agentskillexchange
- 2.9k skills
- 0 followers
- 28 repo stars
- 2 weeks ago last updated
- ▌ Lightning CSS High Performance CSS Parser Transformer And Mi · agentskillexchangeLightning CSS is a Rust-based CSS parser, transformer, bundler, and minifier from the Parcel team. This skill is for agents that need to optimize stylesheets, lower modern CSS syntax for target browsers, and integrate fast CSS processing into build or refactor workflows.
- ▌ Manage Parallel Coding Agent Sessions And Worktrees With Ccm · agentskillexchangeRun Claude Code, Codex CLI, Gemini CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, Kimi CLI, and related coding assistants from one worktree-aware terminal manager.
- ▌ Playwright Python Browser Automation Library For Cross Brows · agentskillexchangePlaywright for Python is Microsoft's cross-browser automation library for Chromium, Firefox, and WebKit. It gives agents and test systems one API for navigation, screenshots, form interaction, assertions, and headless execution across local and CI environments.
- ▌ Put Coding Agents On A Governed Local Git Workflow With Agen · agentskillexchangeRun coding agents inside a repo with explicit policy files, task state, approvals, and closure records when teams need auditable local workflows instead of opaque agent runs.
- ▌ Run Computer Use Agents Inside Cross Os Desktop Sandboxes Wi · agentskillexchangeLaunch computer-use agents in Linux, macOS, Windows, or Android sandboxes and drive full desktop tasks through screenshots, mouse, keyboard, and shell controls.
- ▌ Run Long Horizon Computer Use Agent Loops With Longhorizon H · agentskillexchangeUse LongHorizon-Harness to keep Claude Code, Codex, DeepSeek Harness, or custom agent backends working through long GUI and CLI tasks with verified state, role separation, checkpoints, and recovery loops.
- ▌ Run Long Horizon Research And Coding Agent Workflows With De · agentskillexchangeUse DeerFlow to orchestrate subagents, memory, sandboxes, tools, and skills for supervised research, coding, and creation tasks that take minutes to hours.
- ▌ Run Personal Operator Workflows From Agent Skills With Maker · agentskillexchangeInstall a multi-skill operator pack for decisions, research, second-brain work, content rotation, financial cadence, project management, and skill authoring.
- ▌ Run Terminal Native Coding Agent Workflows With Github Copil · agentskillexchangeUse GitHub Copilot CLI to plan, edit, debug, explain, and automate repository work from a terminal with GitHub context and approval controls.
- ▌ Sync Calendars Between Providers With A Stateless Calendarsy · agentskillexchangeRun a one-shot calendar sync or migration between Google, Outlook, CalDAV, ICS, and related systems without standing up a long-lived sync service.
- ▌ Track Coding Agent Token Spend And Leaderboard Drift Across · agentskillexchangeAggregate local coding-agent usage logs into spend, token, and trend views before quotas or budgets surprise the team.
- ▌ Translate Technical Pdfs Through Retainpdf While Preserving · agentskillexchangeRoute scanned, scientific, and technical PDFs through RetainPDF so an agent can produce translated PDFs while preserving formulas, tables, code blocks, and page layout.
- ▌ Turn Goals Into Traced Multi Agent Task Dags With Open Multi · agentskillexchangeDecompose goals into task DAGs, delegate work to agents and tools, and inspect execution traces.
- ▌ Turn Single Research Papers Into Obsidian Notes With Deeppap · agentskillexchangeRun a source-grounded agent workflow that reads one paper deeply and saves a durable Obsidian-style research note.
- ▌ Build Planner Driven Agent Workflows With Microsoft Semantic · agentskillexchangeCompose prompts, plugins, memory, planners, and connectors into repeatable Python, .NET, or Java agent workflows with Microsoft Semantic Kernel.
- ▌ Capture Low Level Kubernetes Runtime Evidence With Inspektor · agentskillexchangeRun named Inspektor Gadget traces and snapshots when an agent needs eBPF-backed runtime evidence from pods, containers, or nodes that ordinary logs and metrics do not expose.
- ▌ Enforce Red Green Refactor Discipline In Claude Code Session · agentskillexchangeBlock implementation-first agent behavior and keep Claude Code anchored to failing-tests-first TDD loops.
- ▌ Find Deprecated Kubernetes Apis Before Cluster Upgrades With · agentskillexchangeScan manifests and live clusters for removed or deprecated Kubernetes APIs before an upgrade window turns into an outage.
- ▌ Generate Local Subtitles For Video Editing Workflows With Au · agentskillexchangeUse Auto Subs when an operator or media agent needs local-first subtitle generation, editing, and handoff into DaVinci Resolve, Premiere Pro, After Effects, or a command-line video pipeline.
- ▌ Inspect Failing Github Actions Checks And Plan Fixes With Gh · agentskillexchangeInspect failing GitHub Actions checks on the current PR, pull the actionable log snippet, and stop at an approval gate before implementing a fix.
- ▌ Inspect Pdfs With Evidence First MCP Workflows Using PDF Rea · agentskillexchangeConnect PDF Reader MCP when an agent needs source-backed PDF extraction with page evidence, visual crops, OCR provenance, tables, trust reports, and reviewable citations.
- ▌ Install Anthropic Cybersecurity Skills For Agent Security Wo · agentskillexchangeAdd a large source-backed cybersecurity skills library to Claude Code, Codex CLI, Cursor, Gemini CLI, and other agents so security investigations follow structured analyst playbooks.
- ▌ Install Selected Ecc Agent Skills And Rules Across Coding Ha · agentskillexchangeUse Everything Claude Code to install curated skills, rules, hooks, and MCP configuration into Claude Code, Codex, Cursor, OpenCode, and related coding-agent harnesses without copying the whole repo blindly.
- ▌ Install Verified Codex Planning And Completion Loops With La · agentskillexchangeAdd Codex commands, skills, hooks, diagnostics, and sub-agent roles for deep repository initialization, planning, execution, and evidence-backed completion.
- ▌ Investigate Kubernetes Network Incidents Through MCP With Ku · agentskillexchangeQuery live and historical Kubernetes network traffic through Kubeshark's MCP server when an agent needs packet-level evidence, API payloads, or service-path traces for incident response.
- ▌ Keep Claude Code Skills Current From Real Sessions With Auto · agentskillexchangeInstall Autoharness so Claude Code can distill, merge, update, and retire native skills from real operator sessions without a daemon or benchmark loop.
- ▌ Keep Coding Agents From Over Building Implementations With P · agentskillexchangePonytail gives coding agents a portable minimal-implementation ruleset, plugin hooks, and review commands so they reuse existing code, native platform features, and standard library behavior before writing new abstractions.
- ▌ Prepare Meetings And Follow Ups From Local Work Memory With · agentskillexchangeUse Rowboat to build local work memory from email, calendar, notes, and web context, then generate meeting briefs, follow-ups, docs, and decks.
- ▌ Preserve Agent Plans Across Context Resets With Planning Wit · agentskillexchangeGives coding agents a repeatable file-backed planning workflow using task_plan.md, findings.md, and progress.md so long-running work survives /clear, compaction, crashes, and handoffs.
- ▌ Probe Kubernetes Clusters For Exposed Attack Paths With Kube · agentskillexchangeAssess a Kubernetes cluster from the attacker viewpoint when an agent needs exposure-focused findings instead of a general cluster scanner listing.
- ▌ Query Postgres Databases Through Read Only MCP Workflows Wit · agentskillexchangeConnect an MCP-compatible assistant to an existing PostgreSQL database for safe natural-language querying, schema-aware SQL, and streamed results.
- ▌ Repair AI Shaped Drafts With Sepia S Venue Specific Writing · agentskillexchangeUse Sepia to write, review, minimally refactor, or fully recreate fiction and professional prose with agent-native de-AI writing protocols.
- ▌ Retrieve Exact Documentation Sections For Agents With Jdocmu · agentskillexchangeUse jDocMunch MCP when an agent needs to index local or repository documentation, search by heading-level structure, and retrieve only the exact section needed instead of flooding context with full files.
- ▌ Search Large Pdfs And Read Only The Relevant Pages Before An · agentskillexchangeUse pdf-mcp to inspect a PDF, search it, and load only the pages that matter so an agent can answer questions from long documents without brute-forcing the whole file into context.
- ▌ Tail Multi Pod Kubernetes Logs By Label During Incidents Wit · agentskillexchangeAggregate and follow logs from matching Kubernetes pods during incident triage without hopping pod by pod.
- ▌ Turn Lark Meeting Transcripts Into Action Items And Follow U · agentskillexchangeRead a Lark Minutes transcript, extract explicit and implied follow-ups, then let the agent execute selected tasks instead of leaving them as notes.
- ▌ Turn Postgresql Logs Into Incident And Tuning Reports With P · agentskillexchangeUse pgBadger when an agent needs to convert raw PostgreSQL logs into readable evidence about slow queries, errors, and workload hotspots after an incident.
- ▌ Use Obsidian Agent Client As An Obsidian Front End For Local · agentskillexchangeRun ACP-compatible agents such as Claude Code, Codex, Gemini CLI, OpenCode, and custom agents from inside Obsidian notes and vault context.
- ▌ Build And Trace Multi Agent Workflows With Microsoft Agent F · agentskillexchangeCompose, orchestrate, and trace production multi-agent workflows with Microsoft Agent Framework.
- ▌ Build And Validate Shopify Apps With The Official Shopify AI · agentskillexchangeConnect agents and IDE assistants to Shopify docs, API schemas, code validation, and store-management workflows through Shopify's official toolkit.
- ▌ Build N8n Workflows From Node Docs Templates And Schemas Thr · agentskillexchangeUse n8n-MCP when an agent needs structured access to n8n nodes, properties, operations, and template examples while designing or debugging workflows, instead of guessing from raw docs or clicking through the n8n UI by hand.
- ▌ Connect Claude Code To Apple Apps And Tmux With Claude Apple · agentskillexchangeGive Claude Code local command access to Reminders, Calendar, Contacts, Notes, Mail, and tmux for workflow-aware personal ops on macOS.
- ▌ Coordinate Parallel Coding Agent Worktrees And Terminals Wit · agentskillexchangeUse Ouijit to manage parallel CLI coding-agent tasks with per-task git worktrees, integrated terminals, lifecycle hooks, and sandboxed sessions.
- ▌ Evolve Agent Behavior Into Auditable Genes And Capsules With · agentskillexchangeTurn recurring agent lessons, logs, and strategy tweaks into reviewable GEP evolution artifacts that can be applied across supported coding-agent runtimes.
- ▌ Generate Release Prs And Changelog Updates From Conventional · agentskillexchangeUse release-please when an agent should turn merged Conventional Commits into structured release PRs, version bumps, and changelog updates before a human reviews and merges. This is a release-management workflow, not a generic package or CI listing.
- ▌ Infer And Normalize Broken CSV Dialects Before Import With C · agentskillexchangeDetect messy CSV dialects, standardize malformed files, and generate reliable import code before ingestion pipelines or analyst workflows fail.
- ▌ Inspect Binary Hardening Flags And Exploit Mitigations With · agentskillexchangeCheck ELF or PE binaries for hardening gaps like NX, PIE, RELRO, stack canaries, and Fortify before release or incident review.
- ▌ Let Agents Control A Logged In Chrome Browser Through Playwr · agentskillexchangeUse Playwriter to give MCP-compatible agents a bounded, stateful Playwright control surface over an operator-approved Chrome session.
- ▌ Operate Deployments Telemetry And Sandboxes Through Temps Cl · agentskillexchangeUse Temps when an agent needs to deploy applications, inspect production telemetry, and manage self-hosted sandboxes through a pinned CLI and bundled skills.
- ▌ Orchestrate Goal Driven Typescript Agent Teams With Open Mul · agentskillexchangeTurn a user goal into a planned multi-agent task DAG, execute independent tasks in parallel, and trace the run from a TypeScript backend.
- ▌ Review AI Generated Code Changes In A Local Pr Style Loop Wi · agentskillexchangeUse DiffX to review local git changes in a PR-style browser UI, leave inline comments, and hand structured feedback back to a coding agent for repair.
- ▌ Review Dockerfiles For Risky Patterns And Bad Defaults With · agentskillexchangeCatch insecure Dockerfile patterns, brittle package-install habits, and shell pitfalls before image builds ship.
- ▌ Review Open Pull Requests Against Repository Contribution Gu · agentskillexchangeThis entry turns GitHub Next's Contribution Check workflow into a maintainer-facing agent routine. The agent batches open pull requests, compares them to CONTRIBUTING.md, labels likely-ready submissions, comments on gaps, and produces a report issue so humans can spend review time where it matters.
- ▌ Run Supervised Browser Automation Workflows With Aihawk · agentskillexchangeUse AIHawk's local supervised browser UI for bounded web research and extraction, with human review before external actions.
- ▌ Trace Evaluate Simulate And Guardrail Agent Releases With Fu · agentskillexchangeUse Future AGI to instrument agent runs, run evals and simulations, apply guardrails, and turn production traces into release-quality feedback.
- ▌ Analyze Videos With Frame Extraction And Audio Context In Cl · agentskillexchangeGive Claude Code a video perception layer that extracts frames, transcribes audio, and lets Claude answer questions about local videos or YouTube URLs.
- ▌ Audit Github Actions For Privilege And Supply Chain Risks Wi · agentskillexchangeRun a focused security pass on GitHub Actions workflows before merge so token misuse, dangerous permissions, and unpinned actions are caught early.
- ▌ Break Large Coding Jobs Into Focused Subagent Missions With · agentskillexchangeUse AB Method when a Claude Code task is too large for one pass and needs to be broken into focused tasks and missions that are completed incrementally instead of trying to solve the whole project in one conversation.
- ▌ Clone And Refresh Whole Github Orgs For Audit Or Migration W · agentskillexchangeUse ghorg to clone or resync large sets of repositories from a GitHub user or organization for offline audit, migration prep, or bulk analysis work.
- ▌ Extract Android App Apis With A Claude Code Reverse Engineer · agentskillexchangeUse this Claude Code skill to decompile APK, XAPK, JAR, and AAR files, recover Kotlin names, and extract Android HTTP API behavior for authorized analysis.
- ▌ Find Duplicate And Visually Similar Media Before Cleanup Wit · agentskillexchangeScan local archives for duplicate files, similar images, similar videos, empties, and related cleanup targets before deleting or reorganizing them.
- ▌ Inline CSS Into HTML Emails Before Delivery Across Mail Clie · agentskillexchangeUse Juice when an agent already has finished HTML and needs it transformed into email-safe output before sending, archiving, or handing off to another system. The skill inlines stylesheet rules into element style attributes so downstream mail clients and embedded contexts keep the intended presentation without manual cleanup.
- ▌ Install Focused Claude Code Workflow Plugins From Claude Nig · agentskillexchangeReview and install only the Claude Night Market plugins needed for a specific Claude Code workflow, such as PR prep, code review, TDD gates, or spec-driven development.
- ▌ Investigate Telemetry Incidents With Monoscope MCP And Agent · agentskillexchangeConnect agents to Monoscope so they can query logs, traces, metrics, monitors, and issues through stable JSON CLI output or MCP tools for incident triage.
- ▌ Optimize Prompt And Agent Pipelines With Dspy Programs And E · agentskillexchangeUse DSPy to define modular LLM programs, metrics, and evaluation sets so an agent can optimize prompts and pipeline behavior with measurable feedback instead of ad hoc prompt editing.
- ▌ Regenerate Helm Chart Readmes From Values And Comments Befor · agentskillexchangeUses helm-docs to rebuild Helm chart documentation from Chart.yaml, values.yaml, and inline comments so README files stay aligned with the actual chart. The agent can run this before commit or release, then surface changed tables, missing descriptions, and documentation drift in a review-friendly diff.
- ▌ Review Risky Coding Agent Sessions With Local Action Logs Us · agentskillexchangeCapture and inspect file reads, writes, and shell activity from coding agents so developers can audit what actually happened after a session goes sideways.
- ▌ Run Agent Generated Code In Local Microvm Sandboxes With Mic · agentskillexchangeUse Microsandbox to create local microVM-backed sandboxes for isolated execution of untrusted agent-generated code and tool calls.
- ▌ Run An Agent Across Browser And Local File Workflows With Ma · agentskillexchangeUse Microsoft's Magentic-UI to run supervised browser and local file tasks with an agentic UI, model endpoint, and approval-aware configuration.
- ▌ Run Authorized Security Research Pipelines In Claude Code Wi · agentskillexchangeRAPTOR turns Claude Code into an evidence-first offensive and defensive security research workflow for mapping attack surfaces, validating scanner findings, analyzing binaries, generating patches, and tracking project findings.
- ▌ Validate Python Docstrings Against Function Signatures With · agentskillexchangeCheck that Python docstrings stay consistent with parameters, returns, and raised exceptions as code evolves.
- ▌ Verify Local Web Apps With Playwright Scripts And Managed De · agentskillexchangeUse Anthropic's webapp-testing skill to spin up one or more local servers, wait for them to become reachable, and run native Playwright checks against the rendered app. It is for agent-led verification and UI debugging of local web apps, not for listing Playwright as a generic browser framework.
- ▌ Add Multimodal Lifelong Memory To MCP And Python Agents With · agentskillexchangeUse SimpleMem to store, compress, index, and retrieve text or multimodal memories for agents through MCP or Python integrations.
- ▌ Archive Online Videos And Metadata To The Internet Archive W · agentskillexchangeDownload a supported video URL with yt-dlp and upload the preserved file plus metadata to archive.org as a repeatable preservation job.
- ▌ Assemble Minimal Oci Images From Declarative Package Configs · agentskillexchangeUse apko to build small OCI images from declarative package manifests when supply-chain clarity and minimal contents matter more than a conventional Dockerfile flow.
- ▌ Block Unsafe Agent Actions And Scan Newly Added Skills With · agentskillexchangeAdd a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.
- ▌ Configure Supervised Multi Provider Agent Workspaces With Cr · agentskillexchangeSet up Craft Agents workspaces with connected sources, imported skills, MCP servers, permission modes, and session workflow states for supervised agent work.
- ▌ Convert Pdfs And Document Images Into Agent Ready Markdown W · agentskillexchangeRun Docext locally or with a chosen model backend to turn PDFs and document images into structured Markdown for RAG, extraction, and review workflows.
- ▌ Coordinate Parallel Coding Agents And Review Their Worktrees · agentskillexchangeRun Codex, Claude Code, OpenCode, Pi, and similar coding agents side by side in isolated worktrees, then compare, annotate, and merge the best result.
- ▌ Export Live HTML Slide Decks To PDF Handouts Before Review O · agentskillexchangeUses DeckTape to open an existing HTML slide deck and render it into a reviewable PDF or per-slide screenshots. It fits agent workflows that need a stable handout, attachment, or archive artifact from Reveal.js, Remark, WebSlides, and similar browser-based presentations.
- ▌ Give Coding Agents Ast Backed Semantic Code Search With Coco · agentskillexchangeInstall CocoIndex Code as a skill, plugin, CLI, or MCP server so coding agents can initialize, update, and query local AST-backed semantic code indexes.
- ▌ Investigate Crowdstrike Falcon Alerts And Telemetry Through · agentskillexchangeUse falcon-mcp when an agent needs CrowdStrike Falcon detections, incidents, behaviors, threat intel, or read-only response context to triage a security event without leaving an MCP workflow.
- ▌ Load Test Grpc Services From Proto Files And Reusable Reques · agentskillexchangeThis ASE skill uses ghz to run repeatable gRPC load tests from proto files, protosets, or server reflection. An agent can replay request fixtures at controlled concurrency, capture latency and error rates, and export machine-readable reports for regression checks or performance investigations.
- ▌ Parse Documents Into Structured Content For Agent Ingestion · agentskillexchangeExtract document text, tables, logical structure, and metadata into normalized output before RAG, review, or workflow automation.
- ▌ Prevent Broken Github Actions Workflows Before CI Runs With · agentskillexchangeUse actionlint when an agent needs to inspect GitHub Actions workflow files before a push or pull request lands. The skill checks syntax, expressions, action inputs, runner labels, cron patterns, and a few security footguns so the agent can stop bad workflow changes before CI burns time.
- ▌ Profile And Triage Messy Tabular Files From The Terminal Wit · agentskillexchangeInspect CSV, TSV, JSON, and parquet drops interactively, spot suspicious columns fast, and decide the next cleanup step without opening a spreadsheet.
- ▌ Provision OAUTH Capable Microsoft Agent Identities With Entr · agentskillexchangeCreate Microsoft Entra Agent Identity blueprints, principals, and agent identities with the right beta Graph permissions, sponsor rules, and sidecar-based auth patterns.
- ▌ Record Terminal Demos And Reproducible CLI Walkthroughs With · agentskillexchangeCapture a terminal session as a replayable cast when an agent needs a text-native CLI repro or walkthrough instead of a generic screen recording.
- ▌ Regression Test Prompts Agents And RAG Outputs Before Shippi · agentskillexchangeUse promptfoo when an agent needs to evaluate prompt, agent, or RAG behavior against saved assertions before a change goes live. The value here is the repeatable evaluation workflow, not a generic AI tooling catalog entry.
- ▌ Repair Malformed JSON Before Parsing Downstream Automations · agentskillexchangeUse jsonrepair when an agent receives JSON-like output that is almost valid but still breaks parsers, such as trailing commas, missing quotes, or concatenated fragments. The agent’s role is to normalize the payload before validation or routing, not to replace real schema design.
- ▌ Run Personal Corp Os Weekly Operating Loops With Claude Code · agentskillexchangeInstall a maintained skill pack for weekly planning, retrospectives, task routing, department setup, and founder-ops workflows across Claude Code and Codex.
- ▌ Run Visual Co Creation Workspaces For Coding Agents With Pne · agentskillexchangeUse Pneuma Skills when Claude Code, Codex, or Kimi should build slides, documents, diagrams, videos, dashboards, or custom modes in real files while a human reviews and edits through a live visual workspace.
- ▌ Sweep Github For Leaked Secrets And Exposed Credentials With · agentskillexchangeSearch public GitHub broadly for leaked secrets and triage exposures when the workflow is recon and remediation, not generic secret scanning.
- ▌ Triage Production Log Spikes And Incidents From The Terminal · agentskillexchangeOpen raw logs, jump to error clusters, query structured fields, and summarize incident clues without shipping data to a separate platform.
- ▌ Turn A Research Idea Into A Draft Paper Workflow With Autore · agentskillexchangeUse AutoResearchClaw when an agent should turn a raw research topic into literature review, experiment planning, draft writing, and verification artifacts instead of improvising an end-to-end paper workflow by hand.
- ▌ Turn Novels Into AI Short Drama Production Packets With Shuo · agentskillexchangeUse shuohao-skills to have coding agents turn a source novel into character bibles, adaptation outlines, art bibles, screenplays, and storyboards with deterministic quality gates.
- ▌ Apply Repeatable Imap Rules To Triage And Clean Inboxes With · agentskillexchangeRoute, label, and clean routine email traffic with scripted IMAP rules instead of doing the same inbox chores by hand.
- ▌ Autofix Common Nix Anti Patterns Before Style Drift Spreads · agentskillexchangeLint Nix expressions and automatically rewrite common anti-patterns before review or refactor work.
- ▌ Back Up Github Gitlab Bitbucket And Forgejo Repositories Wit · agentskillexchangeRun repeatable cross-forge repository backup jobs from one config instead of hand-scripting clone and export steps per provider.
- ▌ Build And Debug Interactive Wordpress Frontends With Data Wp · agentskillexchangeThis skill helps an agent create or troubleshoot WordPress Interactivity API behavior, from store wiring to server-rendered state and hydration checks. Use it when a block, theme, or plugin needs directive-driven interactivity rather than ad hoc frontend glue.