agentsclimarketplace

Context & AI engineering

25,745 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Ent prompt troubleshoot

    kalyvask/entrepreneurship-lessons/.claude/skills/ent-prompt-troubleshoot Skill

    1★ repo

    Help the user fix AI prompts that aren't working — generic output, hallucinated facts, instruction-ignoring, output that's too long/short, no actionable conclusions. Use when the user complains about AI giving "slop," when they say "this prompt isn't working," or when they're frustrated with generic AI output.

  • Client memory synthesizer

    afelipeg/Anthropic-Skills-for-enterprise-marketing-os/skills/client-memory-synthesizer Skill

    1★ repo

    Synthesizes client history, decisions, preferences, risks, scope changes, operational patterns, commercial context, performance learnings, and relationship dynamics into reusable client memory briefs. Use when preparing client handovers, onboarding new team members, building tenant context, summarizing historical decisions, recovering institutional knowledge, or creating an executive memory layer for the Agency Growth OS. Also trigger when someone says "prepare the QBR", "quarterly review", "client business review", "what happened this quarter", "Q[N] results", "prepare the deck for the client", or "quarterly performance summary". Even casual phrasing like "how did we do this quarter?", "prep for the quarterly", "what's the Q[N] story?", or "summarize the quarter" should activate this skill.

  • Media procurement benchmark

    afelipeg/Anthropic-Skills-for-enterprise-marketing-os/skills/media-procurement-benchmark Skill

    1★ repo

    Benchmarks media costs, supplier terms, inventory quality, volume commitments, make-goods, rebates, payment terms, and procurement efficiency. Use when evaluating media supplier negotiations, annual volume deals, rate cards, platform costs, publisher proposals, or whether media buying terms are commercially competitive. Also trigger when someone says "is this a good rate?", "are we overpaying?", "evaluate this media proposal", "compare publisher rates", "review the IO", "negotiate the deal", "assess this rate card", or when media-routing-planner routes here to validate carrier/supplier terms. Even casual phrasing like "is this CPM right?", "should we take this deal?", "what should we pay?", or "can we get a better rate?" should activate this skill.

  • Agent browser

    NafisRayan/100x-Agent-Toolkit/skills/agent-browser Skill

    no license1★ repo

    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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

  • Agent personas

    NafisRayan/100x-Agent-Toolkit/skills/agent-personas Skill

    no license1★ repo

    142 expert agent personas organized across 23 categories for every software development role — from planning and architecture through coding, testing, security, deployment, and maintenance. Use when needing to invoke a specialized agent role, understand which agent to use for a task, compose multi-agent teams, or find the right persona for code review, debugging, build resolution, or project orchestration. Also use when setting up agent-based workflows, understanding agent capabilities, or deciding between multiple agents for a task. Covers core engineering, development, data/AI, infrastructure, security, quality/testing, spec pipeline, orchestration, build resolution, language-specific review, framework specialization, and more. Trigger on "which agent", "use agent", "agent persona", "agent for", "multi-agent team", "agent team", "orchestrate agents", "delegate to agent", or when configuring agent-based development workflows.

  • Dispatching parallel agents

    NafisRayan/100x-Agent-Toolkit/skills/dispatching-parallel-agents Skill

    no license1★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    The same file is in 13 other repositories

  • Mcp builder

    NafisRayan/100x-Agent-Toolkit/skills/mcp-builder Skill

    no license1★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 42 other repositories

  • Skill creator

    NafisRayan/100x-Agent-Toolkit/skills/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Subagent driven development

    NafisRayan/100x-Agent-Toolkit/skills/subagent-driven-development Skill

    no license1★ repo

    Use when executing implementation plans with independent tasks in the current session

    The same file is in 6 other repositories

  • Ultrareview

    NafisRayan/100x-Agent-Toolkit/skills/ultrareview Skill

    no license1★ repo

    Multi-agent parallel code review system inspired by Claude Code's /ultrareview. Spawn 5-20 specialized agents (security, logic, performance, edge cases, architecture) to review code simultaneously, cross-validate findings, and produce a consolidated bug report. Use when asked to do deep code review, ultrareview, multi-agent review, comprehensive bug hunting, security audit, or thorough pre-merge code inspection.

  • Agent trajectory evaluator

    imtiazrayhan/agentscamp-library/skills/agent-trajectory-evaluator Skill

    1★ repo

    Evaluate a multi-step AI agent's whole run — tool calls, intermediate steps, and final result — not just final-answer correctness, so you can pinpoint WHERE it went wrong. Use when building or debugging a tool-using or multi-step agent, when final-answer-only evals can't explain failures, or when a prompt/model change quietly makes the agent less efficient or more error-prone even though the answer still looks right.

  • Chunking strategy optimizer

    imtiazrayhan/agentscamp-library/skills/chunking-strategy-optimizer Skill

    1★ repo

    Find the chunking strategy and size that maximizes retrieval quality for a specific corpus, by sweeping configurations against a fixed eval set instead of guessing. Use when RAG answers miss obvious content, when standing up a new corpus, or when picking chunk size/overlap.

  • Claude settings auditor

    imtiazrayhan/agentscamp-library/skills/claude-settings-auditor Skill

    1★ repo

    Audit every Claude Code settings layer — user, project, local, and managed — and report the effective merged configuration with its risks: over-broad Bash allows, missing deny rules for secrets, bypassPermissions defaults, unvetted MCP servers and hooks, and rules that never match. Use before trusting a new repo's checked-in settings, or to harden your own before handing the agent more autonomy.

  • Embedding index tuner

    imtiazrayhan/agentscamp-library/skills/embedding-index-tuner Skill

    1★ repo

    Tune a vector index — HNSW graph parameters and quantization — to hit a recall target at the lowest latency and memory, by sweeping settings against a fixed query set instead of trusting defaults. Use when vector search is slow or memory-hungry, when recall dropped after enabling quantization, or when standing up an index and you need defensible parameters.

  • Embedding set inspector

    imtiazrayhan/agentscamp-library/skills/embedding-set-inspector Skill

    1★ repo

    Diagnose the health of an embedding set before blaming the retriever — checking normalization, dimensionality, near-duplicates, degenerate vectors, and corpus/query distribution mismatch. Use when retrieval quality is poor, after a re-embed, or before shipping a new index.

  • Hallucination evaluator

    imtiazrayhan/agentscamp-library/skills/hallucination-evaluator Skill

    1★ repo

    Detect and measure ungroundedness in LLM and RAG outputs — claims the source doesn't support — by decomposing answers into atomic claims and checking each for entailment, so you can quantify faithfulness and gate on it instead of eyeballing it. Use when a RAG/LLM feature makes confident wrong claims, before shipping anything that must be factual, or to add a groundedness gate to evals/CI.

  • Hook writer

    imtiazrayhan/agentscamp-library/skills/hook-writer Skill

    1★ repo

    Turn a plain-language automation request — 'format every file Claude edits', 'block writes to migrations', 'notify me when input is needed' — into a working Claude Code hook: the right event, a safe tested script, and the settings.json registration at the right scope. Use when you want a hook but don't want to hand-write the matcher, stdin JSON parsing, and exit-code plumbing.

  • Llm as judge scorer

    imtiazrayhan/agentscamp-library/skills/llm-as-judge-scorer Skill

    1★ repo

    Design a reliable LLM-as-judge metric — a calibrated rubric, a clear scoring scale, and bias controls — and validate it against human labels before trusting it. Use when grading open-ended LLM output (summaries, answers, tone) that exact-match can't score.

  • Llm eval suite scaffolder

    imtiazrayhan/agentscamp-library/skills/llm-eval-suite-scaffolder Skill

    1★ repo

    Stand up an evaluation suite for an LLM feature from scratch — a representative dataset, the right metrics, a baseline score, and a CI gate — using DeepEval, promptfoo, or RAGAS. Use when a feature has no evals, before tuning a prompt, or when adding an LLM feature to CI.

  • Llm guardrails designer

    imtiazrayhan/agentscamp-library/skills/llm-guardrails-designer Skill

    1★ repo

    Design input and output guardrails for an LLM app — decide what to check (injection patterns, PII, secrets, policy, schema, leakage, toxicity), place them as input vs. output rails, implement with a library like NeMo Guardrails or LLM Guard, and fail closed. Use when adding a safety/validation layer around an LLM, not relying on the prompt alone.

  • Llm output schema generator

    imtiazrayhan/agentscamp-library/skills/llm-output-schema-generator Skill

    1★ repo

    Turn an example of the data you want from an LLM into a precise, validated output schema (Pydantic / Zod / JSON Schema) and wire it into structured-output calls. Use when adding typed LLM output, replacing brittle JSON parsing, or designing an extraction shape.

  • Mcp server scaffolder

    imtiazrayhan/agentscamp-library/skills/mcp-server-scaffolder Skill

    1★ repo

    Scaffold a new Model Context Protocol (MCP) server from a description — pick the SDK and transport, generate a typed first tool with a strict schema, and wire up MCP Inspector testing and the client-registration command. Use when starting a new MCP server and you want a correct, runnable skeleton instead of copying a README.

  • Memory leak hunter

    imtiazrayhan/agentscamp-library/skills/memory-leak-hunter Skill

    1★ repo

    Find and fix a memory leak in a running app: confirm it's a real leak under steady load, diff two heap snapshots to name the growing object and its retention path, cut the root reference that blocks collection, and re-run to confirm memory plateaus. Use when RSS climbs until OOM/restart, heap grows unbounded across a steady workload, or GC pauses worsen the longer the process runs.

  • Prompt cache optimizer

    imtiazrayhan/agentscamp-library/skills/prompt-cache-optimizer Skill

    1★ repo

    Restructure an LLM call to maximize prompt-cache hit rate and add response/semantic caching — move the stable prefix (system prompt, instructions, few-shot, context) to the front and variable input to the end, set cache breakpoints, and measure the hit rate and savings. Use when repeated calls share large common context and token cost or latency is too high.

  • Prompt optimizer

    imtiazrayhan/agentscamp-library/skills/prompt-optimizer Skill

    1★ repo

    Diagnose why a prompt underperforms and rewrite it with the technique that fixes it — clearer structure, few-shot examples, an explicit output contract, or reasoning scaffolding — returning an optimized prompt, the rationale for every change, and what to measure to confirm the lift. Use when a prompt is flaky, verbose, drifting in format, or just not good enough.

  • Prompt pii redactor

    imtiazrayhan/agentscamp-library/skills/prompt-pii-redactor Skill

    1★ repo

    Detect and redact PII and secrets from prompts (and logs/traces) before they reach an LLM provider — mask or tokenize emails, phone numbers, names, IDs, and API keys, reversibly where the response needs the real values back. Use when sending user or document data to a third-party model, or when LLM request logs may capture sensitive data.

  • Prompt regression tester

    imtiazrayhan/agentscamp-library/skills/prompt-regression-tester Skill

    1★ repo

    Build a regression test harness for an LLM prompt so a prompt edit or model upgrade can't silently degrade quality — a fixed eval set, checkable assertions, and a diff against a committed baseline. Use when changing a production prompt, migrating model versions, or any time 'I tweaked the prompt' needs to be backed by evidence instead of eyeballing two outputs.

  • Tool definition generator

    imtiazrayhan/agentscamp-library/skills/tool-definition-generator Skill

    1★ repo

    Generate clean function/tool schemas for an LLM agent from existing code or a spec — accurate JSON Schema, model-facing descriptions, honest required fields, and enums that make invalid calls impossible. Use when wiring functions into an agent's tool-calling loop.

  • Claude design animation capture

    Jody09-dotcom/constructionx-skills/skills/claude-design-animation-capture Skill

    1★ repo

    Convert a Claude Design Animation export (ZIP or folder) into a clean 1080x1920 H.264 MP4 ready for Reels, Shorts, TikTok, or any social upload. Use when the user asks for "render claude design", "capture animation export", "mp4 from claude design", "claude design to video", "export animation to mp4", or has a Claude Design Animation ZIP and wants a video file. Bridges the gap that Claude Design has no native MP4 export. Spins up a tiny local HTTP server to serve the React+Babel HTML, drives Playwright to record at the requested dimensions, runs ffmpeg to crop/trim/transcode. Requires Playwright and ffmpeg installed locally.

  • Plan

    gitgitWi/council-flow/skills/plan Skill

    no license1★ repo

    Multi-LLM Plan and TDD flow

  • Social hook generator

    SkillMedev/social-media-studio/skills/social-hook-generator Skill

    1★ repo

    Generates 10 labeled opening lines for a written social post, one per hook archetype, so the writer can test instead of guess. Use when drafting or rewriting the first line of a LinkedIn post, X post or thread, Instagram caption, or newsletter intro. Do NOT use when the hook is the spoken or on-screen opener of a short-form video (TikTok, Reels, Shorts) - use video-hook-writer instead.

    The same file is in 1 other repository

  • Coding

    vindm/dotclaude/plugins/core/skills/coding Skill

    1★ repo

    Elicit coding hygiene intent for a project and write it to a thin artifact — `.claude/dotclaude/code-anti-patterns.md` plus a few `dotclaude.yml` keys — derived from the project's actual file-size distribution and the bug classes visible in git history. No agent, rule, or hook is authored: the consumed `code-review` agent already reads this artifact at runtime. Invoke /dotclaude:coding in any project root with source code.

  • Testing

    vindm/dotclaude/plugins/core/skills/testing Skill

    1★ repo

    Elicit test-coverage risk priorities for a project and write them to a thin artifact — `.claude/dotclaude/test-risk-model.md` plus a `dotclaude.yml` key — derived from the project's actual test/source ratio, its most-edited untested files, and the user's own sense of what scares them most. No agent, rule, or hook is authored: the consumed `test-architect` agent already reads this artifact at runtime. Invoke /dotclaude:testing in any project where tests exist OR should exist.

  • Worktree

    vindm/dotclaude/plugins/core/skills/worktree Skill

    1★ repo

    Set up worktree-per-feature discipline for a project where several AI sessions (or humans + agents) work concurrently and collide in one checkout. Writes a thin `worktree:` config block that the plugin's CONSUMED main-checkout hook reads (no rendered per-project hook copy), plus a project-specific worktree lifecycle skill — calibrated by interview (which repo, what's exempt, how a fresh worktree gets configured) and PROVEN by a live smoke worktree before handoff. Invoke /dotclaude:worktree when parallel sessions are real or planned.

  • Discovery handoff

    stanislavnianko/product-discovery-claude-skills/plugins/discovery-phase/skills/discovery-handoff Skill

    1★ repo

    [discovery-phase pack · deliverables] Hands discovery findings to a delivery team (could be same agency squad in delivery phase, different agency, or client internal team). Captures decisions made, open questions, risks transferred, evidence chain. The "what we know vs what we don't" document. Produces discovery-handoff.md.

  • Mba infographic prompts

    refaelach/gmba-class-19-skills/skills/exam-or-class-prep/mba-infographic-prompts Skill

    1★ repo

    Generate a ready-to-paste GPT image prompt for an MBA classroom infographic — formula, framework, process, comparison, study sheet, or concept map. Output is a polished prompt formatted per the OpenAI gpt-image-2 prompting guide plus a fresh ChatGPT link to paste it into; this skill produces text, not images. MANDATORY TRIGGERS: 'make me an infographic', 'generate an infographic prompt', 'turn this into an infographic', 'create a cheat sheet for', 'make a study sheet on', 'visualize this framework', 'design a concept map for'. STRONG TRIGGERS (when the topic is business / management / finance / stats / strategy): 'make me a visual for X', 'I need a diagram of', 'how should I picture this', 'turn this PDF into a visual', 'illustrate this concept', 'make a poster for class about', 'visualize this book / chapter / framework'. Do NOT trigger on: requests to actually render or generate the image (this skill produces a prompt only — the user pastes it into ChatGPT), requests for non-MBA / non-business visuals (personal art, party invites, kids' projects), requests for live data charts from a spreadsheet (use a charting tool), requests for multi-slide decks (this is for single-frame infographics). DO trigger when the user wants a polished, deliberately-shaped prompt for a static MBA-context infographic that they will paste into ChatGPT — even on casual phrasing if the topic is clearly business / management / finance / stats.

  • Agent introspection debugging

    simanam/theaiteam/team/skills/engineering/agent-introspection-debugging Skill

    no license1★ repo

    Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

    The same file is in 5 other repositories

  • Claude api

    simanam/theaiteam/team/skills/engineering/claude-api Skill

    no license1★ repo

    Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

    The same file is in 1 other repository

  • Mcp builder

    simanam/theaiteam/team/skills/engineering/mcp-builder Skill

    no license1★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 42 other repositories

  • Ai seo

    simanam/theaiteam/team/skills/marketing/seo/ai-seo Skill

    no license1★ repo

    When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' or 'optimize for Claude/Gemini.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema-markup.

    The same file is in 1 other repository

  • Agent eval

    simanam/theaiteam/team/skills/meta/agent-eval Skill

    no license1★ repo

    Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

    The same file is in 5 other repositories

  • Agentic engineering

    simanam/theaiteam/team/skills/meta/agentic-engineering Skill

    no license1★ repo

    Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

    The same file is in 10 other repositories

  • Dispatching parallel agents

    simanam/theaiteam/team/skills/meta/dispatching-parallel-agents Skill

    no license1★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    The same file is in 13 other repositories

  • Skill creator

    simanam/theaiteam/team/skills/meta/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Subagent driven development

    simanam/theaiteam/team/skills/meta/subagent-driven-development Skill

    no license1★ repo

    Use when executing implementation plans with independent tasks in the current session

    The same file is in 3 other repositories

  • Agentic actions auditor

    simanam/theaiteam/team/skills/security/_trailofbits/agentic-actions-auditor/skills/agentic-actions-auditor Skill

    no license1★ repo

    Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

    The same file is in 3 other repositories

  • Prompt author

    lightrainstech/claude-design-prompt-pack/skills/prompt-author Skill

    no license1★ repo

    Write, refine, and optimize reusable prompts for bento grids, mockups, and workflows. Triggers: "write the master prompt", "draft the homepage prompt", "make a revision prompt", "create a prompt", "write a prompt for".

  • Expert ai engineer

    mehtab78/skills/skills/expert-ai-engineer Skill

    1★ repo

    AI/ML engineering specialist — LLM integrations, prompt design, RAG pipelines, embeddings, evals, fine-tuning decisions, agent architectures. Use for any task involving model APIs, prompts, vector stores, or ML tradeoffs. Normally invoked by model-router.

  • Llm app code

    pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/llm-app-code Skill

    no license1★ repo

    Code calling LLM APIs — model output is untrusted input: defensive parsing, server-side schema validation, authorization never from model output, approval-gated writes, injection awareness, cache-prefix economics, streaming edges. Use for agent loops, tool definitions, or prompt/model changes.

  • Subagent fanout

    pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/subagent-fanout Skill

    no license1★ repo

    Delegate broad searches and independent subtasks to subagents to keep the main context clean. Use when a question requires sweeping many files or directories, when several independent investigations could run in parallel, or when raw tool output would flood the context you need for the real work.

  • Mcp server security scan

    Dolphinllc/claude-security-skills/skills/defensive/genai/mcp-server-security-scan Skill

    1★ repo

    Defensive security scan for Model Context Protocol (MCP) servers built with the official @modelcontextprotocol/sdk or mcp Python SDK. Detects tools exposing filesystem/shell with user-controlled paths, HTTP/SSE transports without authentication, unvalidated tool arguments, sensitive data leaking via resource URIs, and unbounded tool output that floods context. Invoke when the user asks to "review", "audit", or "scan" an MCP server implementation.

  • Anthropic sdk attack probe

    Dolphinllc/claude-security-skills/skills/offensive/genai/anthropic-sdk-attack-probe Skill

    1★ repo

    Authorized red-team probe for applications built on the Anthropic SDK. Tests Claude-specific quirks - XML/tag confusion attacks, tool_use schema bypass, prompt-cache cross-tenant probing, and assistant-prefill manipulation - against your own chat or agent endpoint discovered via env/entrypoint. Use when the user asks to "red-team" or "attack-test" their Claude-based app.

  • Mcp server attack probe

    Dolphinllc/claude-security-skills/skills/offensive/genai/mcp-server-attack-probe Skill

    1★ repo

    Authorized red-team probe for Model Context Protocol (MCP) servers. Tests tool path traversal, command injection in shell-like tools, SSRF via fetch tools, HTTP/SSE transport authentication, DNS rebinding via Origin header, and resource URI traversal. Use when the user asks to "red-team" or "attack-test" their own MCP server.

  • Prompt injection probe

    Dolphinllc/claude-security-skills/skills/offensive/genai/prompt-injection-probe Skill

    1★ repo

    Authorized red-team probe for prompt-injection vulnerabilities in your own LLM application. Submits a battery of direct and indirect injection payloads against a chat/agent endpoint discovered via env/entrypoint, and scores how often the system prompt, tool boundary, or output policy is broken. Use when the user asks to "test prompt injection on" or "red-team" their own LLM app. Pair with framework-specific probes (anthropic-sdk-attack-probe, openai-sdk-attack-probe, vercel-ai-sdk-attack-probe, langchain-attack-probe, mcp-server-attack-probe) for deeper, SDK-aware variants.

  • Verify pipeline

    pol-cc/agentic-data-engineer/skills/verify-pipeline Skill

    1★ repo

    Run a full health check across the MDS pipeline: ingestion (dlt/Airbyte) load status, BigQuery freshness per source, ingest reconciliation (source-vs-destination row counts), dbt model freshness, MCP server health, and raw-vs-staging row count integrity. Invoke when the user wants to confirm the pipeline is healthy or asks 'is everything working?'

  • Competitive benchmark

    kaustavr19/claude-skills/skills/competitive-benchmark Skill

    1★ repo

    Benchmark a brand's website against named competitors and synthesise a strategic direction. Detects business model (B2B / B2C / D2C / marketplace) and scores every site across seven axes — visual design, UX writing, brand voice & positioning, conversion hooks, IA & journey, social proof & trust, and differentiation — producing a comparison matrix plus a synthesis of what to STEAL, DIFFERENTIATE, and AVOID. Orchestrates the visual-aesthetics-audit, ux-writing, and ux-audit skills for depth; hands off to product-requirements or market-intelligence to build. Use whenever the user shares their site AND one or more competitor sites and wants a comparison, benchmark, or teardown. Triggers: "benchmark my site against these", "how do I compare to competitors", "what are they doing better", "what should I steal / avoid / do differently". Distinct from market-intelligence (business/pricing strategy) — this is about the website and digital experience layer.

  • Rag system designer

    omarfarahatoglu-tur/ai-agent-skills/skills/ai-team/rag-system-designer Skill

    1★ repo

    Open-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.

  • Hand off

    Fyzel/claude-skills/skills/hand-off Skill

    1★ repo

    Delegates a defined scope of work to a fresh Claude Code subagent, with full current-context preserved across the boundary. Use this skill whenever the user invokes `/hand-off` or asks (in any phrasing) to hand off, delegate, spin off, fork, or pass work to another agent or a fresh agent. Also use when the user mentions running out of context and wanting to continue elsewhere, or wants to scope a chunk of work to its own session. Captures current context into a handoff directory, spawns a subagent via the Task tool to complete the work, then synthesizes the resulting output back into the parent conversation. Handoff directories persist on disk as an audit trail.

  • Git guardrails claude code

    steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/git-guardrails-claude-code Skill

    no license1★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Write a skill

    steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/write-a-skill Skill

    no license1★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories