All authors
Claude Skills by agentskillexchange
github.com/agentskillexchange3,068 skills12 installs4,345 views
- Monitor Local Coding Agent Sessions And Token Usage With Loongsuite PilotCollect 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.Votes: 0GitHub stars: 36
- Multi Lens ReviewReview a PR or diff through three independent focused lenses (correctness, security, test coverage), then deduplicate and validate findings before persisting. Catches more real bugs than a single general review pass while producing less noise.Votes: 0GitHub stars: 36
- Operate A Local Multi Agent Workforce With EigentUse Eigent when an operator needs a local desktop agent workforce that can coordinate developer, browser, document, multimodal, model-provider, and MCP-backed work in one controlled environment.Votes: 0GitHub stars: 36
- Operate A Persistent Local Terminal Agent With GptmeRun gptme as a terminal-first autonomous agent that can edit files, execute commands, browse the web, and keep local project context.Votes: 0GitHub stars: 36
- Operate An Obsidian Vault As An Agent Maintained Second BrainLet agents ingest sources, update Obsidian notes, reconcile contradictions, search vault context, and maintain a living knowledge base through documented commands.Votes: 0GitHub stars: 36
- Operate Multi Provider Ai Gateway Traffic With BifrostRun Bifrost as an OpenAI-compatible gateway so agents can route model calls across providers with failover, load balancing, caching, and governance.Votes: 0GitHub stars: 36
- Operate Multiple Coding Agents From One Emacs Workflow With Ai Code InterfaceGive Emacs users one workflow layer for Codex, Claude Code, Gemini CLI, Cursor CLI, opencode, and other coding-agent backends.Votes: 0GitHub stars: 36
- Operate Rails Active Job Queues With Mission Control JobsUse Mission Control Jobs when an operator needs a Rails-mounted dashboard to inspect Active Job queues, review failed jobs, and retry or discard jobs with supervision.Votes: 0GitHub stars: 36
- Operate Support Chatbots And Voice Assistants With RasaUse Rasa to design, test, and operate custom conversational assistants for support, service, and voice workflows.Votes: 0GitHub stars: 36
- Optimize Agent Development Loops With Coze LoopUse Coze Loop to evaluate, debug, and improve agent prompts and workflows across development iterations.Votes: 0GitHub stars: 36
- Optimize Agent Skills With Darwin SkillUse Darwin Skill to evaluate, improve, test, and keep or roll back changes to a single agent SKILL.md with a validation-gated, human-reviewed optimization loop.Votes: 0GitHub stars: 36
- Orchestrate Coding Agent Goals And Context With Jumbo ContextUse Jumbo Context when coding agents need local goal state, project memory, session continuity, and context packets that travel across Claude, Codex, Copilot, and other harnesses.Votes: 0GitHub stars: 36
- Orchestrate Coding Agents Across Desktop Mobile And Headless Sessions With PaseoPaseo runs a local daemon for Claude Code, Codex, Copilot, OpenCode, and Pi agents so operators can start, monitor, attach to, and hand off coding-agent work from desktop, mobile, web, or CLI clients.Votes: 0GitHub stars: 36
- Orchestrate Local First Agent Memory And Workflows With OpenhumanSet up OpenHuman as a local-first personal agent harness that syncs context, builds durable memory, and coordinates multi-agent workflows behind approval gates.Votes: 0GitHub stars: 36
- Orchestrate Multi Agent Coding Delivery Loops With Maestro FlowUse Maestro Flow when a coding operator wants intent-driven planning, execution, verification, review, retry, and long-running multi-agent loops from one workflow surface.Votes: 0GitHub stars: 36
- Orchestrate Review First Multi Agent Development Work With KandevUse Kandev when an operator needs to plan, run, isolate, review, and ship multiple coding-agent tasks through a controlled kanban and pipeline workspace.Votes: 0GitHub stars: 36
- Orchestrate Windows Coding Agent Fleets With WmuxUse Wmux to fan out Claude Code, Codex, Gemini, and other agent CLIs across native Windows panes, isolated worktrees, approval gates, durable channels, and browser/MCP automation.Votes: 0GitHub stars: 36
- Organize Reusable Prompt Workflows With PomlUse Microsoft's POML to turn advanced prompts into structured, reusable prompt assets with markup, data components, templating, styling, SDK rendering, and VS Code testing.Votes: 0GitHub stars: 36
- Outagedeck Dependency Outage TriageChecks official cloud and SaaS status evidence through the OutageDeck MCP server or anonymous REST API before an agent changes code for 5xx, timeout, deployment, authentication, or integration failures.Votes: 0GitHub stars: 36
- Parse Agent Ready Pdfs And Document Images With MonkeyocrRun MonkeyOCR over PDFs, scanned pages, formulas, and tables to produce structured Markdown/text that downstream agents can ingest and reason over.Votes: 0GitHub stars: 36
- Parse Documents Into Structured Content For Agent Ingestion With DedocExtract document text, tables, logical structure, and metadata into normalized output before RAG, review, or workflow automation.Votes: 0GitHub stars: 36
- Parse Korean Office Documents For Agents With KordocUse kordoc when an agent needs to parse HWP, HWPX, PDF, Excel, or DOCX files into Markdown, fill forms, compare documents, or expose document tools through MCP.Votes: 0GitHub stars: 36
- Parse Multi Format Rag Inputs With OmniparseRun OmniParse locally or as an API service to turn documents, images, audio, video, and web pages into structured Markdown-ready inputs for agent and RAG workflows.Votes: 0GitHub stars: 36
- Parse Multilingual Documents For Agent Ingestion With Dots OcrUse dots.ocr when an agent needs repeatable multilingual document layout parsing before retrieval, extraction, review, or downstream automation.Votes: 0GitHub stars: 36
- Plan Draft Publish And Review Social Posts From Claude Code With Social PostInstall a Claude Code skill that learns a user's social voice, builds a 14-day content calendar, drafts posts, and publishes only after explicit confirmation.Votes: 0GitHub stars: 36
- Pre Landing ReviewStructured self-review checklist to run before committing substantial code changes. Covers edge cases, error paths, test coverage, documentation, and code quality — so CI is a last resort, not your first reviewer.Votes: 0GitHub stars: 36
- Prepare Agent Ready Pdf And Document Extraction With PymupdfUse PyMuPDF to extract text, layout metadata, tables, images, Markdown, or JSON from PDFs and documents before an agent ingests or reviews them.Votes: 0GitHub stars: 36
- Prepare Bid Proposal Drafts And Compliance Checks With Openbidkit YibiaoUse OpenBidKit Yibiao to turn tender materials, company knowledge, and model-provider settings into reviewable bid proposal drafts with reuse and risk-check workspaces.Votes: 0GitHub stars: 36
- Prepare Evidence Backed Open Source Contribution Proposals With ContribaiUse ContribAI when an agent should analyze a repository, respect maintainer consent, and prepare bounded draft contribution proposals with evidence receipts.Votes: 0GitHub stars: 36
- Prepare Indian Itr Filings With Deterministic Tax Checks Through Itr WalaUse 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.Votes: 0GitHub stars: 36
- Prepare Local Retrieval Embeddings With FastembedGenerate dense, sparse, image, and reranking embeddings locally before writing vectors into Qdrant or another retrieval stack for agent memory and RAG workflows.Votes: 0GitHub stars: 36
- Preserve Agent Plans Across Context Resets With Planning With FilesGives 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.Votes: 0GitHub stars: 36
- Produce Chinese Video Recaps With Video Recap SkillsUse video-recap-skills when an agent should turn source video into a Chinese narration recap with scene understanding, scripting, voiceover, subtitles, and an optional editable JianYing draft.Votes: 0GitHub stars: 36
- Produce Cinematic Product Videos With Video ShotcraftTurns Claude Code, Codex, or another skills-aware coding agent into a Remotion-based product video operator with shot cards, motion previews, templates, capture scripts, sound design, and visual QA.Votes: 0GitHub stars: 36
- Profile Python Agent Workloads With ScaleneUse Scalene when a Python agent, tool server, or retrieval pipeline needs line-level CPU, GPU, and memory profiling before targeted optimization.Votes: 0GitHub stars: 36
- Progressive DisclosureRestructure large documentation files (500+ lines, 5k+ tokens) into slim indexes with on-demand detail directories. Reduces always-included context by 40-60% while preserving full accessibility. Ideal for documentation auto-included in every agent context window.Votes: 0GitHub stars: 36
- Pronounce Developer JargonAnswers short pronunciation questions about developer tools, AI models, acronyms, and project names by using the say-it CLI to play local audio and return IPA, a plain-English respelling, source evidence, and contested alternatives.Votes: 0GitHub stars: 36
- Proofed Completion GateUses the Proofed CLI and current-subject completion receipts to reject unsupported coding-agent completion claims, rerun repository-configured tests, and detect stale PASS evidence after code changes.Votes: 0GitHub stars: 36
- Prove Agent Skills With SkillforgeUse SkillForge to triage, create, test, review, compile, and maintain Claude Code and Codex-ready skills with baseline failures and regression evals.Votes: 0GitHub stars: 36
- Query Clickhouse Analytics Safely From Mcp ClientsUse ClickHouse's official MCP server when an assistant needs schema-aware, reviewable analytics access to ClickHouse through bounded tools instead of ad hoc database credentials.Votes: 0GitHub stars: 36
- Query Operational Databases From Mcp Clients With DbhubUse DBHub to expose guarded, token-efficient database inspection and SQL tools to MCP clients across Postgres, MySQL, SQL Server, MariaDB, and SQLite.Votes: 0GitHub stars: 36
- Query Real Time Global Intelligence Through Worldmonitor McpGive MCP-capable agents a live global-intelligence surface for country briefs, risk scores, conflict, cyber, market, weather, and infrastructure monitoring.Votes: 0GitHub stars: 36
- Read And Modify Figma Designs From Coding Agents With Talk To Figma McpBridge Cursor, Claude Code, and other MCP clients into Figma so agents can inspect selections, create nodes, annotate designs, and apply bulk edits.Votes: 0GitHub stars: 36
- Rebuild Public Websites From Evidence Snapshots With Website Rebuild SkillUse 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.Votes: 0GitHub stars: 36
- Record And Replay Governed Gui Workflows With OpenadaptUse OpenAdapt to demonstrate a repeated browser or GUI workflow once, compile it into a deterministic replay bundle, and certify or halt runs with reviewable reports when interfaces drift.Votes: 0GitHub stars: 36
- Record System Level Agent Activity With AgentsightWrap Claude Code, Codex, Gemini CLI, OpenClaw, or another agent command with AgentSight to capture processes, files, network destinations, prompts, and reports.Votes: 0GitHub stars: 36
- Reduce Agent Terminal Noise With OmniUse OMNI to distill noisy terminal output before coding agents read it while preserving recoverable raw logs for exact follow-up inspection.Votes: 0GitHub stars: 36
- Reduce Coding Agent Output Cost With HoneyUse Honey to make coding agents emit less code, less prose, and denser agent-to-agent handoffs while preserving correctness boundaries.Votes: 0GitHub stars: 36
- Render Interactive Mcp Tool Uis With Mcp UiBuild an MCP Apps resource, attach it to a tool through _meta.ui.resourceUri, and verify the host renders the interactive UI alongside tool results.Votes: 0GitHub stars: 36
- Repair Ai Shaped Drafts With Sepia Venue Specific Writing WorkflowsUse Sepia to write, review, minimally refactor, or fully recreate fiction and professional prose with agent-native de-AI writing protocols.Votes: 0GitHub stars: 36