AI & ML

jaemk Skill

Targeted, read-only review of a PR or checked-out branch. Acquires the diff (a PR number, or the current branch vs origin/master), spawns an independent code-review sub-agent and a library-consumer sub-agent in parallel, then aggregates their findings into a single report with severity and a valid / already-fixed / invalid verdict for each. Read-only — it does not edit files, commit, push, or touch the GitHub PR conversation. The review sub-agents default to Sonnet but can be overridden per run (e.g. to opus). Use when asked to "review this PR", "review the branch", "what's wrong with this diff", "do a code review", or "review with opus". For the full review → fix → push → resolve loop, use `pr-cycle` (which delegates its review step here).

jentic Skill

Import an API that is not yet in jentic-public-apis end to end — generate or find an OpenAPI spec from the vendor's docs, optionally import it into the local Jentic registry so the agent is unblocked immediately, publish it to the user's reusable public import-openapi-specs repo, and open the import issue that drives it into the community catalog. Use when the user says "import the <vendor> API", "add <vendor> — it's not in the catalog yet", "generate a spec for <company> and open an import issue", or gives a docs URL to import. For fixing a spec already in the catalog, use contribute-spec-fix instead.

jiahuiqu17 Bundle

Inspect and diagnose minimal-zine posters, photo restyles, editorial images, and social-card series for subject preservation, factual and text integrity, composition, paper realism, print-process coherence, color signal, anti-AI craft, platform fit, and series continuity. Use when the user asks whether an image has高级感, feels AI-generated, matches Paper Signal or gc-minimal-zine quality, needs improvement, or should be regenerated. Returns evidence-based findings and a targeted correction prompt; regenerates only when the user also asks for a fix.

jiaziui Bundle

一句话说明本 skill 做什么、在什么场景下由 Agent 自动选用。 写清触发关键词，避免与其他 skill 的 description 重复。

level09 Skill

Generate async CRUD API endpoints for an existing stk model. Use when adding API routes, REST endpoints, or CRUD operations to an stk blueprint.

ludo-technologies Skill

Find refactoring targets in Python code using pyscn - duplicate code (clones), overly complex functions, and dead code. Use when user asks about refactoring, code duplication, complexity hotspots, unreachable code, or cleaning up a codebase.

ludo-technologies Skill

Get an overall Python code quality health score using pyscn. Use when user asks how healthy or good the code is, wants a quality overview, a grade, a summary of technical debt, or a before/after quality comparison.

ludo-technologies Skill

Analyze Python module architecture using pyscn - class coupling (CBO), cohesion (LCOM), dependency cycles, and module communities. Use when user asks about architecture, module structure, coupling, circular dependencies, or which files to review or change together.

mainmatter Bundle

A skill that allows the agent to generate a GUID.

mainmatter Skill

A skill that allows the agent to flip a coin.

mainmatter Bundle

A skill that allows the agent to roll a dice and return the result.

mainmatter Bundle

A skill that allows the agent to setup a webhook site so that it can receive events.

megara-arevaco Bundle

Route nontrivial coding work across models to reduce cost while preserving quality: use strong reasoning for planning and risk decisions, delegate bounded implementation to a cheaper model, validate the result, and escalate only when evidence justifies it. Apply when the user requests cost-aware model routing, a strong-plan/cheap-implementation workflow, or explicitly invokes this skill.

metapages Bundle

How the framejs Agent Skill is listed in the ComposioHQ/awesome-claude-skills directory, and the exact steps to submit or refresh that listing. Load when asked to publish/submit/contribute the framejs skill to awesome-claude-skills (or another skills directory), when the listing entry or its description needs updating after a skill change, when `just check-awesome-listing` reports drift, or when the upstream CONTRIBUTING rules have changed.

nolly-studio Bundle

Bootstrap a repository's AI coding agent operating system — AGENTS.md, CLAUDE.md, CONTEXT.md (domain language), docs/agents (architecture, code-style, lessons-learned), docs/plans, docs/release.md, and portable plan-mode/code-review skills — all rewritten from evidence gathered in the target repo. Use when setting up agent docs for a new or existing project. Triggers on "bootstrap agent system", "set up AGENTS.md", "port agent docs", "create agent operating system", "agent onboarding docs".

noor-u1-huda Bundle

Refines vague machine-learning performance improvement requests into structured, evidence-driven diagnostic prompts. Use when a user wants to improve model accuracy or other evaluation metrics but the cause of poor performance has not yet been established.

noor-u1-huda Bundle

Produces evidence-based answers by researching relevant sources, verifying important claims, checking links and references, comparing sources, distinguishing evidence from inference, and communicating uncertainty instead of presenting unsupported information as fact.

openjiuwen-ai Bundle

Security review checklist for DeepSearch changes involving secrets, file paths, LLM/search providers, prompts, server APIs, storage, and logs.

platonai Skill

Guides the creation of Browser4 plugins from requirements gathering through deployment. Use when the user wants to create, build, scaffold, or extend Browser4 with a new plugin — whether for CAPTCHA solving, media processing, content conversion, page category detection, custom RPA actions, or new LLM agent tools.

ros-claw Skill

Use when operating, validating, or changing ROSClaw physical-AI runtime workflows, especially CLI smoke tests, Practice evidence loops, body/runtime checks, MCP integration, MuJoCo sandbox verification, and safe ROS or hardware boundaries.

ros-claw Bundle

Safely install, validate, diagnose, and optimize ROSClaw simulation workflows across MuJoCo/MJWarp, ROS 2 rosbridge, turtlesim, Gazebo, Isaac Sim, Isaac Lab multi-GPU training, MCP, and the signed ROSClaw Hub. Use for evidence-backed physical-AI smoke tests, 4-GPU validation, simulator integration, Hub upload/download tests, or ROSClaw verification reports without a real robot.

ros-claw Skill

ROSClaw 具身任务纪律——通用物理原语编排、任务沙箱编码、证据验收、安全分层（何时用：任何涉及机器人/仿真/动作的任务）

scannedinc Bundle

Migrate a Xojo desktop project from API 1.0 (which Xojo's own documentation calls "pre-API 2.0") to API 2.0: a rule-driven, confidence-tiered conversion of the source code, committed one category at a time, that fixes the index bases, sentinels and epoch shift a rename alone leaves wrong. Replaces deprecated APIs such as MsgBox, Dim, RecordSet, SQLSelect, Date, InStr, Mid, Len, Ubound, ListBox members, GetFolderItem and error-code checks. Covers more than a thousand deprecated and removed symbols with hundreds of vetted conversion rules. Invoke this skill only when the user asks for it by name: it rewrites a whole project across many commits, so never start it on inference. When a user wants a migration, tell them to run the skill themselves (/xojo:xojo-migrate in Claude Code, $xojo-migrate in Codex) and wait for them to do it. Questions about API 1.0 versus API 2.0, whether a symbol is deprecated, and what replaced it belong to the xojo skill instead, which holds the documentation and the deprecation indexes

smartgate-network Bundle

research-agent

standardharness Skill

Add, inspect, or authenticate an MCP server. Use when the user pastes an MCP URL or npx package, says tools are missing, or asks to connect DeepWiki, Playwright, or similar. Not for writing a new MCP server from scratch.

nanocoai Skill

Add Ollama MCP server so the container agent can call local models for cheaper/faster tasks like summarization, translation, or general queries.

markheydon Skill

Intelligent README.md generation prompt that analyses project documentation structure and creates comprehensive repository documentation. Scans repository documentation files and AGENTS.md to extract project information, technology stack, architecture, development workflow, coding standards, and testing approaches while generating well-structured markdown documentation with proper formatting, cross-references, and developer-focused content.

crystian Bundle

Mirrors the portfolio's pages into Notion after publishing, creating one Notion page per site page via the Notion MCP. Use it from $publish, or when the user asks to sync the site to Notion.

ravnhq Bundle

Transform user requests into detailed, precise prompts for AI models. Use when users say 'promptify', 'promptify this', 'rewrite this prompt', 'make this prompt better/more specific', or explicitly request prompt engineering or improvement of their request for better AI responses.

ravnhq Skill

Analyzes git diffs and commit history to intelligently fill PR templates and create pull requests via gh CLI. Use when user wants to create a PR, needs PR description help, or says 'create a pull request', 'fill PR template', 'make a PR', 'open a pull request', or mentions PR creation.

nahisaho Bundle

Copilot agent that assists with comprehensive code review focusing on code quality, SOLID principles, security, performance, and best practices Trigger terms: code review, review code, code quality, best practices, SOLID principles, code smells, refactoring suggestions, code analysis, static analysis Use when: User requests involve code reviewer tasks.

nahisaho Bundle

Integrated orchestrator agent that manages and coordinates 25 specialized AI agents for Specification Driven Development Trigger terms: orchestrate, coordinate, multi-agent, workflow, execution plan, task breakdown, agent selection, project planning, complex task, full lifecycle, end-to-end development, comprehensive solution Use when: User requests involve orchestrator tasks.

frankxai Skill

Expert prompt engineering and music generation with Suno AI v4/v4.5 for professional-quality songs across all genres with advanced composition techniques

frankxai Bundle

Expert Suno AI prompt engineering for cinematic, transformative music creation. Use this skill when creating Suno prompts for Vibe OS sessions, meditation tracks, or any AI-generated music that needs professional quality and emotional resonance.

aradotso Skill

Guide AI agents through CLI-based coding workflows with Claude, including context preparation, prompt scoping, diff review, and testing habits.

aradotso Skill

Comprehensive guide to understanding Claude Code's architecture, Agent Runtime, tool systems, and Context Engineering for AI agent development