Claude Code Skills Repository

Create videos programmatically with Claude Code using Remotion. This MCP server indexes Remotion's entire documentation into a vector database, giving Claude deep knowledge of Remotion's video framework. Build professional videos with React components, animated graphics, code visualizations, and more - all through natural language prompts.

Remove signs of AI-generated writing from text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide maintained by WikiProject AI Cleanup. Detects and fixes 24 patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words (delve, tapestry, landscape), negative parallelisms, sycophantic tone, and generic conclusions.

Automatically generates meaningful, conventional commit messages by analyzing staged changes. Follows the Conventional Commits specification with type prefixes like feat, fix, docs, refactor, etc.

Performs thorough code reviews checking for bugs, security issues, performance problems, and style inconsistencies. Provides actionable feedback with specific line references.

Generates comprehensive unit tests for functions and classes. Covers happy paths, edge cases, error conditions, and boundary values. Supports Jest, Pytest, JUnit, and other frameworks.

Systematically debugs issues by analyzing error messages, stack traces, and code flow. Adds strategic logging, identifies root causes, and suggests fixes.

A platform-agnostic agent skill that captures the current conversation as a structured Markdown snapshot and generates a ready-to-paste bootstrap prompt for resuming in a future session. Triggers on explicit commands (/log-session, "save session") or auto-detects intent from phrases like "let's pick this up tomorrow", "I need to take a break", or "summarize what we did". Produces a fully structured log with Goal, Context, Steps Taken, Key Decisions, Code Changes, Errors & Fixes, Insights, Next Steps, Reusable Prompts, and a self-contained Bootstrap Prompt.

Find papers and preprints that cite a given URL, especially blogs, docs pages, project pages, or other web content that standard citation indexes often miss. Use when the user provides a URL and wants confirmed citing works, evidence from PDF or HTML references, DOI or arXiv links, BibTeX, or a deduplicated citation report.

Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.

Work with a user's Semantic Scholar account to read Research Feeds, inspect private Library folders, add papers to folders, and resolve Semantic Scholar paper records from identifiers such as arXiv IDs.

Convert a finished raster image, especially a generated poster or visual resume, into an image-based PDF with an additional selectable, copyable, searchable text layer. Use when the image is the final visual layout, when recreating that layout in PPT, HTML, or LaTeX would be fragile, and when the user needs both a final invisible-text PDF and a visible inspection PDF for checking OCR or text-layer placement.

Create a topic-specific GitHub awesome-list repository scaffold with a polished README, concise contribution rules, AI-agent instructions, URL verification, license, and reusable templates. Use when the user wants to generate a new awesome repo, awesome list, curated repository, or topic resource catalog from a topic plus optional taxonomy, inclusion criteria, and researched entries.

Take a rough idea, brief, or project sketch and return a clear audience, a concrete pain point, an offer framing, and a ranked first-action plan. Triggers on "I have an idea for X", "help me think through X", "I want to build/launch/start X", "what should I do next with X", or any pasted brief that mentions an audience and an outcome but no plan. Refuses to invent specifics the user didn't supply; pushes back on generic answers ("small businesses", "scale their operations") and demands the user's literal phrasing before drafting.

Plan Zentao tasks, and perform Zentao operations including creating tasks, logging work hours, and completing tasks.规划禅道任务，以及对禅道操作，创建任务、录入工时、完成任务。

Plan Zentao tasks, and perform Zentao operations including creating tasks, logging work hours, and completing tasks.规划禅道任务，以及对禅道操作，创建任务、录入工时、完成任务。

A Claude Code skill for Windows that cleans and organizes your desktop in two steps: first silently removes all shortcuts (.lnk, .url), then offers two modes — Full Cleanup (auto-sorts files into category folders) or Show List (interactive selection for manual deletion). Works with both regular and OneDrive-redirected desktops, warns about sensitive files (credentials, certificates, active project folders), and generates a clean summary report.

Work with a user's Semantic Scholar account to read Research Feeds, inspect private Library folders, add papers to folders, and resolve Semantic Scholar paper records from identifiers such as arXiv IDs.

Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.

Remove signs of AI-generated writing from text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide maintained by WikiProject AI Cleanup. Detects and fixes 24 patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words (delve, tapestry, landscape), negative parallelisms, sycophantic tone, and generic conclusions.

A platform-agnostic agent skill that captures the current conversation as a structured Markdown snapshot and generates a ready-to-paste bootstrap prompt for resuming in a future session. Triggers on explicit commands (/log-session, "save session") or auto-detects intent from phrases like "let's pick this up tomorrow", "I need to take a break", or "summarize what we did". Produces a fully structured log with Goal, Context, Steps Taken, Key Decisions, Code Changes, Errors & Fixes, Insights, Next Steps, Reusable Prompts, and a self-contained Bootstrap Prompt.

Find papers and preprints that cite a given URL, especially blogs, docs pages, project pages, or other web content that standard citation indexes often miss. Use when the user provides a URL and wants confirmed citing works, evidence from PDF or HTML references, DOI or arXiv links, BibTeX, or a deduplicated citation report.

Publish, submit, and verify local skills across public skill marketplaces, directories, and registries. Use when an agent needs to take a skill folder or skill repository, confirm current submission paths, prepare cross-market metadata, run verified live adapters, or generate manual submission bundles for markets such as AgentSkill.sh, Skillstore, SkillNet, agent-skills.md, SkillsMD, SkillHub, SkillHQ, and related registries.

Work with a user's Semantic Scholar account to read Research Feeds, inspect private Library folders, add papers to folders, and resolve Semantic Scholar paper records from identifiers such as arXiv IDs.

Convert a finished raster image, especially a generated poster or visual resume, into an image-based PDF with an additional selectable, copyable, searchable text layer. Use when the image is the final visual layout, when recreating that layout in PPT, HTML, or LaTeX would be fragile, and when the user needs both a final invisible-text PDF and a visible inspection PDF for checking OCR or text-layer placement.