AI & ML

ddaanet Skill

Verify a Python function against its intended behavior by writing an icontract contract and checking it with `edify check` (CrossHair), repairing in a loop. Triggers on "formalize", "verify this function", "add a contract and check it", or after writing a function whose correctness matters. The in-context agent holds intent and asks the user when behavior is ambiguous; CrossHair owns the deduction.

jeandiable Bundle

Automatic citation insertion for LaTeX manuscripts. Parses LaTeX source to find uncited statements (factual claims, method comparisons, background assertions, dataset references, numerical claims), searches for the correct papers via Semantic Scholar and DBLP, fetches official BibTeX (never fabricates), and inserts \cite{} commands. Returns modified .tex files and updated .bib file. Inspired by github.com/ZhangNy301/citation-assistant. Use when the user says "add citations", "find references for", "cite this", "my paper needs citations", or provides LaTeX files needing references.

pythoughts-labs Skill

Release designer-skill-mcp to npm with a git tag and GitHub release. Use when the user asks to ship, publish, cut a release, bump version, push tags, or run npm publish for designer-skill-mcp.

bv-venky Bundle

Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when asked to draw, diagram, chart, or visualize a system, process, or dataset.

bv-venky Skill

Guide for structuring graph input (nodes and edges) for the Excalidraw Architect MCP tool to produce clean, readable diagrams. Use when generating architecture diagrams, flow diagrams, or any visual diagram via create_diagram or mermaid_to_excalidraw.

bv-venky Skill

Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg_* tools. Use when creating or updating the knowledge graph (.claude/architecture.md), mapping services and their dependencies, or analyzing one or more repos to capture how services communicate.

xuziqiang98 Bundle

基于LSP的智能代码安全审计Skill。利用OpenCode内置LSP进行代码理解、符号追踪、数据流分析，Agent自主识别项目特点并执行多维度安全审计（污点分析、认证授权、业务逻辑、敏感信息等），输出可验证的漏洞报告与PoC。适用于任何编程语言和项目类型。

whit3rabbit Skill

Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room / reverse-engineering / source-to-clean-implementation task hands-off but without paying per-token for `clean-room-skill run`, or says "clean-room as a workflow", "unattended clean-room without API cost", "/clean-room-loop". Runs a short discussion (authorization, end goal, target stack, policies, source roots, output roots, iterations) then launches the `clean-room-loop` workflow with the answers. NOT the enforced OS-level wall - that is `clean-room-skill run --agent-runtime claude`.

birdcar Bundle

Scaffolds an agentic harness into a target repository — AGENTS.md or CLAUDE.md, feature_list.json, progress.md, init.sh, and session-handoff.md. Detects the target's stack (Node, Python, PHP, Go, Rust, Java, .NET) and emits stack-appropriate verification commands — framework-aware for Laravel/Filament, Django, and uv-managed Python. Use when the user asks to "scaffold a harness", "add AGENTS.md", "set up CLAUDE.md", "make this repo agent-ready", "create a feature tracker for this repo", "add session continuity", or "audit this repo's agent harness". Do NOT use for creating a Claude Code skill (use forge-skill instead) or for improving an existing skill (use improve-skill).

birdcar Bundle

Analyzes and optimizes existing Claude Code skills for better trigger precision, structural compliance, instruction quality, and agent efficiency. Produces measurable before/after scorecards. Use when the user asks to "improve a skill", "optimize a skill", "review a skill", "audit skill quality", "fix skill triggers", or references an existing SKILL.md that needs work. Do NOT use for creating new skills (use create-skill instead) or for reviewing non-skill code (use code-review instead).

razorpay Skill

Generate Razorpay MCP server tool implementations from API documentation URLs, curl commands, or request/response examples. Produces Go tool code, unit tests, registration, and README updates. Use when the user provides a Razorpay API doc link, curl example, or request/response payload and wants a new MCP tool created.

taylorleese Bundle

Get a second opinion from a non-Claude frontier model — Codex (OpenAI's coding agent), Antigravity (Google's coding agent), or DeepSeek. Use when the user says "ask Codex", "ask Antigravity", "ask agy", "ask DeepSeek", "get a second opinion", "what would another model say", "sanity-check this with another model", or wants cross-model consensus on code, an architecture decision, or an implementation plan.

britrik-skill-vettr Bundle

Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patterns before installation. Use when vetting skills from ClawHub or untrusted sources.

vdustr Skill

Manage agent skills using the npx skills CLI. Use when the user asks to "install a skill", "add a skill", "remove a skill", "list skills", "update skills", "find skills", "search for skills", or mentions "npx skills", skill management, or agent skill installation. Also trigger when the user mentions skills.sh, agent-skills, vercel skills, or wants to discover available skills for their environment. Boundary: not for creating new skills (use skill-creator) or managing plugins (/plugin commands).

vdustr Skill

Generate a meaningful session name based on the overall session theme, not just the last action. Use when asked to "name this session", "rename session", "prename", "give this session a name", "what should I call this session", or when the user invokes /prename. Outputs a concise session title, with a platform-specific rename command only when the current agent supports one. Boundary: not for renaming files, variables, or git branches.

microsoft Bundle

Start and interact with the Dataset Analysis Tool (dataviewer) for browsing, annotating, and exporting robotic training episodes

dgalarza Bundle

Audit codebase documentation for accuracy, completeness, and freshness. Compares docs against actual code structure, auto-fixes small discrepancies, reports structural changes. Works with any language/framework. Companion to agent-ready.

dgalarza Bundle

Make a codebase agent-ready by scaffolding AGENTS.md, ARCHITECTURE.md, and docs/ structure, installing regression-aware quality gates, and recommending project-local, stack-specific skills. Analyzes codebase structure, generates documentation artifacts following progressive disclosure patterns, installs report/check/baseline quality-gate commands with merge-base-aware CI and a human-reviewed baseline, and audits existing artifacts for staleness and coherence. Use when improving a codebase for AI agent work.

philoserf Skill

Re-normalizes MCP connector enable/disable state across all project entries in ~/.claude.json (computer-use on; claude-in-chrome and claude.ai connectors off). Use when project dirs drift off the connector spec and every entry needs fixing at once.

nexus-labs-automation Skill

Instrument agent tool executions with proper context and error handling

nexus-labs-automation Skill

Plan what to measure in AI agent systems using tiered approach

nonlinear Bundle

Natural language task queue via Apple Reminders. Agent executor with 🤖 tracking.

chris-buckley Bundle

The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.

jhd3197 Skill

Add function-calling tools to Prompture agents. Covers ToolDefinition, ToolRegistry, tool_from_function, decorator patterns, serialization formats, and Conversation integration. Use when adding callable tools for LLM function calling.

jhd3197 Skill

Create reusable persona system prompts for Prompture. Covers Persona dataclass, template variables, composition, trait registry, global registry, serialization, and Conversation integration. Use when defining system prompts for extraction or agent behavior.

clickhouse Skill

Set up the `clickhouse-js` repository in a fresh checkout so the agent can run tests, lints, type checks, builds, or examples. Use this skill before invoking any `npm run test:*`, `npm run lint`, `npm run typecheck`, `npm run build`, or `npm run run-examples` script — or after pulling changes that touch any `package.json` (root, `examples/node`, or `examples/web`). Covers Node.js version requirements, installing dependencies across the npm workspaces and the two independent example packages, building the workspace packages so inter-package imports resolve, and starting ClickHouse via Docker Compose for integration tests. Do NOT use this skill for downstream user projects that merely depend on `@clickhouse/client` or `@clickhouse/client-web`; it is specific to contributing to the `ClickHouse/clickhouse-js` repo itself.

clickhouse Skill

Drive a package release of `ClickHouse/clickhouse-js` end to end: bump the version, sync the protected `release` branch from `main`, watch the npm publish (which is gated by a manual approval on the `npm-publish` environment), and create the GitHub Release from the CHANGELOG. Use this skill whenever the task is to "release", "cut a release", "publish a new version", or "ship" one of the packages: `@clickhouse/client` (Node.js), `@clickhouse/client-web` (Web), `@clickhouse/client-common` (deprecated, rarely released), the standalone `@clickhouse/datatype-parser` (the type parser, under `packages/datatype-parser`), or `@clickhouse/rowbinary` (the RowBinary codec skill/package, under `skills/clickhouse-js-node-rowbinary`). The agent drives the GitHub Actions workflows (`gh workflow run`), watches CI, pauses at the human-judgment points (PR review, the approval gate, GitHub Release text), and hands the deployment-approval link back to the human. Do NOT use this for fixing a failing release PR — that is the `fix-r

octagonai-octagon-mcp-server Skill

Analyze 10-K annual filings to extract business model, financial priorities, risk factors, segments, and notable changes. Use when the user asks about 10-Ks, annual filings, SEC risk factors, or filing-based due diligence.

octagonai-octagon-mcp-server Skill

Validate Octagon plugin configuration and run a lightweight smoke test across the main Octagon MCP workflows. Use when checking whether the plugin is configured correctly, debugging auth, or verifying tool availability.

hashgraph-online-hol-guard-plugin Skill

Scan AI agent skills, plugins, MCP servers, and agent tooling locally for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.

microsoft Skill

服务端路径安全与文件访问编码规范。在编写文件下载路由、Agent 工具（文件读取/目录列出）、数据连接器/Loader、Workspace 路径操作、沙箱配置时使用。

microsoft Skill

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（message_code）时使用。

wipcomputer-wip-ai-devops-toolbox Bundle

Reference installer for agent-native software. Scans a repo, detects which interfaces it exposes, and installs them all.

rawe Bundle

Use this skill when you need to orchestrate specialized Claude agents in separate sessions. Perfect for long-running tasks, specialized agents with MCP tools, and resumable workflows.

cisco-ai-defense Bundle

Security-aware code generation — teaches the agent CodeGuard rules to write secure code by default

rivet-dev Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.