specifications and structured prompts using EARS syntax.
A 7-phase research pipeline that produces cited, source-governed reports with mandatory counter-review.
Verifies factual claims in your documents against official sources and applies corrections only after you approve them.
Turns plain text or rough markdown into a clean, scannable article with frontmatter, headings, lists and tables — without changing a single word of the original.
A three-mode translation skill (quick / normal / refined) with glossary merging, markdown chunking and a publication-quality review pipeline.
Turns Markdown files into beautifully styled, inline-CSS HTML ready to paste into WeChat or any editor.
Fixes speech-to-text errors in two stages — a free dictionary pass plus Claude's native AI correction — and learns from every fix so the same errors auto-correct next time.
Writes consistent, template-driven Microsoft Teams channel posts that teach colleagues Claude Code features, tips, and best practices.
Fetches X (Twitter) posts and long-form Articles with all images and saves them as complete Markdown with metadata.