[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CZ3PGFC64PQ2SF3DRCATX":3,"skill-same:01M75CZ3PGFC64PQ2SF3DRCATX":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M75CZ3PGFC64PQ2SF3DRCATX","ogment-agentic-cli",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fasoviche\u002Fogment-agentic-cli\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"# Ogment CLI Skill\n\nSecurely invoke MCP tools via the Ogment CLI. Access your connected SaaS tools (Linear, Notion, Gmail, PostHog, etc.) through Ogment's governance layer.\n\n---\n\n## Quick Start (First-Time Onboarding)\n\n**Follow this flow when first using Ogment with a user:**\n\n### Step 1: Check Auth\n```bash\nogment auth status\n```\n- If `loggedIn: true` → skip to Step 3\n- If `loggedIn: false` → continue to Step 2\n\n### Step 2: Login (if needed)\n```bash\nogment auth login\n```\nExtract the code from the response and **send it to your human**.\n\n⚠️ **Make links clickable!** Use markdown or full URLs so humans can tap\u002Fclick directly.\n\n> **🔐 Approve this code to connect Ogment: `XXXX-XXXX`**\n> 👉 [dashboard.ogment.ai\u002Fcli\u002Fapprove](https:\u002F\u002Fdashboard.ogment.ai\u002Fcli\u002Fapprove)\n\nWait for approval, then verify with `ogment auth status`.\n\n### Step 3: Discover What's Available\n```bash\nogment catalog\n```\nThen for each server:\n```bash\nogment catalog \u003CserverId> | jq '[.data.tools[].name]'\n```\n\n### Step 4: Summarize to Your Human\nTell them what you found:\n\n> **✅ Connected to Ogment!** Here's what I can access:\n> - **Linear:** 28 tools (issues, projects, teams, docs)\n> - **Gmail:** 11 tools (messages, threads, drafts)\n> - **Notion:** 5 tools (search, fetch, comments)\n> - **Slack:** 7 tools (conversations, users)\n>\n> What would you like me to help with?\n\n---\n\n## Prerequisites\n\n| Requirement | Install | Required |\n|-------------|---------|----------|\n| `ogment` CLI | `npm install -g @ogment-ai\u002Fcli` | ✅ Yes |\n| `jq` | `brew install jq` \u002F `apt install jq` | Optional (for filtering) |\n\n## First-Time Setup (Login Flow)\n\n⚠️ **IMPORTANT FOR AGENTS:** Don't tell the human to run `ogment auth login` — run it yourself and send them the code!\n\n### Step 1: Check if already authenticated\n```bash\nogment auth status\n```\nIf `loggedIn: true`, skip to Core Workflow.\n\n### Step 2: If not logged in, start device flow\n```bash\nogment auth login\n```\nThis returns JSON with a device code. Extract and send to the human:\n\n**Example output:**\n```json\n{\n  \"data\": {\n    \"event\": \"auth_login.pending\",\n    \"verification\": {\n      \"userCode\": \"ABCD-1234\",\n      \"verificationUri\": \"https:\u002F\u002Fdashboard.ogment.ai\u002Fcli\u002Fapprove\"\n    }\n  }\n}\n```\n\n### Step 3: Send the code to your human\nTell them:\n> **Approve this code: `ABCD-1234`**\n> 👉 https:\u002F\u002Fdashboard.ogment.ai\u002Fcli\u002Fapprove\n\n### Step 4: Wait for approval\nThe `ogment auth login` command will complete automatically once approved. Then verify:\n```bash\nogment auth status\n```\n\n## Authentication & Credentials\n\n- **Credentials location:** `~\u002F.config\u002Fogment\u002Fcredentials.json`\n- **Token management:** Ogment handles OAuth for all connected services\n- **Scope:** Access depends on services connected in your [Ogment dashboard](https:\u002F\u002Fdashboard.ogment.ai)\n- **Per-agent permissions:** Each agent only sees tools you've explicitly granted\n\nNo credentials are stored in this skill — all auth is managed by the Ogment CLI.\n\n## When to Use\n\n- User asks to interact with their connected services (issues, docs, emails, analytics)\n- You need to call MCP tools that require auth\u002Fcredentials\n- Discovering what integrations the user has available\n\n## Core Workflow\n\n```\nstatus → catalog → catalog \u003Cserver> → catalog \u003Cserver> \u003Ctool> → invoke\n```\n\n### 1. Check connectivity (if issues suspected)\n\n```bash\nogment status\n```\n\nReturns auth state, connectivity, and available servers. Check `summary.status` for quick health.\n\n### 2. Discover servers\n\n```bash\nogment catalog\n```\n\nReturns list of servers with `serverId` and `toolCount`. Use `serverId` in subsequent calls.\n\n### 3. List tools on a server\n\n```bash\nogment catalog \u003CserverId>\n```\n\nReturns all tools with `name` and `description`. Scan descriptions to find the right tool.\n\n### 4. Inspect tool schema\n\n```bash\nogment catalog \u003CserverId> \u003CtoolName>\n```\n\nReturns `inputSchema` with properties, types, required fields, and descriptions.\n\n### 5. Invoke a tool\n\n```bash\nogment invoke \u003CserverId>\u002F\u003CtoolName> --input '\u003Cjson>'\n```\n\n**Input methods:**\n- Inline JSON: `--input '{\"query\": \"test\"}'`\n- File: `--input @path\u002Fto\u002Finput.json`\n- Stdin: `echo '{}' | ogment invoke ... --input -`\n\n### 6. Debug errors\n\n```bash\nogment invoke \u003CserverId>\u002F\u003CtoolName> --input '{}' --debug\n```\n\nThe `--debug` flag surfaces raw MCP error messages with field-level validation details.\n\n## Security Considerations\n\n### File Input Safety\n\nThe `--input @path` flag reads local files. **Avoid these paths:**\n- `~\u002F.ssh\u002F*` — SSH keys\n- `~\u002F.aws\u002F*` — AWS credentials  \n- `~\u002F.config\u002F` — App configs and tokens\n- `~\u002F.bash_history`, `~\u002F.zsh_history` — Shell history\n- Browser profile directories\n\n**Best practice:** Only use `--input @path` with files you've explicitly created for this purpose.\n\n### Network Security\n\n- All API calls route through `dashboard.ogment.ai`\n- No direct connections to SaaS APIs\n- TLS encrypted in transit\n\n### Permission Model\n\n- Tools are scoped per-agent in your Ogment dashboard\n- Agents only see tools you've granted access to\n- Write operations may be restricted based on agent permissions\n\n## Output Format\n\nAll commands return structured JSON:\n\n```json\n{\n  \"ok\": true,\n  \"data\": { ... },\n  \"error\": null,\n  \"meta\": { \"command\": \"...\" },\n  \"next_actions\": [\n    { \"command\": \"...\", \"title\": \"...\", \"reason\": \"...\" }\n  ]\n}\n```\n\n- **Check `ok` first** — boolean success indicator\n- **`next_actions`** — suggested follow-up commands\n- **`error.category`** — `validation`, `not_found`, `remote`, `auth`, `internal`\n- **`error.retryable`** — whether retry might help\n\n## Common Patterns\n\n### Find a tool by intent\n\n```bash\nogment catalog \u003CserverId> | jq '.data.tools[] | select(.name + .description | test(\"email\"; \"i\"))'\n```\n\n### List issues assigned to user\n\n```bash\nogment invoke openclaw\u002FLinear_list_issues --input '{\"assignee\": \"me\"}'\n```\n\n### Search Notion\n\n```bash\nogment invoke openclaw\u002FNotion_notion-search --input '{\"query\": \"quarterly review\", \"query_type\": \"internal\"}'\n```\n\n### Get Gmail messages\n\n```bash\nogment invoke openclaw\u002Fgmail_listMessages --input '{\"q\": \"is:unread\", \"maxResults\": 10}'\n```\n\n## Error Recovery\n\n| Error Code | Meaning | Action |\n|------------|---------|--------|\n| `TOOL_NOT_FOUND` | Bad server\u002Ftool name | Run `ogment catalog` to rediscover |\n| `VALIDATION_INVALID_INPUT` | Malformed JSON | Check JSON syntax |\n| `TRANSPORT_REQUEST_FAILED` | Server rejected call | Add `--debug`, check schema |\n| `AUTH_INVALID_CREDENTIALS` | Bad\u002Fexpired API key | Run `ogment auth login` |\n| `HTTP_401` | Service connection expired | Tell human to reconnect (see below) |\n| `HTTP_502` | Server down | Retry after delay |\n\n## Handling Expired Connections\n\nWhen you get `HTTP_401` with a message like:\n> \"Your connection to [Service] has expired. Please reconnect...\"\n\n**Tell your human (with clickable link):**\n> **⚠️ Your [Service] connection has expired.**\n> Please reconnect it here: [dashboard.ogment.ai](https:\u002F\u002Fdashboard.ogment.ai)\n> (Go to Integrations → [Service] → Reconnect)\n>\n> Let me know when done and I'll retry!\n\n## Handling Missing Permissions\n\nIf a tool you expect isn't available (e.g., `gmail_createDraft` not in catalog):\n- **This is normal** — agents have scoped permissions\n- Write tools may be disabled by default\n\n**Tell your human (with clickable link):**\n> **I don't have write access to [Service].**\n> To enable it, go to: [dashboard.ogment.ai](https:\u002F\u002Fdashboard.ogment.ai)\n> (Agents → [Agent Name] → Permissions)\n>\n> Let me know when updated and I'll check again!\n\n## Exit Codes\n\n| Code | Meaning |\n|------|---------|\n| 0 | Success |\n| 2 | Validation\u002Fparse error |\n| 5 | Not found |\n| 7 | Remote\u002Ftransport error |\n| 9 | Internal error |\n\n## Flags Reference\n\n| Flag | Effect |\n|------|--------|\n| `--debug` | Include raw error diagnostics |\n| `--human` | Human-readable output |\n| `--yes` | Auto-confirm prompts |\n| `--api-key \u003Ckey>` | Override API key |\n\n**Avoid:** `--quiet` (suppresses all output including data)\n\n## Pre-flight Checklist\n\nBefore invoking a tool:\n\n1. ✅ Confirmed server exists (`catalog`)\n2. ✅ Confirmed tool exists (`catalog \u003Cserver>`)\n3. ✅ Checked required fields in schema\n4. ✅ Matched types exactly (number vs string)\n5. ✅ Used exact casing for IDs\n6. ✅ If using `--input @path`, verified file doesn't contain sensitive data\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fasoviche\u002Fogment-agentic-cli",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill ogment-agentic-cli",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill ogment-agentic-cli",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill ogment-agentic-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fasoviche\u002Fogment-agentic-cli\u002FSKILL.md",true,[],[46,54,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":53},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":53},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":53},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":53},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":53},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":53},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]