Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
13733 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| Build deterministic multi-agent networks with Inngest AgentKitagentskillexchange/skillsUse Inngest AgentKit to build TypeScript agent networks with deterministic routing, shared state, MCP tools, and local tracing. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Build Go MCP servers with MCP Goagentskillexchange/skillsUse MCP Go to implement typed Model Context Protocol servers in Go that expose tools, resources, prompts, and transport handlers to agent clients. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Build Persistent Codebase Context Graphs with Graftagentskillexchange/skillsBuild and maintain a repository-local context graph so coding agents can orient inside large codebases without rediscovering the same structure every session. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Buildkite Agent Monitoragentskillexchange/skillsMonitors Buildkite agent pools via the Buildkite REST API v3 and GraphQL API. Tracks agent connectivity, queue depth, job wait times, and dispatches Slack alerts for stalled or disconnected agents. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Cloudinary Asset Optimization Agentagentskillexchange/skillsManages image and video assets using the Cloudinary Node.js SDK and Upload API. Applies automatic format selection, responsive breakpoints, and AI-based cropping with face detection. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Cloudinary Media Optimization Agentagentskillexchange/skillsAutomates image and video optimization workflows via the Cloudinary Upload and Admin APIs. Applies responsive breakpoints, format negotiation, and intelligent cropping with gravity detection. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Cloudinary Media Transform Skillagentskillexchange/skillsManages image and video assets through the Cloudinary Upload and Admin APIs. Applies on-the-fly transformations, generates responsive breakpoints, and optimizes delivery with f_auto and q_auto parameters. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| Common Crawl Index Query Agentagentskillexchange/skillsQueries the Common Crawl Index API for large-scale web archive research and data extraction. Uses the CDX Server API, WARC record parsing with warcio, and the Common Crawl S3 bucket for bulk data access. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| session-statsfoyzulkarim/skillsRender a dashboard of the current Claude Code session — message counts, token usage, cache read/write, dollar cost, context %, lines changed, cost-per-turn sparkline, and a tool-call histogram — parsed from the session transcript JSONL by a bundled bash script. One bash call, zero analysis, zero confirmation. Optionally pass a session id to inspect a different session. Use when the user asks for session stats, usage, token or cost breakdown, or a session dashboard. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| setup-cost-trackingfoyzulkarim/skillsInstall genuine per-session cost tracking for Claude Code by wiring bundled logger scripts into the user's statusline — preserving any existing statusline and hooks. Use when the user asks to set up, install, enable, or repair cost tracking / cost logging / session cost capture. Idempotent; safe to re-run. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| sync-skillsfoyzulkarim/skillsCopy this repo's skills into another agent harness's skills directory by name — resolves the harness alias to its path via scripts/sync-targets.json and runs sync-skills.sh. Use only when the user asks to copy/sync/push the skills to another harness (oh-my-pi, opencode, kimi, codex, etc.) — never trigger automatically. | Stars: 43 | Updated | Claude CodeCodex | Verified | Install |
| gay-mcpplurigrid/asi | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| CRDT Skillplurigrid/asi | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| CRDT Skillplurigrid/asi | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| mcp-tripartiteplurigrid/asi | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| gay-mcpplurigrid/asi | Stars: 72 | Updated | Claude CodeCodex | Verified | Install |
| taisly-social-media-postingtaisly/agentConnect AI agents to Taisly through MCP to publish and schedule videos, inspect history, and manage reposts. | Stars: 222 | Updated | Claude CodeCodex | Verified | Install |
| architecture-decision-recordssupreme12343/Stai-ProjectCapture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| deep-researchsupreme12343/Stai-ProjectMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| super-collectzzsoszz/ai-software-factoryFind problems in one project, verify each, write one findings doc and hand it to Matt Pocock's /to-spec then /to-tickets; 1–5 tickets go to /implement-spec, 6+ to the super-board Backlog (no /to-spec or /to-tickets installed → files straight into Backlog). Source plug-ins - sentry (app errors), posthog (exceptions, rage/dead clicks, failure events, web vitals, tracking gaps), github (issues not on the board), prs (recurring problems in merged PRs and their review comments), architecture (refactor findings), plus any custom source added in onboard (an MCP server, HTTP API, CLI command or app). Each candidate is checked by one fresh verifier first. Dry-run by default. Use when the user says "super-collect", "/super-collect", "/super-collect sentry", "collect tickets", "triage errors onto the board", "what keeps breaking", or "find refactors". | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| ai-assisted-researchafeezadebayo/research-learning-skillsUse AI research tools well: choosing between deep research modes, AI search, assistants and browsing agents, writing research briefs with preferred sources and evidence standards, verifying citations, filling gaps, resolving conflicts, protecting confidential data and writing a human-checked synthesis. Use whenever someone uses deep research, AI search or an AI agent to research a topic, wants better research prompts, needs to verify AI-cited sources or turn an AI research report into a reliable summary. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| learning-plansafeezadebayo/research-learning-skillsBuild learning plans that work: testable target performances, starting assessments, sub-skills, focused resources, deliberate practice with feedback, real projects, weekly schedules, retrieval practice, spacing and interleaving, progress checks and adjustments, with a 12-week example. Use whenever someone wants to learn a new skill, tool, language or subject, plan study for a certification, change careers, build a learning roadmap or learn faster with practice instead of passive courses. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| work-issueby-carlos/plan-staged-rolloutWorks one GitHub issue or Jira ticket that the user names by number or key. When the ticket carries an AI prompt it reads the thread, branches, implements, opens a pull request and merges only after an explicit yes; without one it guides a person through the work and changes nothing. It can also resume a ticket's existing branch, or wait for a blocking issue to close first. Use only when the user explicitly asks to work a named ticket, such as "work issue 124", "work WID-120", "resume issue 124" or "work 124 after 123". Never start it on your own initiative. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| agentic-engineeringsakamoto-family-smile/agent_monorepoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| prediction-market-risk-reviewsakamoto-family-smile/agent_monorepoReview prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk. Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| auto-competitor-intelligence-ai-codingopenamer/openamerPowerContext, Context for work that humans and agents hand off and continue 1 project | news. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| auto-competitor-intelligence-claudepowered-aiopenamer/openamerAI agent system prompts cannot serve as the sole enforcement layer — guardrails must be implemented at the API gateway and token-permission level, not | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| auto-competitor-intelligence-electricity-useopenamer/openamerAs a heavy Claude Code user, Simon estimates his own usage at the equivalent of 4,400 "typical queries" to an LLM, for an equivalent of around $15-$20 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| auto-competitor-intelligence-jetbrains-zedopenamer/openamerProtocol ACP | Techzine Oct 08, 2025 Zed Code Editor Adds Agent Protocol for Flexible AI Integration | WebProNews Aug 28, 2025 Google Integrates Gemin | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| auto-competitor-intelligence-layerfs-aopenamer/openamerSet up LayerFS 1 Copy the prompt 2 Paste it into your agent 3 Open dsh web and watch every Branc | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |