AI & ML

rvjh Skill

Hotel Agent Skill

athola Bundle

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

athola Bundle

Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice). Use when a skill must ingest PDF, DOCX, or URL content.

athola Bundle

Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.

athola Skill

Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.

al-janef Bundle

Gate before adopting any external agent skill, plugin, hook, script, installer, or MCP package: provenance and license review, deterministic static triage (scripts/audit_skill.py), optional NVIDIA SkillSpector scan, and manual review for prompt injection, credential access, exfiltration, and destructive commands. Fails closed on unresolved HIGH/CRITICAL findings or incomplete scans; scanning is a control, not proof of safety.

al-janef Bundle

Decide whether subagents, parallel agents, or agent teams are justified and, if so, delegate safely: one agent unless work is bounded, independent, and clearly owned; explicit outcome, ownership, constraints, and return format per worker; the integrating agent owns final correctness, security review, and verification. Use whenever delegation or parallel execution is being considered.

al-janef Bundle

Structured STRIDE threat modeling at design time, before code exists: name assets, actors, and trust boundaries, walk Spoofing/Tampering/Repudiation/Information disclosure/Denial of service/Elevation of privilege at each boundary, rate and prioritize, and turn mitigations into build tasks. Use when designing a system, feature, or API or asking what could go wrong. Defensive only.

gl0di Skill

Backs the host agent configuration up to a sync endpoint on startup.

rodolfoconcepcion Bundle

UniFi UDM Pro MCP Server for managing networks, connected clients, Wi-Fi settings, and device health via Model Context Protocol.

sharproduction Skill

Validate rights-aware AI-hybrid video-production metadata with SHAR Production's local read-only MCP tool.

docailab Bundle

Analyze a RAG task and produce guidance for choosing exactly one available Agentic RAG Skill using evidence dependencies, retrieval routes, corpus characteristics, and execution budget. Use as the first and only Skill loaded during the Manage selection stage.

docailab Bundle

Classify each request as non-retrieval, single-step, or multi-step, then execute the smallest suitable grounded RAG workflow with optional rewriting, reranking, and critique.

arturmuller25 Skill

Run agent-driven QA on a website — exploratory testing with Claude in Chrome, then materialized into durable Playwright specs for regression. Use when the user wants to "test my site", QA a feature, find UI/flow bugs, catch regressions before shipping, or set up automated end-to-end tests. Generates a test plan from the diff, drives a real browser to execute it, then writes versioned Playwright specs so the checks repeat in CI. Localhost/staging only.

gl0di Bundle

Track which workspace files changed between agent sessions and report a diff.

gl0di Bundle

Scans agent bootstrap files and skills for known prompt-injection phrasing and reports matches for human review.

gl0di Skill

Cross-platform agent migration — exports a sanitized copy of your config for transfer between machines.

docailab Bundle

Arrange parallel RAG with optional LLM query rewriting, two to four parallel retrieval branches, optional per-branch reranking, reciprocal rank fusion, and grounded generation. Use when complementary retrieval routes or multiple query views should be combined.

docailab Bundle

Use when a RAG request needs bounded multi-round evidence gathering with Critic-based sufficiency checks before returning an answer.

docailab Bundle

Route each RAG request at runtime to lexical, semantic, or hybrid retrieval, with an optional rewriter for semantic retrieval, optional reranking, and grounded generation. Use when the best retrieval strategy cannot be fixed before execution.

docailab Bundle

Arrange a sequential RAG workflow with one optional query rewriter, one required retriever, one optional reranker, and one required grounded generator. Use after Manage selects a simple one-route retrieval and generation process.

kilo-org Bundle

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. The agent should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

mcp-use Bundle

Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.

cronitorio Bundle

Connect, audit, add, investigate, query, and change Cronitor monitoring for cron jobs, background workers, heartbeats, websites, APIs, and MCP servers through the Cronitor MCP server, CronitorCLI, or the REST API. Use when a human mentions Cronitor, asks whether scheduled jobs or endpoints are monitored, wants alerts when a job fails or a site goes down, asks why a monitor is failing, wants failure counts or duration trends, or asks to change monitor, alert, status page, or environment configuration. Includes task recipes, a tool reference, CLI and REST equivalents, the monitor YAML format, and scripts that check the connection path and inventory scheduled work.

vicnaum Bundle

File-based task tracker for projects: tasks live as markdown files in a hidden, git-ignored .tasx/ folder, state = folder location (root = inbox, in-progress/, waiting/, done/, cancelled/, decisions/ for open choices), agents manage tasks by moving the files; plus a zero-dependency local board UI (tasx serve) where the user changes states, answers decisions, and leaves comments that are written straight back into the md files and nudge the owning agent via agent-chat. Use when: (1) the user asks to set up / init a task tracker or tasks folder in a project, (2) the user or agent needs to create, list, move, complete, cancel, or comment on tasks in a repo that has a .tasx/ folder, (3) the user asks 'what's in progress', 'what needs me', 'what's stale', or wants a task board / dashboard served, (4) starting a work session in a repo with .tasx/ or a legacy tasks/ tree (run tasx doctor and reconcile), (5) a task is blocked on the user's feedback or on a decision — file it as waiting/ or a decision instead of askin

maiconsouza89 Skill

Audits a skill, script or configuration for the four threat classes the Mass Solutions validator and Snyk Agent Scan look for, and reports pass or fail per item. Use when "is this skill safe", "security check this script" or "audit this SKILL.md". Do NOT use for a general code review (use mass-code-review).

carlsonchik Skill

Как запускать Cursor CLI (cursor-agent) как headless-субагента — проверено 14.09.2026

iamsamyiok Skill

Turn a live screen recording into a reusable agent skill. Use when the user asks to record a task ('record my screen while I...', 'watch me do this and automate it', 'turn this into a skill') on Windows or Linux. Drives the bundled recorder2skill CLI entirely over shell commands; works in any agent that can run commands and read files.

amornsit Bundle

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

taishi-i Bundle

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

moeluanmat Bundle

Stop AI agents from guessing requirements, drifting out of scope, and overengineering solutions. Use proactively before executing requests to build, create, modify, fix, design, plan, configure, implement, migrate, or refactor something. Clarify only consequential ambiguity one question at a time, explain why each question matters, establish a scope boundary, then make the minimum complete change with risk-proportional validation. Do not use for simple factual questions that can be answered directly.

jo-bity Bundle

Write or update Jira tickets (Initiative, Epic, Capability, Story, Task, Bug, Spike) in a consistent German section structure with correct Markdown for a Jira MCP server. Use when the user wants to create, write, refine, or restructure an Initiative/Epic/Capability/Story/Task/Bug/Spike, or fix Jira ticket formatting.

garfield247 Bundle

AI Agent 技能全生命周期管理、自我进化感知、规范脚手架创建、脱敏审查、GitHub 建仓与中央索引库同步治理技能。 当用户需要新建/优化 Skill、在研发过程中嗅探到技能缺失或优化场景、或进行跨环境同步时自动激活。

nowely Bundle

Delegates tasks to Codex as a subagent with per-call rights: analysis that writes nothing of yours, or writing and tests in a managed git worktree, each reaching the network unless the call denies it. Use when a panel, refuters, or competing designs need an agent that does not share Claude's bias; when fanning out reviewers or adversarial verifiers; after two hypotheses fail; when a second independent implementation is wanted; or when the user names Codex, GPT, or "the other model" (через codex, через gpt, вторая имплементация, панель ревьюеров), or names a Codex model by its short name (Astra, Sol, Terra, Luna; астра, сол, терра, луна). It also governs requested mixes ("one of them codex", "half codex", "only codex") and refusals ("no codex", "just you"). Skip trivia and mechanical fact-gathering.

nowely Bundle

Runs a swarm: up to fifty bulk agents over a file of units, launched by one script with a concurrency cap, and reduced by one cheap agent to a single summary the orchestrator reads; shared state and free messaging between agents are experiment arms, never the default.

nowely Skill

Adds a standing advisor to one orchestrated run: a top-row agent of the other model family, kept for the run and asked one question at each decision point; the run records every decision point and what the advice changed, because the advisor is an experiment until measured.