Search for AI agents
100 security-reviewed search listings, skills, MCP servers, and toolkits you can install into Claude Code, Cursor, and other agents with one command.
Jev Pref
Configure or use jev-pref for semantic preference-based code review. Use when setting up jev-pref or reviewing changes in an already configured repository.
Supergrep
Retrieval + inference offload for AI coding agents.
Mock Interview
Conduct one stateful mock-interview operation using an exact application JD and submitted resume. Use only inside the mock-interview workflow for planning questions, deciding a follow-up, evaluating one question after the interview, or producing a practice report; do not use for employer-process claims or general interview research.
Resume Tailoring
Draft or revise a resume for one specific job using an exact resume version, a complete JD, and grounded match evidence. Use only inside the resume-tailoring capability; never use for job discovery or unsupported career-history invention.
Skill Design Reference
Use when creating or reviewing a Skill package for this Career Agent, including its SKILL.md, progressive disclosure, tool workflow, MCP coordination, subagent boundaries, validation, and iteration rules.
Job Research
Research public company, product-line, business, market, and competitor context for one saved job when the user explicitly requests it. Do not use automatically during job matching, resume tailoring, or interview preparation, and do not claim to recover a specific team's private work from a generic JD.
Job Discovery
Use when the user explicitly asks to find new jobs or open a recruitment-platform search page.
Shodan Skill
Use the installed shodan-skill CLI for documented Shodan REST, Streaming, Trends, and Exploits operations, including host intelligence, search and facets, DNS, scans, alerts, notifiers, bulk datasets, organizations, API-plan and credit-balance checks, and real-time feeds. Trigger for Shodan lookups, exposure research, scan or monitoring requests, API coverage questions, and Shodan account or Ente…
Competitor Gap
Identify a domain's real search competitors from shared rankings, then map keyword, content, backlink, and traffic-channel gaps with a prioritised closing plan. Use when the user asks who competes with them in search, which keywords or content they are missing, or how they compare against a named competitor.
Technical Seo Audit
Audit crawlability, indexability, HTTPS and redirects, Core Web Vitals, mobile parity, metadata, canonicals, structured data, and internal architecture using Semrush Site Audit data, separating confirmed defects from analyst judgment. Use when the user asks for a technical SEO audit or a site health check, why pages are not indexed, or why a site is losing search visibility for technical reasons.
Keyword Research
Run a keyword research workflow on a topic or domain — existing rankings, keyword ideas from a seed, intent classification, filtering by volume, difficulty, CPC and business value, then clustering by topic. Use when the user asks for keyword research, keyword ideas, search volume or keyword difficulty, or which keywords to target.
Agent Evaluation
Evaluate prompt, model, retrieval, and agent changes through repeated trials and outcome grading.
Documentation Site
Build and migrate Zensical documentation sites, navigation, search, and course pages.
Cnki Search
Search Chinese journal literature on CNKI by keywords; use for basic China National Knowledge Infrastructure searches.
Cnki Navigate Pages
Change CNKI result pages, page size or sorting while retaining the current search criteria.
Cnki Advanced Search
Search CNKI with subject, title, author, institution, journal and date filters using the current advanced-search UI.
Cnki Researcher
Coordinate a CNKI literature workflow from search and screening to evidence-based reading and citation export.
Cnki Parse Results
Extract and deduplicate records from the currently open CNKI results page without changing the search.
Jevify
Use Jev as System One to save the user reasoning-model tokens, time, and cost on bulk reading or repeated semantic decisions. Trigger when sifting large documents or tool outputs, selecting evidence or actions from many candidates, or checking many items against criteria, even if the user never mentions Jev. Also use for "Jevify this", Jev question design, and product work where frequent, inexpen…
Prompt Injection Defense
Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a tool set fixed before content is read, consequential calls gated on the user, and destinations that cannot be chosen by the content. Use when an agent reads web pages, retrieved documents, emails, tool results, file contents or another agent's output and can also take actions, when…
Context Engineering
Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining, what compaction must preserve, and what loading everything costs. Use when a prompt or agent pulls in many files, docs or tool transcripts, when quality decays over a long session, when choosing between fetching at runtime and pasting up front, or when a context has to be trimmed…
Model Routing
Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same task set, a readable routing rule, and an explicit retry-versus-fallback path with pinned model ids. Use when cost or latency has become a problem, when adding a cheaper or larger model to an existing system, or when a fallback fires silently and quality drops without anyone not…
Memory Design
Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory is detected and retired. Use when an agent forgets something across sessions, when a memory or persistent-context feature is being designed, or when stored memories have grown noisy, wrong, or are leaking between users. Not for retrieval over a document corpus, not for prompt or…
Jev Search
Use after any web or API search, before opening results or spending another round. Jev picks which results to read, whether the evidence is enough, and which query to run next from ones you wrote.
Rankcontrol
RankControl (rctrl.com) - Your Agentic SEO suite. Seven AI agents discover the questions buyers ask ChatGPT, Perplexity, Claude, Gemini, Grok, and Google, write brand-matched guides, and publish them as native posts. Track AI citations, rankings, backlinks. Earn traffic from AI search and Google.
Fastsearch Mcp
⚡ Lightning-fast file search MCP server using NTFS Master File Table - WizFile performance for Claude Desktop
Mneme
🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.
Jevgrep
Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
Redmine Ai Helper
A Redmine plugin that adds AI agents, MCP Server, smart completion, and vector search.
Awwards Mcp
Free, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA, capture and record live sites. A Mobbin alternative. No API key.
Altprobe Lab
collector
Tilth
Smart code reading for humans and AI agents. Definitions, callers, dependencies and function-level diffs from tree-sitter. One binary, no index. MCP server + CLI. Install: cargo install tilth or npx tilth
Search Procedures
Model how a specification universe is actually walked, rather than assuming it is enumerated. Implements the search procedures a p-hacker or a pressured agent uses (first-significant stopping, random trial within a budget, greedy coordinate descent from the pre-registered analysis, random hill-climbing, and the two-stage split-sample walk with an optional continuation rule, after Adda, Decker and…
Phack Eval Harness
Run and score the agent p-hacking benchmark. Composes prompt cells across research framing and significance pressure, drives an agent through them, and scores each run into a P-Hacking Intensity index decomposed into selection, search breadth, estimate inflation, inference gap, pre-registration departure and disclosure. Use when benchmarking whether an AI agent p-hacks, comparing models or tool s…
Framing Attacks
Catalogue of prompt framings that determine whether an agent refuses or performs specification search, and the harness for probing them. Reproduces and extends the published finding that coding agents refuse an explicit request for significant results but comply when the identical request is reframed as uncertainty reporting. Use when running a red-team probe of statistical guardrails, designing…
Specification Search
Run an instrumented walk of a specification universe and recover honest inference from it. Estimates every specification in a design card (or walks it with a realistic search procedure), logs a complete ledger, flags pathological specifications, calibrates the search against an enforced null, runs the Simonsohn joint tests on the whole curve, measures how far the finding sits from the pre-registe…
Forking Paths
Map the garden of forking paths for a concrete econometric design and turn it into a machine-readable design card that the specification-search engine can walk. Use when asked how many defensible analyses a dataset or research design admits, to enumerate researcher degrees of freedom for a specific DiD, IV, RDD, staggered-adoption, panel or cross-sectional study, to build or validate a design car…
Phack Immunization
Make an empirical analysis robust to specification search, before or after the fact. Covers pre-registration and pre-analysis plans encoded as design cards, specification-curve reporting with the Simonsohn joint tests, Romano-Wolf and effective-multiplicity corrections, full-procedure null calibration including for sequential searches, the distance-from-pre-registration diagnostic, split-sample a…
Phack Taxonomy
Name and classify p-hacking strategies, and quantify what each one does to the false-positive rate. Covers the twelve-strategy compendium of Stefan and Schoenbrodt (2023), thirteen econometrics-specific degrees of freedom (clustering doctrine, fixed-effect structure, RDD bandwidth, kernel and inference mode, IV instrument sets and first-stage screening, staggered-DiD estimator and comparison-grou…
Phack Router
Entry point for the p-hacking skills suite. Routes a request to the right sub-skill for (a) mapping researcher degrees of freedom in an econometric design, (b) running an instrumented specification search, (c) detecting p-hacking in a body of results, (d) immunising an analysis against it, or (e) running the agent p-hacking evaluation harness. Use whenever the request involves specification searc…
Narrative Laundering
Audit how an empirical write-up presents its analytical choices, and detect the rhetorical moves that convert a specification search into an apparently confirmatory finding. Covers HARKing, robustness theatre, selective disclosure, the vanishing pilot study, and estimator-choice narratives. Use when reviewing a paper or an agent-produced report for undisclosed search, refereeing an empirical manu…
Phack Polyglot
Run the instrumented specification search in the user's own statistical language — Stata (reghdfe, ivreghdfe, rdrobust, did2s), R (fixest, rdrobust, did2s), Python (statsmodels, linearmodels) or StatsPAI — and bring the results back into the audit, null calibration and honest report. Exports the enumerated grid as a language-neutral specs table plus a generated runner, ingests the runner's ledger…
Melech Diff Minimizer
Minimize an existing PR or diff while preserving its required behavior and containing semantic blast radius.
Arc1 Adt Abap Mcp Ext
Eclipse plugin that wakes SAP's dormant ADT MCP server and contributes extra read-only ABAP repository tools (search, metadata, find-definition, system info) for Claude Code / Copilot / Cursor / Claude Desktop.
Semantic Km Creator
A Claude skill from ontology-of-everything/concept-skills.
Semantic Pkm Creator Cn
>-
Semantic Km Creator Cn
Builds evidence-only Kimball semantic layers for enterprise knowledge from APIs, CLIs, or tables/databases with an HTML decision workbench; emits OKF/YAML. Use when 企业知识、知识建模、KM、semantic-km-creator-cn、semantic-creator、semantic layers, dimensional models, ontology, OKF, 语义层、接口转语义、维度建模或本体.
Semantic Pkm Creator
>-
Smart Test Me
Educational retrieval-practice skill — active recall, prediction, confidence calibration, and transfer; not multiple choice, trivia, or flashcards. Invoke when the user runs /smart-test-me <target> where the target is code, an architectural area, or a concept (e.g. /smart-test-me @src/auth/login.ts loginUser, /smart-test-me @src/api, /smart-test-me async-await) or explicitly asks to be tested to…
Nyaa
Search and download anime torrents from nyaa.si. Use when the user needs to find anime, manga, or East Asian media torrents.
Tvdb
Search and retrieve TV series, movie, and people info from TheTVDB. Get details by ID, list episodes, seasons, and artwork. Use when looking up TV/movie metadata from TheTVDB.
Yts
Search and download movie torrents from YTS (YIFY releases). Use when the user needs to find or download movie torrents with quality and rating filters.
Jellyfin
Interact with the Jellyfin media server API to list libraries, search media, get item details, export metadata, and trigger library rescans. Use when working with Jellyfin servers.
Imdb
Search IMDB for movies, TV series, and people. Get details by name or ID, browse upcoming/popular titles. Use when looking up movie/TV/celebrity info from IMDB.
Plex
Interact with a Plex Media Server to list libraries, search media, get item details, manage playlists and collections, export metadata, and trigger library rescans. Use when working with Plex servers.
Libgen
Search and download ebooks from Library Genesis (LibGen). Use when the user needs to find or download ebooks, EPUBs, or PDFs from LibGen.
Deep Research
Use when a task needs material external evidence, frame discovery, multi-source retrieval, provenance/freshness, competing explanations, or explicit Deep/Max/Ultra research.
Serpapi Web Search
>-
Ng Accessibility
Make an Angular (v17+) application accessible – semantic HTML, keyboard & focus, color contrast, text alternatives, accessible forms & tables, plus Angular-specific tooling (ARIA attribute bindings, CDK a11y LiveAnnouncer/cdkTrapFocus, Angular Aria & Material, accessible custom components, router titles/active-links/focus management). Use when the user wants to improve accessibility/a11y, meet WC…
Web Search
多源搜索（17源+学术API+auto路由）
Sealeap Amazon Ca Apparel Ads
Diagnose and draft Amazon Canada apparel advertising plans with lifecycle and seasonal timing, English/French search coverage, account evidence, profitability guardrails, and approval-ready experiments. Use for 加拿大站服饰广告, Amazon.ca Coat 外套夹克, Underpants 内衣文胸, 季节性长生命周期, 长生命周期, 新品期成长期成熟期, 广告预算配比, SP/SB/SBV/SD/商品投放, 法语关键词, 旺季预热, 复购再营销, CPC/ROAS/ACOS 异常, or when converting the authorized course materi…
Sealeap Baize Amazon Ad Strategy Router
Route an Amazon product into precise-attribute, broad-intent, or no-clear-keyword advertising structures based on product truth, search behavior, conversion, and unit economics. Use for 不同产品怎么选广告打法、服装多变体、泛流量品、无明确关键词产品、保守或进攻策略.
A11y
Master accessibility audit skill that scans every screen with axe-core, tests keyboard navigation, checks focus visibility, audits ARIA and semantic structure, then fixes every violation from critical down to minor. Works screen by screen in priority order with visual and programmatic verification. Use when user wants to fix accessibility issues, meet WCAG 2.1 AA, improve keyboard nav, or invokes…
Full Meeting
Use when the user has an upcoming meeting and wants a comprehensive brief on the person they're meeting. Acts as a senior meeting strategist: pulls rich profile data (work history, education, skills) and company context from FullEnrich, supplements with web search for fresh signals, and delivers a structured brief with expert talking points, suggested questions, and tactical advice on how to run…
Full Prospecting
Use when the user wants to find and enrich B2B contacts matching an ICP. Triggers on: \"find me contacts\", \"build a prospect list\", \"search for people\", \"enrich leads\", or any request describing a target audience by title, industry, location, or company size.
Naming Scout
Find and validate names for a company, product, SaaS, app, CLI, library, newsletter, community, agency, course, or content brand. Runs a positioning interview, generates inside metaphor territories rather than by permutation, filters for brand quality, then verifies domains and namespaces at registry level. Use when the user asks for name ideas, a brand name, a product, project or domain name, he…
Metasploit
Drive msfconsole across the workflow - DB-backed recon (db_nmap, auxiliary scanners), version->exploit search/check/run, multi/handler reverse shells (meterpreter-first, plain shell_reverse_tcp backup for Windows/EDR), sessions + local_exploit_suggester + post modules, and autoroute/portfwd/socks pivoting. Points to the metasploit cheatsheet for syntax. Use for "metasploit", "msfconsole", "msfven…
Wiki
Search, query, and maintain the qmd-indexed wiki - semantic search, keyword search, re-index after adding pages, check index status.
Symbolgraph
Local-first code intelligence for AI agents — tree-sitter symbol graphs and hybrid (FTS5 + vector + graph) retrieval via CLI and MCP server.
PyMemoryEditor
A pure-Python library that lets you inspect, modify and search the memory of any running process in a few lines of Python :snake: .
Transcripts Mcp
Search local Cursor, Claude Code, and Codex session transcripts via MCP
Writing Guard
Scientific manuscript writing, polishing, auditing, and safe Word editing guard. Use for academic papers, abstracts, introductions, methods, results, discussions, rebuttals, DOCX edits, AI-style cleanup, defensive-writing cleanup, over-explanation reduction, semantic-restatement cleanup, scientific-claim preservation, table formatting, and edit-scope verification.
Topper Mcp
Top Paper Retriever — top-only academic paper search (CCF A/B · 中科院 1/2 区 · flagship journals) as a library, CLI and MCP server
Seo Keyword Preserving Rewrite
Rewrite or humanize text while keeping target SEO keywords, entities, and rough keyword density intact. Use when improving copy that must still rank — blog posts, landing pages, product descriptions — and the user cares about specific keywords, search intent, or on-page SEO.
Agentwheel
Manage and explicitly inspect reusable agent artifacts with Agentwheel. Use when the user asks to search, add, install, update, customize, eject, or uninstall skills, integrations, workflows, or other OpenPack artifacts across runtimes. For automatic capability suggestions, install the separate agentwheel-discovery skill.
Agentwheel Discovery
MUST use proactively when a request expresses an operational intent that an existing reusable skill or integration could plausibly fulfill—even if the user did not ask for a skill or describe a capability gap. Inspect installed artifacts, then run Agentwheel semantic search before generic or manual solution design when none already covers the intent. Suggest up to three evidence-backed matches an…
S2 Cli
Semantic Scholar CLI (`s2`) for on-demand citation graph lookup: papers a work cites, papers that cite a work, and graph search across 200M+ papers. Use whenever the user asks for Semantic Scholar, S2, cited papers, references, bibliography, citing papers, citation count from Semantic Scholar, or papers outside a local catalog. Prefer `s2` over curl or ad-hoc Graph API requests.
Awesome Seo Mcp
A curated list of MCP servers for SEO. Search Console, keywords, backlinks, crawling, SERPs and AI search visibility, verified with install details and auth requirements.
Explore Run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Do not use…
Literature Search
Medium-depth literature search — read AI-summarized reports for every paper analyzed
Literature Overview
Quick landscape scan — discover papers on a topic without full-text reading
Okf Agent Memory
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Semantic Compression
>
Universal Memory Mcp
超级个人助理 - 通用、跨项目、100%本地私有的AI记忆系统（基于MCP协议）- Super personal assistant for any AI CLI - Universal, cross-project, 100% local & private via MCP
Refactoring Code
Use when semantic refactoring is needed in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, XAML, Razor, and other GameDev or mixed-language projects. Trigger when edits must update declarations and usages across IDE-resolved references — rename symbols, move types or namespaces, safe-delete unused code, extract interface/base class/method, change sign…
Ue Code Authoring
Use when writing or modifying Unreal Engine C++ — classes, actors, components, subsystems, interfaces, ability-system (GAS) code, module dependencies, reflected UPROPERTY/UFUNCTION API, native gameplay tags, and testable gameplay behavior — in a project open in JetBrains Rider. Source changes go through Read/Grep/Glob/Edit/Write; Rider supplies symbol search, code analysis, formatting, and builds…
Research
Search authoritative primary sources and verify factual claims in official documentation
Notes
CLI and MCP server to search and browse Apple Notes
Novelty Assessment
Assess research idea novelty through systematic literature search. Multi-round search-evaluate loops with harsh critic persona. Binary novel/not-novel decision with justification. Use before committing to a research direction.
Citation Management
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Literature Search
Search academic literature using Semantic Scholar, arXiv, and OpenAlex APIs. Returns structured JSONL with title, authors, year, venue, abstract, citations, and BibTeX. Use when the user needs to find papers, check related work, or build a bibliography.
Learning Accelerator
Compresses domain mastery using Ultralearning and Metacognition principles — moving from passive consumption to active production through directness, retrieval practice, and feedback loops. Use when learning a new domain rapidly, building a study plan, or preparing for a high-stakes professional skill.
Git Commits
Write clear, semantic git commit messages and PR/MR titles following Conventional Commits. Use when the user asks to write commit messages, format git history, improve commit quality, or set a PR/MR title, or mentions "commit message", "conventional commits", "merge message", or "git history". For the full PR/MR body description, use the create-pull-request skill instead. Generates professional,…
Hiring Manager Intake
Runs the intake / kick-off conversation with a hiring manager and produces a role brief that de-risks the search — business case, success measures, ranked trade-offs, target profile and pool, comp reality, interview loop, agreed service levels, calibration plan and open risks. Use when the user is about to run or is on a hiring manager intake, kick-off, scoping or briefing call; when they say "I'…
Job Navigation Skill
Research current job markets and hiring requirements, analyze recent job descriptions (JDs), compare them with a user's resume, projects, skills, and constraints, and turn evidence gaps into prioritized career actions. Use when students, job seekers, or career changers ask about current role or industry outlook (including “现在行情怎么样”), whether a role or JD fits them (including “这个JD适合我吗”), cross-pl…
Research Company
Build a structured intelligence brief on a company from its LinkedIn page posts plus the personal posts of up to three of its executives, using the Insaight MCP server, then score it as a prospect on fit, pain signals and decision-maker visibility. Covers where the company came from, what it is shipping and hiring for now, and where it is heading. Use this skill whenever the user points at a comp…
Research Person
Build a structured intelligence brief on one person from their LinkedIn posts and their full profile — experience, education, skills, languages, volunteer work — using the Insaight MCP server. Covers role and career trajectory, content themes, decision-maker signals, outreach hooks, and uncommon commonalities to open a cold message with. Use this skill whenever the user points at a named individu…
Citation Management
Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Exa Search
Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when…
Synapto
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP