AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
aibot88 Bundle Obsidian Vault ManagerObsidian Vault Manager is built around HashiCorp Vault secrets platform. The underlying ecosystem is represented by hashicorp/vault (35,266+ GitHub stars). It gives an agent a more technical and reliable way to work with the tool than a thin one-line wrapper, using stable interfaces like KV v2, policies, leases, tokens, transit, dynamic secrets and preserving the […]
3 - aibot88 Bundle Cancer Metabolism Agent
---name: cancer-metabolism-agent
3 - aibot88 Bundle Owasp Zap Scanner Agent
Integrates the OWASP ZAP API to run automated DAST scans against web applications. Parses ZAP JSON reports, triages alerts by CVSS severity, and generates remediation tickets via Jira REST API.
3 - aibot88 Bundle Agent Instructions Audit
Audit the project's agent / LLM instruction files for vague rules, missing examples, drifted compliance, and mechanical-enforcement opportunities.
3 - aibot88 Bundle Chezmoi Dotfiles Manager
chezmoi manages dotfiles across multiple machines securely using a Git-backed source-of-truth model with templates, encryption, and cross-platform support. Written in Go with 18k+ GitHub stars, it handles machine-specific configs, secrets, and one-command bootstrap.
3 - aibot88 Bundle Personal Pre Push Review
Pre-push adversarial review for personal repos before git push. Runs adversarial-input sweep, parallel-implementation symmetry audit, project AGENTS.md compliance, dead-code sweep, secrets scan. Use before any push; mandatory for repos that will become public or shared. Tier 2 sub-agent does the bulk; Tier 3 main synthesizes.
3 - aibot88 Bundle Prompt Engineering Skill
Publishable Prompt Engineering skill package that compiles a user request into a ready-to-use high-quality Prompt, with support for diagnosis, module injection, debugging, and evaluation.
3 - aibot88 Bundle Sonarqube Analysis Agent
Integrates with the SonarQube REST API to run static code analysis scans, retrieve quality gate results, and flag code smells. Supports SonarCloud and on-premise SonarQube instances via token-based authentication.
3 - aibot88 Bundle Hashicorp Vault MCP Server
The official HashiCorp Vault MCP server lets AI assistants read, write, list, and delete secrets in Vault's KV engine through a safe, auditable MCP interface. Supports both stdio and HTTP transports, TLS encryption, and CORS controls.
3 - aibot88 Bundle LLM Trading Agent Security
中文优先：用于LLMtrading智能体安全相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.
3 - aibot88 Bundle Sam33339999 Dynamic Layout Docs
Dynamic Layout Report System - LLM Skill Guide
3 - aibot88 Bundle Woocommerce REST Sync Agent
Synchronizes WooCommerce product data bidirectionally using the WC REST API v3 and wc/v3/products endpoints. Handles batch create/update/delete with OAuth 1.0a authentication and rate-limit backoff.
3 - aibot88 Bundle Google Calendar Sync Agent 2
Synchronizes events across multiple Google Calendar accounts using the Calendar API v3 and OAuth 2.0. Handles recurring events, timezone conversions, and conflict resolution.
3 - aibot88 Bundle Jinja2 Template Engine Agent
Renders Jinja2 templates with variable injection, macro expansion, and template inheritance. Integrates with the Jinja2 Environment API for sandboxed execution and custom filter registration.
3 - aibot88 Bundle Sonarqube Code Scanner Agent
Automated code quality scanning using SonarQube REST API and SonarScanner CLI. Detects code smells, bugs, and vulnerabilities across 30+ languages with configurable quality gates.
3 - aibot88 Bundle Overflow65537 Maa Snowbreak Skill
MAA_SnowBreak AI Agent Skill 规范
3 - aibot88 Bundle Chromosomal Instability Agent
---name: chromosomal-instability-agent
3 - aibot88 Bundle Dalle 3 Batch Asset Generator
Generates multiple image variations from a single brief using the OpenAI Images API (POST /v1/images/generations) with DALL-E 3, applying brand guidelines via structured prompt templates. Handles concurrent generation requests with retry logic for rate limit compliance.
3 - aibot88 Bundle Audit Linux Host Hardening Drift Before Exposing Ssh Or Roll
Uses Lynis to run an on-host security audit and turn the findings into a prioritized hardening checklist for an agent or operator. Invoke it when a machine is about to become internet-facing, after base image changes, or whenever you need a quick read on hardening drift instead of a generic vulnerability scan.
3 - aibot88 Bundle Block Agent Egress MCP Prompt Injection And Secret Exfiltrat
Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.
3 - aibot88 Bundle Build And Debug Custom Wordpress REST API Endpoints With Sch
Uses the WordPress wp-rest-api skill to help an agent design, register, validate, and troubleshoot custom REST routes without skipping schema, auth, or permission_callback details. This is for agent-led endpoint work in plugins, themes, or core-adjacent codebases, not for browsing the WordPress REST API as a product catalog.
3 - aibot88 Bundle Filter Prompts And Model Outputs For Injection Secrets Toxic
Screen prompts and responses with input and output scanners before an LLM interaction reaches production users or downstream systems.
3 - aibot88 Bundle Statically Scan Agent Repos For Prompt Injection And Unsafe
Audit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping.
3 - aibot88 Bundle Triage Active Security Incidents With AI Augmented Workflows
Guide live digital-forensics and incident-response work with human approval gates when the job is evidence review and triage, not general MCP setup.
3 - aibot88 Bundle Audit And Normalize Spdx License Headers Before Releasing Or
Use REUSE when an agent needs file-level licensing clarity instead of guessing from a single top-level LICENSE file. The agent checks compliance, adds or verifies SPDX headers, pulls missing license texts into LICENSES/, and produces a concrete remediation list or SPDX export.
3 - aibot88 Bundle Audit Github Actions Workflows For Insecure Permissions And
This ASE skill uses zizmor to audit GitHub Actions workflows and composite actions for security mistakes before they ship. An agent can scan local repos or remote GitHub repositories, flag risky permission scopes and unsafe workflow patterns, and return plain output, GitHub-native findings, or SARIF for follow-up automation.
3 - aibot88 Bundle Benchmark Prompt Injection Attacks Defenses And Recovery Pip
Run structured prompt-injection attack and defense experiments against an LLM-integrated app before production by measuring attack success and testing detection or recovery pipelines.
3 - aibot88 Bundle Block Unsafe Agent Actions And Scan Newly Added Skills With
Add a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.
3 - aibot88 Bundle Broker API Credentials To AI Agents Without Exposing Raw Key
Store credentials once, then inject them into outbound agent requests at runtime so agents can call services without receiving raw secrets.
3 - aibot88 Bundle Browse Search And Cost Audit Local Coding Agent Histories Be
Index local coding-agent sessions into a searchable SQLite-backed view so you can inspect usage, compare failures, and recover prior context quickly.
3 - aibot88 Bundle Co Author Structured Docs With Staged Context Gathering And
Use Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.
3 - aibot88 Bundle Coordinate Human In The Loop Agent Teams In Auditable Matrix
Run manager-worker agent collaboration in Matrix rooms where humans can watch, intervene, and keep credentials out of worker hands.
3 - aibot88 Bundle Detect Repository Licenses Before Dependency Approval Or Ope
Use Licensee when an agent needs to inspect a repository and determine what license text it actually matches before a dependency is approved or a codebase is redistributed. The skill is about evidence-backed license detection, not legal advice or broader compliance automation.
3 - aibot88 Bundle Encrypt And Decrypt Age Secrets With Hardware Backed Yubikey
Use age-plugin-yubikey when an agent needs age encryption tied to a physical YubiKey identity instead of software-only keys.
3 - aibot88 Bundle Extract Data And Complete Workflows In Your Real Logged In B
Use bb-browser when an agent needs to inspect pages, pull data, or complete form-driven tasks inside the user's actual logged-in Chrome session. It is for browser work where normal HTTP fetches fail because the important context lives behind auth, cookies, or internal web apps.
3 - aibot88 Bundle Investigate Crowdstrike Falcon Alerts And Telemetry Through
Use falcon-mcp when an agent needs CrowdStrike Falcon detections, incidents, behaviors, threat intel, or read-only response context to triage a security event without leaving an MCP workflow.
3
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include obsidian-vault-manager, cancer-metabolism-agent, owasp-zap-scanner-agent. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.