Start with the job, then find an open-source answer

paper2anything packages five independent skills for turning an academic PDF into a PowerPoint deck, conference poster, single-page project site, Xiaohongshu post, or WeChat article. It is useful when a research team needs several dissemination formats from the same paper without rebuilding each workflow separately. Paper extraction uses MinerU credentials, and some rendering or visual-check paths also require local tools such as LibreOffice, Poppler, and Node.js.

writing-style-skill provides a reusable template for Claude Code and OpenClaw that improves from the user's own revisions. It records the original AI draft and the final edited version, compares them, extracts recurring preferences, and updates SKILL.md so later drafts follow those rules. The observation step is a dependency-free Python script, while automatic rule extraction and application require an available Claude CLI, the llm command, or a user-configured LLM command.

Quota Float is a lightweight always-on-top widget for Windows and macOS that reads an existing local Codex Desktop login and queries the five-hour quota, weekly quota, next reset time, and reset-credit details when available. It collapses into a small orb when idle and shows explicit stale, signed-out, loading, or unavailable states rather than inventing values. The app stores only widget preferences, not tokens, account IDs, prompts, chat history, or raw responses. Real quota access requires Codex Desktop to be signed in on the same machine, and current builds are unsigned.

Give mimeo a person’s name and it searches public essays, talks, interviews, and other sources, distills recurring principles, and writes a SKILL.md, an AGENTS.md file, or both for a coding agent. It can verify extracted quotes and refine drafts through critique passes. Parallel and OpenRouter API keys are required, with extra dependencies for local podcast transcription.

jd-gui-duo is a standalone desktop interface that brings several Java and Android decompilers into one application, including JD-Core, CFR, Procyon, Fernflower, Vineflower, and Jadx. It opens formats such as APK, DEX, JAR, CLASS, WAR, and ZIP, then lets users browse generated source, search for types, and navigate references. Comparison tools can show archive and class differences, making it useful when one decompiler’s output is unclear or when reverse-engineering results need cross-checking.

Joplin Plugin Backup creates backups on a schedule or on demand from the Tools menu. It exports notebooks as JEX files and saves supporting profile data such as settings, keyboard shortcuts, custom styles, templates, and installed plugin files. The plugin is built into Joplin 2.14.6 and newer, but each profile must be configured separately. Note-history revisions and inactive profiles are not included, and restoring notes generally involves importing the JEX backup.

Vexor creates reusable semantic indexes over files and source code so users can locate relevant material with natural-language queries. The same engine is available through a CLI, a Python API, and a built-in MCP server, with configurable embedding and reranking providers, hybrid keyword-plus-semantic ranking, and fully local model options. For agents such as Claude Code or Codex, the included skill and MCP server expose the same core search capability, so a workflow generally needs only one of those integrations.

Micro-Drama-Skills provides a Claude Skills workflow for producing a 25-episode short drama, with roughly 30 seconds per episode. It creates scripts, character definitions, six-panel storyboards, and project configuration, then can call Gemini and Veo for images and video before submitting batches to a Seedance workflow. The project is intended for tools that load Claude Skills and requires users to configure the Python environment and the relevant media-generation APIs.

SkillCompass is a local-first evaluator and manager for people who maintain agent skills. It scores a skill across six dimensions, identifies the weakest area to improve, and tracks versions so later evaluations show whether a change helped. Usage hooks feed an inbox that surfaces unused skills, stale evaluations, declining adoption, and updates, while SKILL.md edits trigger structural and security-pattern checks. SHA-256 snapshots make regressions recoverable. It is not a general code reviewer, runtime debugger, or tool for creating skills from scratch.

Awesome Apify Skills is a community collection of SKILL.md packages for AI coding assistants. Each skill teaches an agent which Apify Actors to use, how to prepare inputs, and how to handle failures for a specific web-data or research task, including areas such as advertising intelligence and search visibility. Users can install the whole repository or select one skill, and the packages work across Claude Code, Codex, Cursor, Gemini CLI, and many other compatible agents. Running the workflows generally requires an Apify account and authentication token.

ScreenCaptureKit-rs gives Rust developers an idiomatic interface to Apple’s ScreenCaptureKit for capturing displays, windows, applications, system audio, and microphones. It supports runtime-agnostic async workflows and low-copy frame delivery for recording, transcription, and remote-desktop software. Features are gated by macOS versions, the base crate requires macOS 12.3 or later, and every app must obtain the user’s Screen Recording permission.

Blueprint packages a focused software-delivery process into agent skills for design documents, specifications, planning, implementation, testing, browser verification, and code review. Teams can invoke one stage or coordinate tickets through review-ready pull requests. Completion is tied to tests and observable proof, and browser-based checks require a compatible automation setup.

GRACE Marketplace distributes a contract-first set of AI engineering skills plus an optional CLI; it is not a standalone end-user application. The workflow anchors planning, implementation, verification, review, and refactoring in shared XML artifacts for requirements, technology choices, development plans, verification evidence, and a knowledge graph. The skills target Claude Code, Codex CLI, and Kilo Code, while the CLI mainly adds integrity checks and module navigation around the same artifacts.

The official Basecamp CLI lets users list projects, create and complete todos, search across workspaces, manage cards, files, chats, and comments, and emit structured JSON for automation. OAuth tokens refresh automatically, and the repository includes both a Claude plugin and a portable agent skill for shell-capable assistants.

Claude Trading Skills is a collection of 67 Agent Skills for market data, on-chain research, technical analysis, backtesting, portfolio and risk work, and other quantitative-finance workflows. The library is crypto and DeFi first, while its structure can be extended to additional markets. It requires Python, uv, and an Agent Skills-compatible client, with API credentials needed for some data providers. Skills that can interact with live markets default to demonstration or simulation behavior and require explicit confirmation before execution.

Bitget Wallet Skill gives agents tools for token discovery, market and address analysis, balance queries, swaps, transfers, and order tracking across supported EVM chains and Solana. Fund-moving workflows generate transaction data and require user confirmation and signing by default. Using it depends on Bitget Wallet's API, network access, and appropriate wallet credentials.

rgitui is a cross-platform desktop Git client with tabs for multiple repositories and visual views for the commit graph, unified or side-by-side diffs, file history, blame, and reflog. Users can stage at file, hunk, or line level and perform branch, remote, stash, worktree, conflict-resolution, and interactive-rebase operations; Gemini-based commit drafting is optional. The project is in early active development, release binaries are unsigned, and macOS builds are explicitly experimental.

SuperSEO Skills lets an agent start with a URL, keyword, or topic, research the page, search results, and competitors, then produce SEO audits, content plans, drafts, and other growth work. It is built for live, one-off research workflows rather than historical Search Console analysis or ongoing site monitoring.