[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-cao-worker-protocols":3,"mdc--rfhou8-key":33,"related-repo-aws-labs-cao-worker-protocols":336,"related-org-aws-labs-cao-worker-protocols":437},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":31,"mdContent":32},"cao-worker-protocols","manage CAO worker task protocols","Worker-side callback and completion rules for assigned and handed-off tasks in CAO",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20],{"name":14,"slug":15,"type":16},"Automation","automation","tag",{"name":18,"slug":19,"type":16},"Orchestration","orchestration",{"name":21,"slug":22,"type":16},"Agents","agents",871,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fcli-agent-orchestrator","2026-07-12T08:36:59.573157",null,164,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fcli-agent-orchestrator\u002Ftree\u002FHEAD\u002Fskills\u002Fcao-worker-protocols","---\nname: cao-worker-protocols\ndescription: Worker-side callback and completion rules for assigned and handed-off tasks in CAO\n---\n\n# CAO Worker Protocols\n\nUse this skill when acting as a worker agent inside CLI Agent Orchestrator.\n\nThis skill explains how workers should interpret assigned versus handed-off work, when to call `send_message`, and how to report results back cleanly.\n\n## Understand the Dispatch Mode\n\nWorkers receive tasks through one of two orchestration modes:\n\n- `handoff`: blocking work where the orchestrator captures your final output automatically\n- `assign`: non-blocking work where you must actively return results to the requesting terminal\n\nDepending on provider and CAO behavior, a handoff may be made explicit in the task text. For example, Codex workers currently receive a `[CAO Handoff]` prefix for blocking handoffs. Other providers may rely on the task wording and orchestration context instead.\n\n## Rules for Handoff Tasks\n\nWhen the task is a blocking handoff, complete the work and present the result in your normal response. The orchestrator captures that response automatically.\n\nDo not call `send_message` for ordinary handoff completion unless the task explicitly asks for additional side-channel communication.\n\n## Rules for Assigned Tasks\n\nWhen the task came through `assign`, send your results back after you finish the work:\n\n1. Format the result clearly and concisely.\n2. Call `send_message(message=...)` — omitting `receiver_id` routes the result to the terminal that assigned the task (the recorded caller). This is the reliable default.\n3. If the task message names a different callback terminal (directly or in an appended suffix such as `[Assigned by terminal ...]`), pass that ID as `receiver_id` instead.\n\nDo not stop after writing a normal response if the assignment explicitly requires a callback. The requesting terminal depends on `send_message` to receive the result.\n\nYour own `CAO_TERMINAL_ID` identifies your terminal, not the callback target. Never pass it as `receiver_id`.\n\n## Message Formatting\n\nReturn results that are easy for the supervisor to merge into a larger workflow:\n\n- Identify what task or dataset the result belongs to\n- Include the requested output or deliverable\n- Keep the message specific enough to act on without re-reading the whole task\n\nIf the task asks for progress updates, use `send_message` for those updates too. Otherwise prefer one final callback with the completed deliverable.\n\n## Filesystem and Reporting Discipline\n\nIf the task asks you to create files, write them before reporting completion. When sending results back to a supervisor, include absolute file paths so the supervisor can continue the workflow without ambiguity.\n\n## Reliability Guidelines\n\n- If the task names an explicit callback terminal, note its ID before you start expensive work; otherwise rely on the default routing (omit `receiver_id`).\n- If `send_message` is available and the task requires a callback, call it directly rather than ending with prose alone.\n- Keep callback messages structured so the supervisor can merge them into a larger workflow.\n- For handoff tasks, return the completed output directly and let the orchestrator handle delivery.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,52,66,73,78,105,118,124,129,141,147,159,209,221,241,247,252,270,282,288,293,299],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","CAO Worker Protocols",{"type":39,"tag":47,"props":48,"children":49},"p",{},[50],{"type":44,"value":51},"Use this skill when acting as a worker agent inside CLI Agent Orchestrator.",{"type":39,"tag":47,"props":53,"children":54},{},[55,57,64],{"type":44,"value":56},"This skill explains how workers should interpret assigned versus handed-off work, when to call ",{"type":39,"tag":58,"props":59,"children":61},"code",{"className":60},[],[62],{"type":44,"value":63},"send_message",{"type":44,"value":65},", and how to report results back cleanly.",{"type":39,"tag":67,"props":68,"children":70},"h2",{"id":69},"understand-the-dispatch-mode",[71],{"type":44,"value":72},"Understand the Dispatch Mode",{"type":39,"tag":47,"props":74,"children":75},{},[76],{"type":44,"value":77},"Workers receive tasks through one of two orchestration modes:",{"type":39,"tag":79,"props":80,"children":81},"ul",{},[82,94],{"type":39,"tag":83,"props":84,"children":85},"li",{},[86,92],{"type":39,"tag":58,"props":87,"children":89},{"className":88},[],[90],{"type":44,"value":91},"handoff",{"type":44,"value":93},": blocking work where the orchestrator captures your final output automatically",{"type":39,"tag":83,"props":95,"children":96},{},[97,103],{"type":39,"tag":58,"props":98,"children":100},{"className":99},[],[101],{"type":44,"value":102},"assign",{"type":44,"value":104},": non-blocking work where you must actively return results to the requesting terminal",{"type":39,"tag":47,"props":106,"children":107},{},[108,110,116],{"type":44,"value":109},"Depending on provider and CAO behavior, a handoff may be made explicit in the task text. For example, Codex workers currently receive a ",{"type":39,"tag":58,"props":111,"children":113},{"className":112},[],[114],{"type":44,"value":115},"[CAO Handoff]",{"type":44,"value":117}," prefix for blocking handoffs. Other providers may rely on the task wording and orchestration context instead.",{"type":39,"tag":67,"props":119,"children":121},{"id":120},"rules-for-handoff-tasks",[122],{"type":44,"value":123},"Rules for Handoff Tasks",{"type":39,"tag":47,"props":125,"children":126},{},[127],{"type":44,"value":128},"When the task is a blocking handoff, complete the work and present the result in your normal response. The orchestrator captures that response automatically.",{"type":39,"tag":47,"props":130,"children":131},{},[132,134,139],{"type":44,"value":133},"Do not call ",{"type":39,"tag":58,"props":135,"children":137},{"className":136},[],[138],{"type":44,"value":63},{"type":44,"value":140}," for ordinary handoff completion unless the task explicitly asks for additional side-channel communication.",{"type":39,"tag":67,"props":142,"children":144},{"id":143},"rules-for-assigned-tasks",[145],{"type":44,"value":146},"Rules for Assigned Tasks",{"type":39,"tag":47,"props":148,"children":149},{},[150,152,157],{"type":44,"value":151},"When the task came through ",{"type":39,"tag":58,"props":153,"children":155},{"className":154},[],[156],{"type":44,"value":102},{"type":44,"value":158},", send your results back after you finish the work:",{"type":39,"tag":160,"props":161,"children":162},"ol",{},[163,168,189],{"type":39,"tag":83,"props":164,"children":165},{},[166],{"type":44,"value":167},"Format the result clearly and concisely.",{"type":39,"tag":83,"props":169,"children":170},{},[171,173,179,181,187],{"type":44,"value":172},"Call ",{"type":39,"tag":58,"props":174,"children":176},{"className":175},[],[177],{"type":44,"value":178},"send_message(message=...)",{"type":44,"value":180}," — omitting ",{"type":39,"tag":58,"props":182,"children":184},{"className":183},[],[185],{"type":44,"value":186},"receiver_id",{"type":44,"value":188}," routes the result to the terminal that assigned the task (the recorded caller). This is the reliable default.",{"type":39,"tag":83,"props":190,"children":191},{},[192,194,200,202,207],{"type":44,"value":193},"If the task message names a different callback terminal (directly or in an appended suffix such as ",{"type":39,"tag":58,"props":195,"children":197},{"className":196},[],[198],{"type":44,"value":199},"[Assigned by terminal ...]",{"type":44,"value":201},"), pass that ID as ",{"type":39,"tag":58,"props":203,"children":205},{"className":204},[],[206],{"type":44,"value":186},{"type":44,"value":208}," instead.",{"type":39,"tag":47,"props":210,"children":211},{},[212,214,219],{"type":44,"value":213},"Do not stop after writing a normal response if the assignment explicitly requires a callback. The requesting terminal depends on ",{"type":39,"tag":58,"props":215,"children":217},{"className":216},[],[218],{"type":44,"value":63},{"type":44,"value":220}," to receive the result.",{"type":39,"tag":47,"props":222,"children":223},{},[224,226,232,234,239],{"type":44,"value":225},"Your own ",{"type":39,"tag":58,"props":227,"children":229},{"className":228},[],[230],{"type":44,"value":231},"CAO_TERMINAL_ID",{"type":44,"value":233}," identifies your terminal, not the callback target. Never pass it as ",{"type":39,"tag":58,"props":235,"children":237},{"className":236},[],[238],{"type":44,"value":186},{"type":44,"value":240},".",{"type":39,"tag":67,"props":242,"children":244},{"id":243},"message-formatting",[245],{"type":44,"value":246},"Message Formatting",{"type":39,"tag":47,"props":248,"children":249},{},[250],{"type":44,"value":251},"Return results that are easy for the supervisor to merge into a larger workflow:",{"type":39,"tag":79,"props":253,"children":254},{},[255,260,265],{"type":39,"tag":83,"props":256,"children":257},{},[258],{"type":44,"value":259},"Identify what task or dataset the result belongs to",{"type":39,"tag":83,"props":261,"children":262},{},[263],{"type":44,"value":264},"Include the requested output or deliverable",{"type":39,"tag":83,"props":266,"children":267},{},[268],{"type":44,"value":269},"Keep the message specific enough to act on without re-reading the whole task",{"type":39,"tag":47,"props":271,"children":272},{},[273,275,280],{"type":44,"value":274},"If the task asks for progress updates, use ",{"type":39,"tag":58,"props":276,"children":278},{"className":277},[],[279],{"type":44,"value":63},{"type":44,"value":281}," for those updates too. Otherwise prefer one final callback with the completed deliverable.",{"type":39,"tag":67,"props":283,"children":285},{"id":284},"filesystem-and-reporting-discipline",[286],{"type":44,"value":287},"Filesystem and Reporting Discipline",{"type":39,"tag":47,"props":289,"children":290},{},[291],{"type":44,"value":292},"If the task asks you to create files, write them before reporting completion. When sending results back to a supervisor, include absolute file paths so the supervisor can continue the workflow without ambiguity.",{"type":39,"tag":67,"props":294,"children":296},{"id":295},"reliability-guidelines",[297],{"type":44,"value":298},"Reliability Guidelines",{"type":39,"tag":79,"props":300,"children":301},{},[302,314,326,331],{"type":39,"tag":83,"props":303,"children":304},{},[305,307,312],{"type":44,"value":306},"If the task names an explicit callback terminal, note its ID before you start expensive work; otherwise rely on the default routing (omit ",{"type":39,"tag":58,"props":308,"children":310},{"className":309},[],[311],{"type":44,"value":186},{"type":44,"value":313},").",{"type":39,"tag":83,"props":315,"children":316},{},[317,319,324],{"type":44,"value":318},"If ",{"type":39,"tag":58,"props":320,"children":322},{"className":321},[],[323],{"type":44,"value":63},{"type":44,"value":325}," is available and the task requires a callback, call it directly rather than ending with prose alone.",{"type":39,"tag":83,"props":327,"children":328},{},[329],{"type":44,"value":330},"Keep callback messages structured so the supervisor can merge them into a larger workflow.",{"type":39,"tag":83,"props":332,"children":333},{},[334],{"type":44,"value":335},"For handoff tasks, return the completed output directly and let the orchestrator handle delivery.",{"items":337,"total":436},[338,357,370,382,398,411,425],{"slug":339,"name":339,"fn":340,"description":341,"org":342,"tags":343,"stars":23,"repoUrl":24,"updatedAt":356},"add-app-to-server","add interactive UI to MCP servers","This skill should be used when the user asks to \"add an app to my MCP server\", \"add UI to my MCP server\", \"add a view to my MCP tool\", \"enrich MCP tools with UI\", \"add interactive UI to existing server\", \"add MCP Apps to my server\", or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[344,347,350,353],{"name":345,"slug":346,"type":16},"Frontend","frontend",{"name":348,"slug":349,"type":16},"MCP","mcp",{"name":351,"slug":352,"type":16},"Plugin Development","plugin-development",{"name":354,"slug":355,"type":16},"UI Components","ui-components","2026-07-12T08:41:40.4008",{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":23,"repoUrl":24,"updatedAt":369},"agui-author","emit interactive dashboard UI components","Author live dashboard UI from an agent via the `emit_ui` MCP tool. Emit one of six allow-listed components (approval_card, choice_prompt, diff_summary, progress, metric, agent_card) with JSON props and it renders in any AG-UI client watching the fleet. Use when you want the operator to see a decision, a diff, or a status readout instead of scrolling terminal text. Arbitrary HTML\u002Fmarkup is refused.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[363,364,367,368],{"name":21,"slug":22,"type":16},{"name":365,"slug":366,"type":16},"Dashboards","dashboards",{"name":348,"slug":349,"type":16},{"name":354,"slug":355,"type":16},"2026-07-22T05:35:50.851108",{"slug":371,"name":371,"fn":372,"description":373,"org":374,"tags":375,"stars":23,"repoUrl":24,"updatedAt":381},"cao-agent-routing","route tasks to appropriate CAO agents","Find and select the best installed CAO agent profile for a task before delegating with assign or handoff. Use when a supervisor needs to route coding, documentation, infrastructure, review, research, or other specialist work and the user has not already chosen an agent profile.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[376,377,380],{"name":21,"slug":22,"type":16},{"name":378,"slug":379,"type":16},"AWS","aws",{"name":18,"slug":19,"type":16},"2026-07-25T05:56:34.255071",{"slug":383,"name":383,"fn":384,"description":385,"org":386,"tags":387,"stars":23,"repoUrl":24,"updatedAt":397},"cao-learning","report task outcomes and distill lessons","Report task outcomes and distill lessons so the team improves across runs — report_outcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learning_enabled; degrade silently when the tools report disabled.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[388,391,394],{"name":389,"slug":390,"type":16},"Best Practices","best-practices",{"name":392,"slug":393,"type":16},"Engineering","engineering",{"name":395,"slug":396,"type":16},"Operations","operations","2026-07-29T06:00:28.147989",{"slug":399,"name":399,"fn":400,"description":401,"org":402,"tags":403,"stars":23,"repoUrl":24,"updatedAt":410},"cao-mcp-apps","operate CAO MCP application surfaces","Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman). Use when the user says \"enable MCP Apps in CAO\", \"the ui:\u002F\u002Fcao views aren't rendering\", \"rebuild MCP Apps bundles\", \"add a new ui:\u002F\u002Fcao\u002F* view\", or \"configure the MCP Apps OAuth scope layer\". Operates on the CAO_MCP_APPS_ENABLED surface and cao_mcp_apps\u002F build system. Not for the localhost:9889 browser dashboard, not for plugins, providers, or session management.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[404,405,408,409],{"name":21,"slug":22,"type":16},{"name":406,"slug":407,"type":16},"CLI","cli",{"name":348,"slug":349,"type":16},{"name":354,"slug":355,"type":16},"2026-07-22T05:35:52.952289",{"slug":412,"name":412,"fn":413,"description":414,"org":415,"tags":416,"stars":23,"repoUrl":24,"updatedAt":424},"cao-memory","manage durable agent memory and preferences","Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[417,418,421],{"name":21,"slug":22,"type":16},{"name":419,"slug":420,"type":16},"Memory","memory",{"name":422,"slug":423,"type":16},"Productivity","productivity","2026-07-12T08:37:03.180421",{"slug":426,"name":426,"fn":427,"description":428,"org":429,"tags":430,"stars":23,"repoUrl":24,"updatedAt":435},"cao-plugin","scaffold CAO agent plugins","Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when the user asks what plugin events are available, how plugin discovery works, or how to install a plugin into a CAO environment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[431,432,433,434],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":406,"slug":407,"type":16},{"name":351,"slug":352,"type":16},"2026-07-12T08:36:49.784639",16,{"items":438,"total":614},[439,458,479,489,502,515,525,535,556,571,586,599],{"slug":440,"name":440,"fn":441,"description":442,"org":443,"tags":444,"stars":455,"repoUrl":456,"updatedAt":457},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[445,446,449,452],{"name":378,"slug":379,"type":16},{"name":447,"slug":448,"type":16},"Debugging","debugging",{"name":450,"slug":451,"type":16},"Logs","logs",{"name":453,"slug":454,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":459,"name":460,"fn":461,"description":462,"org":463,"tags":464,"stars":455,"repoUrl":456,"updatedAt":478},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[465,468,469,472,475],{"name":466,"slug":467,"type":16},"Aurora","aurora",{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},"Database","database",{"name":473,"slug":474,"type":16},"Serverless","serverless",{"name":476,"slug":477,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":480,"name":481,"fn":461,"description":462,"org":482,"tags":483,"stars":455,"repoUrl":456,"updatedAt":488},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[484,485,486,487],{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},{"name":473,"slug":474,"type":16},{"name":476,"slug":477,"type":16},"2026-07-12T08:36:42.694299",{"slug":490,"name":491,"fn":461,"description":462,"org":492,"tags":493,"stars":455,"repoUrl":456,"updatedAt":501},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[494,495,496,499,500],{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},{"name":497,"slug":498,"type":16},"Migration","migration",{"name":473,"slug":474,"type":16},{"name":476,"slug":477,"type":16},"2026-07-12T08:36:38.584057",{"slug":503,"name":504,"fn":461,"description":462,"org":505,"tags":506,"stars":455,"repoUrl":456,"updatedAt":514},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[507,508,509,512,513],{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},{"name":510,"slug":511,"type":16},"PostgreSQL","postgresql",{"name":473,"slug":474,"type":16},{"name":476,"slug":477,"type":16},"2026-07-12T08:36:46.530743",{"slug":516,"name":517,"fn":461,"description":462,"org":518,"tags":519,"stars":455,"repoUrl":456,"updatedAt":524},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[520,521,522,523],{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},{"name":473,"slug":474,"type":16},{"name":476,"slug":477,"type":16},"2026-07-12T08:36:48.104182",{"slug":526,"name":526,"fn":461,"description":462,"org":527,"tags":528,"stars":455,"repoUrl":456,"updatedAt":534},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[529,530,531,532,533],{"name":378,"slug":379,"type":16},{"name":470,"slug":471,"type":16},{"name":497,"slug":498,"type":16},{"name":473,"slug":474,"type":16},{"name":476,"slug":477,"type":16},"2026-07-12T08:36:36.374512",{"slug":536,"name":536,"fn":537,"description":538,"org":539,"tags":540,"stars":553,"repoUrl":554,"updatedAt":555},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[541,544,547,550],{"name":542,"slug":543,"type":16},"Accounting","accounting",{"name":545,"slug":546,"type":16},"Analytics","analytics",{"name":548,"slug":549,"type":16},"Cost Optimization","cost-optimization",{"name":551,"slug":552,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":557,"name":557,"fn":558,"description":559,"org":560,"tags":561,"stars":553,"repoUrl":554,"updatedAt":570},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[562,563,564,567],{"name":378,"slug":379,"type":16},{"name":551,"slug":552,"type":16},{"name":565,"slug":566,"type":16},"Management","management",{"name":568,"slug":569,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":572,"name":572,"fn":573,"description":574,"org":575,"tags":576,"stars":553,"repoUrl":554,"updatedAt":585},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[577,578,579,582],{"name":545,"slug":546,"type":16},{"name":551,"slug":552,"type":16},{"name":580,"slug":581,"type":16},"Financial Statements","financial-statements",{"name":583,"slug":584,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":553,"repoUrl":554,"updatedAt":598},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[592,593,596],{"name":14,"slug":15,"type":16},{"name":594,"slug":595,"type":16},"Documents","documents",{"name":597,"slug":587,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":600,"name":600,"fn":601,"description":602,"org":603,"tags":604,"stars":553,"repoUrl":554,"updatedAt":613},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[605,606,609,610],{"name":542,"slug":543,"type":16},{"name":607,"slug":608,"type":16},"Data Analysis","data-analysis",{"name":551,"slug":552,"type":16},{"name":611,"slug":612,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150]