agentskillexchange
- 2.9k skills
- 0 followers
- 28 repo stars
- 2 weeks ago last updated
- ▌ Control Hosted Browser Research And Extraction Through Hyper · agentskillexchangeGive MCP clients hosted browser tools for scraping, crawling, structured extraction, search, and computer-use browser automation.
- ▌ Convert Browser Har Captures Into Reusable K6 Load Tests Wit · agentskillexchangeUse har-to-k6 when an agent has recorded browser traffic and needs to turn it into a repeatable k6 script instead of hand-writing one from scratch. The skill is about transforming captured sessions into a starter load-test artifact with validation and export, not about listing k6 or Grafana as products.
- ▌ Convert DOCX Documents Into Clean HTML For Publishing Workfl · agentskillexchangeUse Mammoth when an agent needs to turn a .docx file into simple HTML that preserves semantic structure instead of Word-specific styling. This is for ingestion and publishing workflows, not for full document editing or perfect visual fidelity.
- ▌ Debug Dns Resolution And Record Mismatches From The Terminal · agentskillexchangeRun fast DNS lookups, compare record types, and inspect resolver behavior when domains, MX records, or service endpoints look wrong.
- ▌ Deploy A Self Hosted Phone Call Agent For Asterisk And Freep · agentskillexchangeBring up a self-hosted voice agent that answers, routes, or transfers live calls through Asterisk or FreePBX with a PBX-native workflow.
- ▌ Deploy Document To JSON Extraction Apis And Etl Pipelines Wi · agentskillexchangeUse Unstract when an operator needs agents or automation pipelines to turn recurring PDFs, scans, and document batches into structured JSON through prompt-defined extraction workflows.
- ▌ Encrypt And Decrypt Age Secrets With Hardware Backed Yubikey · agentskillexchangeUse age-plugin-yubikey when an agent needs age encryption tied to a physical YubiKey identity instead of software-only keys.
- ▌ Format Shell Scripts Into A Stable House Style Before Review · agentskillexchangeNormalize Bash, POSIX shell, and Zsh scripts before review or CI so style noise stops hiding the real changes.
- ▌ Generate Dependency Update Pull Requests From Code With Depe · agentskillexchangeScan manifests, compute safe version bumps, and prepare dependency update PR material when you need self-hosted or custom Dependabot flows outside the default GitHub service.
- ▌ Generate Reusable Site Adapters From Live Browser Behavior W · agentskillexchangeUse OpenCLI to explore a logged-in site, synthesize a deterministic adapter, and expose the result as a reusable CLI command an agent can call again later.
- ▌ Govern Agent Skills MCP Servers Prompts And Tool Calls With · agentskillexchangeUse DefenseClaw as an operator-controlled admission, runtime guardrail, sandbox, and audit layer before untrusted agent capabilities run.
- ▌ Inspect And Debug MCP Servers Visually Before Connecting The · agentskillexchangeUse MCP Inspector when you need to launch an MCP server, inspect its tools and resources, exercise calls manually, and troubleshoot transport or schema issues before putting that server in front of real agents.
- ▌ Inspect Freshservice Service Management Tickets And Modules · agentskillexchangeConnect Freshservice modules to MCP clients for supervised IT service-management ticket lookup and support-ops preparation.
- ▌ Load Test An HTTP Endpoint With A Fast Reproducible CLI Prob · agentskillexchangeRun a quick concurrent HTTP benchmark against a URL before deeper performance work or regression triage.
- ▌ Read And Modify Figma Designs From Coding Agents With Talk T · agentskillexchangeBridge Cursor, Claude Code, and other MCP clients into Figma so agents can inspect selections, create nodes, annotate designs, and apply bulk edits.
- ▌ Run Evidence First Research Investigations In Claude Code Wi · agentskillexchangeInstall Deepdive as a Claude Code skill for structured investigations with plans, source files, claim tracing, dissent checks, and reusable research reports.
- ▌ Run Repeatable Marketing Operator Workflows With Aaron Marke · agentskillexchangeInstall a maintained marketing skill library so agents can run scoped SEO/GEO, email, paid ads, influencer, launch, social, and brand narrative workflows with shared quality gates.
- ▌ Run Wechat Public Account Content Operations With Wechat Art · agentskillexchangeUse WeChat Article Skills to run a confirmed, multi-step WeChat article workflow from topic planning through drafting, review, formatting, images, and publishing.
- ▌ Simplify Recently Changed Code And Open Low Risk Refactor Pu · agentskillexchangeThis entry turns GitHub Next's Code Simplifier workflow into a narrow cleanup agent. The agent inspects code changed in the last day, proposes behavior-preserving simplifications, runs validation, and opens small refactor pull requests instead of attempting broad rewrites.
- ▌ Strip Noisy Jupyter Output From Notebooks Before Commit With · agentskillexchangeKeep notebook diffs reviewable by removing execution output and excess metadata before notebooks land in Git history.
- ▌ Turn Long Video Or Audio Into Reviewed Clips And Subtitles W · agentskillexchangeUse FunClip when an agent needs a repeatable local workflow for transcribing media, proposing clip timestamps, and producing reviewable video segments with subtitle files.
- ▌ Turn Mixed Local Folders Into A Queryable Knowledge Graph Wi · agentskillexchangeIngest code, docs, PDFs, images, and video from local folders into a searchable knowledge graph so agents can follow entities and relationships instead of only raw text.
- ▌ Benchmark CLI Agents On Autonomous LLM Post Training With Po · agentskillexchangeRun Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.
- ▌ Control Kubernetes Infrastructure Through Natural Language M · agentskillexchangeLet MCP-compatible agents inspect, debug, deploy, audit, and manage Kubernetes clusters through a controlled kubectl-backed server.
- ▌ Generate Social Carousel And Cover Assets With Guizang Socia · agentskillexchangeUse Guizang Social Card Skill from Claude Code or Codex to turn source material into Rednote/Xiaohongshu carousel cards and WeChat cover image pairs.
- ▌ Give MCP Agents Disposable Code Execution Sandboxes With Ope · agentskillexchangeExpose sandbox creation, command execution, and file operations to MCP-capable agents so they can run untrusted code inside disposable Docker or Kubernetes-backed runtimes.
- ▌ Implement Review And Optimize Swiftui Code With Trace Backed · agentskillexchangeGuide SwiftUI implementation and refactoring with current Apple patterns, then analyze Instruments traces to diagnose hangs, hitches, and expensive view updates.
- ▌ Plan And Preview Warehouse SQL Model Changes Before Rollout · agentskillexchangeCompare SQL model changes, preview backfills and downstream impact, and stage safer warehouse rollouts before execution.
- ▌ Prepare Bid Proposal Drafts And Compliance Checks With Openb · agentskillexchangeUse OpenBidKit Yibiao to turn tender materials, company knowledge, and model-provider settings into reviewable bid proposal drafts with reuse and risk-check workspaces.
- ▌ Push Pull And Attach Non Container Oci Artifacts In Registri · agentskillexchangeUse ORAS to move SBOMs, model bundles, provenance, and other non-container artifacts through OCI registries without wrapping them as conventional images.
- ▌ Run Autonomous White Box Pentests Against Web Apps And Apis · agentskillexchangeAnalyze a web app's source code, execute real exploit attempts against the running target, and return proof-backed findings before release.
- ▌ Run Postgresql Backup Restore And Wal Recovery Workflows Wit · agentskillexchangeExecute PostgreSQL backup, restore, verification, and point-in-time recovery runbooks with explicit repository and WAL handling.
- ▌ Run Repeatable Google Ads And SEO Audits Inside Claude Code · agentskillexchangeUse Toprank when an agent needs a repeatable Claude Code workflow for Google Ads and SEO audits, with concrete slash commands, account-backed analysis, and optional repo edits instead of one-off marketing prompting.
- ▌ Score RAG Answer Quality And Retrieval Quality Before Rollou · agentskillexchangeMeasure whether a RAG change actually improved answers and retrieval, instead of guessing from a few spot checks.
- ▌ Sync Cloud And Saas Inventory Into SQL Tables For Audits Wit · agentskillexchangeExtract cloud and SaaS configuration data into queryable tables so agents can run audits, drift checks, and evidence collection with SQL.
- ▌ Apply Rule Based Guardrails To Agent Traces And Tool Flows W · agentskillexchangeInsert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules.
- ▌ Build Ocr And Layout Analysis Preprocessing Pipelines With D · agentskillexchangeUse deepdoctection when an agent workflow needs a local Python pipeline for document layout analysis, OCR, table recognition, and page-level extraction before LLM ingestion.
- ▌ Control Codex And Claude Coding Agent Sessions From Mobile W · agentskillexchangeRun a self-hosted bridge so an operator can start, resume, approve, and review Codex or Claude Code sessions from a phone or tablet.
- ▌ Cut And Finish Chinese Talking Head Videos With Chengfeng Vi · agentskillexchangeProvides Codex plugin skills for reviewed talking-head video editing: cut mistakes from source video and subtitles, finish a captioned deliverable, report bugs with confirmation, and check trusted plugin updates.
- ▌ Drive Dependency And Config Bumps Through Declarative Update · agentskillexchangeUse Updatecli when an agent needs to detect upstream releases, validate conditions, patch versioned files, and open reviewable update actions from one policy run instead of hand-editing manifests or relying on a single ecosystem bot.
- ▌ Monitor Local Coding Agent Sessions And Token Usage With Loo · agentskillexchangeCollect local telemetry from Claude Code, Codex, Cursor, OpenClaw, OpenCode, and related coding agents, then inspect token usage, tool calls, sessions, and traces from one local dashboard or OpenTelemetry pipeline.
- ▌ Prepare Evidence Backed Open Source Contribution Proposals W · agentskillexchangeUse ContribAI when an agent should analyze a repository, respect maintainer consent, and prepare bounded draft contribution proposals with evidence receipts.
- ▌ Prepare Indian Itr Filings With Deterministic Tax Checks Thr · agentskillexchangeUse itr-wala when an agent needs a review-first workflow for reading Indian tax documents, running deterministic AY 2026-27 tax calculations, comparing regimes, and guiding the user up to the pay, submit, and e-verify steps.
- ▌ Probe Ml And LLM Systems For Regressions And Vulnerabilities · agentskillexchangeRun automated red-team and failure scans against an LLM or RAG app before users find the breakage.
- ▌ Query And Inspect Postgres Databases Through MCP With Pgedge · agentskillexchangeConnect an MCP client to PostgreSQL databases for schema discovery, safe querying, and database inspection through a documented pgEdge MCP server and agent client workflow.
- ▌ Regenerate Repository Config From A Single Project Definitio · agentskillexchangeUse projen when an agent should synthesize and refresh repository boilerplate from one canonical project definition instead of hand-editing many config files.
- ▌ Run Claude Trading Skills For Investor Market Review And Tra · agentskillexchangeUse the Claude Trading Skills pack to run structured market-regime checks, portfolio reviews, swing-trade screens, trade journals, and performance retrospectives inside Claude workflows.
- ▌ Run Context Spec Implement Coding Loops In Claude Code With · agentskillexchangeTurn Claude Code into a structured project workflow that captures context, plans work, and executes implementation in reviewable tracks.
- ▌ Run Deepseek Harness Agent Sessions From A Claude Code Style · agentskillexchangeUse dsh-cc-tui to run DeepSeek Harness coding-agent sessions from a full-screen terminal with live activity, context meters, session rewind, presets, model switching, file mentions, and MCP access.
- ▌ Run Local Coding Agents From Feishu Or Lark With Lark Coding · agentskillexchangeUse Lark Coding Agent Bridge to connect Feishu or Lark chat threads to a local Claude Code or Codex CLI session with streaming cards, per-chat continuity, workspace switching, file handling, and controlled slash commands.
- ▌ Run Nature Style Academic Writing And Figure Workflows With · agentskillexchangeInstall reusable Codex or Claude Code skill bundles for Nature-style manuscript polishing, academic writing, citations, paper reading, response drafting, data handling, slides, and scientific figures.
- ▌ Run Ruff Mypy And Other Code Quality Tools On Jupyter Notebo · agentskillexchangeApply standard Python formatters, linters, and type checkers to notebook-heavy repositories without manually converting notebooks to scripts.
- ▌ Scan Project Dependencies For Supply Chain Vulnerabilities W · agentskillexchangeRun MurphySec CLI against a project before release or dependency approval to detect vulnerable direct and transitive dependencies.
- ▌ Add A Browser Review Checkpoint Before Risky Agent Actions W · agentskillexchangeUse AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.
- ▌ Broker API Credentials To AI Agents Without Exposing Raw Key · agentskillexchangeStore credentials once, then inject them into outbound agent requests at runtime so agents can call services without receiving raw secrets.
- ▌ Co Author Structured Docs With Staged Context Gathering And · agentskillexchangeUse 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.
- ▌ Connect Azure Devops Projects Work Items Repos And Pipelines · agentskillexchangeUse Azure DevOps MCP when an agent needs governed access to ADO projects, work items, builds, repos, test plans, wikis, and pipelines.
- ▌ Convert Mixed Documents Into Agent Ready Markdown And JSON W · agentskillexchangeConvert PDFs, scans, office files, images, and URLs into clean Markdown, structured JSON, CSV, or HTML before an agent ingests or reviews the content.
- ▌ Convert Smtp Only Alerts Into Routed Notification Deliveries · agentskillexchangeUse Mailrise to accept ordinary email alerts and fan them out through Apprise-backed notification channels when legacy systems can only speak SMTP.
- ▌ Evolve Reusable Coding Agent Skills From Failed Trajectories · agentskillexchangeMine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.
- ▌ Execute Devops Delivery And Infrastructure Workflows With Cc · agentskillexchangeUse generator and validator loops for infra, CI, and platform work so agents ship operational changes with more checks and less improvisation.
- ▌ Expose Fhir Healthcare Data Resources To MCP Agents With Rev · agentskillexchangeUse a FHIR MCP server to query healthcare data resources for documentation and integration workflows while keeping PHI and clinical-use limits explicit.
- ▌ Extract Schema Shaped JSON From Javascript Rendered Pages Wi · agentskillexchangeOpen a rendered page, describe the fields you want, and return structured data without hand-maintaining brittle selectors.
- ▌ Gate MCP Tool Calls Behind Deterministic Policy Enforcement · agentskillexchangeUse Intercept when an MCP-connected agent needs transport-layer policy enforcement for risky tools, argument limits, spend caps, hidden tools, or rate limits before calls reach the upstream server.
- ▌ Generate And Screen Lookalike Domains With Dnstwist For Bran · agentskillexchangeGenerate typosquat and homograph domain candidates, resolve them, and flag likely phishing or impersonation infrastructure before manual brand-abuse review.
- ▌ Generate Drift And Quality Reports For Ml And LLM Pipelines · agentskillexchangeProduce repeatable drift and quality reports after data, model, or prompt changes so regressions are visible before rollout.
- ▌ Generate Fast Static Photo Album Sites From Curated Folders · agentskillexchangeTurn exported photo folders into a mobile-friendly static album site without standing up a database-backed gallery system.
- ▌ Generate Reproducible Algorithmic Art Sketches With Seeded P · agentskillexchangeUse the Anthropic algorithmic-art skill when an agent should turn a creative brief into executable generative art, not into a static image prompt or a generic design suggestion. It directs the agent toward a repeatable p5.js workflow with seeded randomness, parameter controls, and an explicit creative philosophy.
- ▌ Ghost Open Source Publishing Platform For Memberships Newsle · agentskillexchangeGhost is an open-source publishing platform built for modern blogs, newsletters, memberships, and headless CMS use cases. It combines editorial workflows, subscription management, and API-first content delivery in one self-hostable stack.
- ▌ Parse Local Pdfs Into Agent Ready Text JSON And Screenshots · agentskillexchangeRun LiteParse locally to extract PDF text, spatial JSON, OCR-backed output, and page screenshots before sending documents into an agent workflow.
- ▌ Rebuild Public Websites From Evidence Snapshots With Website · agentskillexchangeUse website-rebuild-skill when an agent needs to classify a public site, capture a read-only evidence mirror, reconstruct behavior from shipped assets, and verify the rebuild with console, network, DOM, geometry, and pixel-diff gates.
- ▌ Record And Replay HTTP Fixtures For Deterministic Python Tes · agentskillexchangeUse VCR.py when an agent needs to turn flaky, slow, or rate-limited Python tests into stable runs by recording real HTTP interactions once and replaying them from cassette files. The agent decides which requests belong in fixtures, refreshes stale cassettes when upstream APIs change, and keeps external traffic out of the repeat test loop.
- ▌ Run Configurable Multi Source Deep Research Passes With Open · agentskillexchangeUse Open Deep Research when an agent should run a configurable research job that searches, compresses, synthesizes, and writes a cited report across multiple model and search backends.
- ▌ Search Cross Agent Markdown Memory And Conversation History · agentskillexchangeGive supported coding agents a shared Markdown-first memory layer so they can recall prior decisions, transcripts, and notes across sessions instead of re-deriving context from scratch.
- ▌ Search Local Notes Docs And Meeting Transcripts For Agent Co · agentskillexchangeIndex local notes, docs, and meeting transcripts, then return ranked files or structured JSON so an agent can pull only the context it needs.
- ▌ Turn Markdown Runbooks Into Executable Parameterized Procedu · agentskillexchangeRun named steps directly from Markdown runbooks so operational docs stay executable instead of drifting into stale reference text.
- ▌ Verify Markdown Links Before Docs Or Content Ship With Markd · agentskillexchangeCatch dead links in README files, docs folders, and content drafts before a broken reference ships to users.
- ▌ Apply Git Branching Commit And Pull Request Best Practices T · agentskillexchangeGive an agent a portable Git workflow playbook for branch strategy, commit hygiene, pull requests, merge choices, and CI-aware collaboration.
- ▌ Capture And Search AI Coding Sessions Alongside Git History · agentskillexchangeRecord AI coding sessions next to commits so an agent can recover why code changed, resume from checkpoints, and hand off work cleanly.
- ▌ Capture Polished Terminal Screenshots For Docs And Changelog · agentskillexchangeRender clean terminal screenshots with stable framing before publishing documentation, release notes, or runbooks.
- ▌ Decode Inspect Sign And Verify Jwts While Debugging Auth Flo · agentskillexchangeDecode JWTs, inspect claims, and verify or sign tokens with local keys during auth debugging and test setup.
- ▌ Build Graph Based Retrieval Workflows With Graphrag · agentskillexchangeIndex private text into graph-backed retrieval structures, tune prompts, and query the resulting knowledge graph for RAG workflows.
- ▌ Build Java Agent Transport Gateways With Atmosphere · agentskillexchangeUse Atmosphere to build JVM agent gateways that stream over WebSocket, SSE, gRPC, WebTransport, MCP, A2A, and AG-UI with governance hooks.
- ▌ Build Persistent Codebase Context Graphs With Graft · agentskillexchangeBuild and maintain a repository-local context graph so coding agents can orient inside large codebases without rediscovering the same structure every session.
- ▌ Build Portable Single File Agent Memory With Memvid · agentskillexchangeUse Memvid when an agent needs local, portable long-term memory and retrieval without running a vector database or full RAG service.
- ▌ Build React Agent Chat Interfaces With Assistant UI · agentskillexchangeUse assistant-ui to build production React chat interfaces with reusable threads, runtimes, message components, and model/provider adapters.
- ▌ Compact Terminal Heavy Agent Output With Tokenjuice · agentskillexchangeUse Tokenjuice when an agent runs noisy shell commands and needs deterministic, inspectable output reduction before continuing a coding or operations workflow.
- ▌ Decap Cms Git Based Content Management For Static Sites · agentskillexchangeAn agent skill built on Decap CMS (formerly Netlify CMS), the open-source Git-based content management system for static site generators. Provides a visual editing interface backed by Git commits, enabling content workflows for Hugo, Jekyll, Gatsby, Next.js, and other Jamstack frameworks.
- ▌ Design Loop Engineering Workflows For Coding Agents · agentskillexchangeUse Loop Engineering to scaffold, audit, and operate repeatable coding-agent loops with explicit state, budget, readiness, and tool-specific patterns.
- ▌ Dokploy Self Hosted Application Deployment Platform · agentskillexchangeDeploy and manage Dockerized apps on your own infrastructure with Dokploy, an open source platform positioned as an alternative to Heroku, Vercel, and Netlify. This skill is useful when agents need to stand up services, manage compose stacks, provision databases, and reason about Traefik-backed deployment workflows from real Dokploy docs and project conventions.
- ▌ Enforce Engineering Workflows With Ring Skill Packs · agentskillexchangeUse Ring to load curated engineering skills and specialist agents for TDD, systematic debugging, code review, product planning, and technical writing across supported agent hosts.
- ▌ Expose Fastapi Routes As MCP Tools With Fastapi MCP · agentskillexchangeMount FastAPI-MCP on an existing FastAPI app so agents can call authenticated route-backed MCP tools with preserved schemas.
- ▌ Formbricks Open Source Survey And Experience Management Plat · agentskillexchangeFormbricks is an open source survey platform and privacy-first experience management solution. Create in-app, website, link, and email surveys to gather user and customer insights at every point of their journey.
- ▌ Give Agents Fast Searchable Memory With Supermemory · agentskillexchangeUse Supermemory as an agent memory and context layer for ingesting user facts, documents, connectors, and searchable RAG context across assistant workflows.
- ▌ Give Coding Agents Figma Layout Context Through MCP · agentskillexchangeConfigure Framelink's Figma MCP server so coding agents can fetch clean design layout context from Figma files before implementing UI.
- ▌ Give MCP Agents Structured Graph Memory With Rushdb · agentskillexchangeConnect RushDB's MCP server so agents can store, search, update, and traverse persistent structured memory without hand-building a separate vector and graph stack.
- ▌ Gotify Self Hosted Push Notification Server And API · agentskillexchangeRun self-hosted push notifications with Gotify, including a REST API, WebSocket stream, web UI, plugins, and mobile clients. This skill helps agents send alerts, manage applications, and connect monitored events to a private notification channel instead of relying on third-party push vendors.
- ▌ Inngest Event Driven Durable Workflow Orchestration Platform · agentskillexchangeInngest is an open-source workflow orchestration platform that replaces queues, state management, and scheduling with durable step functions. It enables developers to write reliable event-driven workflows triggered by events, cron schedules, or webhooks, with built-in retries, concurrency control, and flow control.
- ▌ Linear MCP Server For Issue Tracking And Project Management · agentskillexchangeAn MCP server that integrates Linear project management with AI assistants. Enables creating, searching, updating, and commenting on Linear issues, managing projects and teams, and querying workflows through the Model Context Protocol.
- ▌ Mailtrap Node JS Sdk For Transactional And Sandbox Email · agentskillexchangeAn ASE skill built on the official Mailtrap Node.js SDK for sending transactional email and working with Mailtrap sandbox or production flows. It is well suited to agent workflows that need API-driven email delivery, test inbox validation, and structured messaging automation.