Writing & Editing

13-agent academic paper writing pipeline for Claude Code. 11 modes: full, plan, outline, revision, revision-coach, abstract, lit-review, format-convert, citation-check, disclosure, translate (Chinese→English with reference-paper style matching). Install: claude skill add --url https://github.com/Youn-17/academic-paper

Codex skill for matching resumes to daily internship opportunities

Modules that extend how Claude reads, writes, reasons, and plays

Claude skills for the Vivreal MCP server — managing content, channels, sites, and billing in the Vivreal CMS

A Claude agent skill that turns a brief into a consulting-grade presentation, output as editable PowerPoint, HTML, or Markdown. Accent colour and display font are set per deck (defaulting to deep pine and Charter); it draws on a render-tested pattern library and screens every slide against a built-in anti-slop gate.

Point Claude, Cursor, or Codex at this repo to run a high-stakes job application end-to-end: parse your CV + the job post, score 4-stakeholder fit, build a tailored kit, and draft outreach — all from your filesystem.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Claude Code skill that delegates summarisation, log triage, and bulk-text tasks to local models. Saves API tokens, keeps content on-device, hardware-aware model auditing.

Health check for AI agent skills. skill-doctor diagnoses why a SKILL.md won't reliably trigger, runs a routing-recall test on every reference, and restructures the package. 4 deterministic scripts + GLM routing eval. Claude Code & Codex.

Composable writing instructions for AI agents on four orthogonal axes (Voice, Tone, Style, Format). Early/experimental. Install via the product-on-purpose marketplace.

Ready Agent 1 — is your codebase ready for the agents? Score agent-readiness (deterministic, cited, Level 1-5) and clear the gates.

🛡️ Production guardrail skills for AI-assisted Laravel — stop cross-tenant leaks, N+1, destructive migrations before your AI agent ships them. For Claude Code, Cursor & 40+ agents.

Turn any study material into a spaced-repetition mastery loop: AI-generated active-recall items plus a real FSRS scheduler, in a portable Claude/Codex/Cowork skill.

An agent skill that turns any project folder into a polished, publish-ready open source repository — without touching your source code.

Codex skill for producing Chinese foreign-trade Xiaohongshu and Douyin content packages

Various skills used for development, content, etc.

Custom Claude Code skills: accessibility testing pipeline (axe-core, JAWS braille simulation, site crawler), session/knowledge management, Google Docs CLI, and dev-content tools

A guarded Codex skill for source-verified academic research writing, inspired by Deli_AutoResearch.

A composable dev process for agentic coding harnesses, packaged as modular skills. Turbo has sibling editions for Claude Code and Codex.

Privacy-safe context receipts for AI coding agents: prove what context, memory, tools, skills, compactions, and security findings crossed the boundary without logging raw content.

Three composable Claude skills for end-to-end long-tail SEO blog publishing on Ghost CMS: topic research, draft & publish, SVG figure generation.

Read-only diagnosis and a safe, rollback-aware cleanup plan for bloated Git repositories. Zero-dependency Python; ships as a Claude Code skill.

MCP server for W-2 event staffing across 345 US/CA markets: plan_staffing planner, live rates, availability, compliance, the Event Staffing Rate Index, and quote requests. npx -y tempguru-mcp

Gemini, Claude, Skills for Building Apps