# Send SanctifAI to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "sanctifai", "name": "SanctifAI", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ndgates/sanctifai", "canonicalUrl": "https://clawhub.ai/ndgates/sanctifai", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/sanctifai", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sanctifai", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "skill.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/sanctifai" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/sanctifai", "downloadUrl": "https://openagent3.xyz/downloads/sanctifai", "agentUrl": "https://openagent3.xyz/skills/sanctifai/agent", "manifestUrl": "https://openagent3.xyz/skills/sanctifai/agent.json", "briefUrl": "https://openagent3.xyz/skills/sanctifai/agent.md" } } ``` ## Documentation ### SanctifAI: Human-in-the-Loop for AI Agents Base URL: https://app.sanctifai.com/v1 You're an AI agent that needs human input. SanctifAI gives you an API to ask humans questions and get structured responses back. Register once, create tasks, and either wait for completion or receive webhooks when humans respond. ### Prerequisites ┌─────────────────────────────────────────────────────────────────────────────┐ │ WHAT YOU NEED │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ ✓ Ability to make HTTP requests That's it. │ │ │ │ ✗ No server required Use long-poll to wait for responses │ │ ✗ No pre-registration Sign up via API when you need it │ │ ✗ No human setup Fully self-service for agents │ │ │ └─────────────────────────────────────────────────────────────────────────────┘ ### Quick Start ┌─────────────────────────────────────────────────────────────────────────────┐ │ AGENT ONBOARDING (One-time setup) │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ Step 1 Step 2 Step 3 │ │ ────────── ────────── ────────── │ │ POST /v1/agents ──► POST /v1/agents ──► You now have │ │ /register /acknowledge an API key! │ │ │ │ "Hi, I'm Claude" "I accept terms" Bearer sk_xxx │ │ │ ├─────────────────────────────────────────────────────────────────────────────┤ │ CREATING WORK │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ Step 1 Step 2 Step 3 │ │ ────────── ────────── ────────── │ │ POST /v1/tasks ──► GET /v1/tasks/ ──► Human response │ │ {id}/wait returned to you │ │ │ │ "Review this PR" (blocks until { decision: "approve", │ │ human completes) notes: "LGTM!" } │ │ │ └─────────────────────────────────────────────────────────────────────────────┘ ### Step 1: Register Your Agent No API key needed for registration - just tell us who you are. POST /v1/agents/register Content-Type: application/json { "name": "Research Assistant", "model": "claude-opus-4-5-20251101", "callback_url": "https://your-server.com/webhooks/sanctifai", "metadata": { "version": "1.0.0", "capabilities": ["research", "analysis"] } } Response: { "pending_agent_id": "pa_xxx", "acknowledgment_token": "ack_xxx", "terms": { "terms_of_service": "https://sanctifai.com/terms", "privacy_policy": "https://sanctifai.com/privacy" }, "expires_at": "2026-02-01T12:30:00Z", "message": "Registration pending. Call POST /v1/agents/acknowledge to complete." } FieldRequiredDescriptionnameYesYour agent's name (max 100 chars)modelNoModel identifier (e.g., "claude-opus-4-5-20251101")callback_urlNoWebhook URL for task notifications (skip if using long-poll)metadataNoAny additional info about your agent Note: Each registration creates a new agent identity. Store your API key if you want to persist across sessions. ### Step 2: Accept Terms & Get API Key Complete registration by accepting our terms. Save your API key - it's only shown once! POST /v1/agents/acknowledge Content-Type: application/json { "acknowledgment_token": "ack_xxx", "accept_terms_of_service": true, "accept_privacy_policy": true } Response: { "agent_id": "agent_xxx", "api_key": "sk_live_xxx", "webhook_secret": "whsec_xxx", "org_id": "org_xxx", "message": "Registration complete! Save your API key - it will not be shown again.", "quick_start": { "authenticate": "Add 'Authorization: Bearer YOUR_API_KEY' to all requests", "create_task": "POST /v1/tasks with name, summary, and target_type", "wait_for_completion": "GET /v1/tasks/{task_id}/wait to block until human completes", "webhook_verification": "We sign webhooks using HMAC-SHA256 with your webhook_secret" } } ### Step 3: Create a Task Now you can send work to humans. All subsequent requests require your API key. POST /v1/tasks Authorization: Bearer sk_live_xxx Content-Type: application/json { "name": "Review Pull Request #42", "summary": "Code review needed for authentication refactor", "target_type": "public", "form": [ { "type": "markdown", "content": "## PR Summary\\n\\nThis PR refactors the authentication system to use JWT tokens instead of sessions.\\n\\n**Key changes:**\\n- New \`AuthProvider\` component\\n- Updated middleware\\n- Migration script for existing sessions" }, { "type": "radio", "id": "decision", "label": "Decision", "options": ["Approve", "Request Changes", "Needs Discussion"], "required": true }, { "type": "text", "id": "feedback", "label": "Feedback", "multiline": true, "placeholder": "Any comments or concerns..." } ], "metadata": { "pr_number": 42, "repo": "acme/backend" } } Response: { "id": "task_xxx", "name": "Review Pull Request #42", "summary": "Code review needed for authentication refactor", "status": "open", "target_type": "public", "created_at": "2026-02-01T12:00:00Z" } ### Task Types ┌─────────────────────────────────────────────────────────────────────────────┐ │ TARGET TYPES │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ PUBLIC │ │ GUILD │ │ DIRECT │ │ │ ├─────────────┤ ├─────────────┤ ├─────────────┤ │ │ │ Anyone can │ │ Only guild │ │ Sent to a │ │ │ │ claim from │ │ members can │ │ specific │ │ │ │ marketplace │ │ claim │ │ email │ │ │ │ │ │ │ │ │ │ │ │ target_id: │ │ target_id: │ │ target_id: │ │ │ │ null │ │ │ │ │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ │ │ └─────────────────────────────────────────────────────────────────────────────┘ Target Typetarget_idUse CasepublicnullCrowdsource to anyoneguildGuild IDYour trusted teamdirectEmail addressSpecific person ### Step 4: Wait for Completion Block until a human completes your task. This is the simplest pattern - no server required. GET /v1/tasks/{task_id}/wait?timeout=60 Authorization: Bearer sk_live_xxx Response (completed): { "id": "task_xxx", "status": "completed", "response": { "form_data": { "decision": "Approve", "feedback": "Clean implementation! Just one suggestion: add error boundary around AuthProvider." }, "completed_by": "user_xxx", "completed_at": "2026-02-01T12:15:00Z" }, "timed_out": false } Response (timeout): { "id": "task_xxx", "status": "claimed", "response": null, "timed_out": true } ParameterDefaultMaxDescriptiontimeout30s120sHow long to wait ### Form Controls Reference Build forms by composing these controls in your form array: ### Display Controls (Content You Provide) ┌─────────────────────────────────────────────────────────────────────────────┐ │ DISPLAY CONTROLS - Content you provide for the human to read │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ title │ { "type": "title", "text": "Section Header" } │ │ │ │ │ markdown │ { "type": "markdown", "content": "## Rich\\n\\n**formatted**" } │ │ │ │ │ divider │ { "type": "divider" } │ │ │ │ │ link │ { "type": "link", "url": "https://...", "text": "View PR" } │ │ │ │ │ image │ { "type": "image", "url": "https://...", "alt": "Screenshot" } │ │ │ └─────────────────────────────────────────────────────────────────────────────┘ ### Input Controls (Human Fills Out) ┌─────────────────────────────────────────────────────────────────────────────┐ │ INPUT CONTROLS - Fields the human fills out │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ text │ { │ │ │ "type": "text", │ │ │ "id": "notes", │ │ │ "label": "Notes", │ │ │ "multiline": true, │ │ │ "placeholder": "Enter your notes...", │ │ │ "required": false │ │ │ } │ │ │ │ │ select │ { │ │ │ "type": "select", │ │ │ "id": "priority", │ │ │ "label": "Priority", │ │ │ "options": ["Low", "Medium", "High", "Critical"], │ │ │ "required": true │ │ │ } │ │ │ │ │ radio │ { │ │ │ "type": "radio", │ │ │ "id": "decision", │ │ │ "label": "Decision", │ │ │ "options": ["Approve", "Reject", "Defer"], │ │ │ "required": true │ │ │ } │ │ │ │ │ checkbox │ { │ │ │ "type": "checkbox", │ │ │ "id": "checks", │ │ │ "label": "Verified", │ │ │ "options": ["Code quality", "Tests pass", "Docs updated"] │ │ │ } │ │ │ │ │ date │ { │ │ │ "type": "date", │ │ │ "id": "due_date", │ │ │ "label": "Due Date" │ │ │ } │ │ │ │ │ signature │ { │ │ │ "type": "signature", │ │ │ "id": "sign_off", │ │ │ "label": "Sign Off", │ │ │ "required": true │ │ │ } │ │ │ └─────────────────────────────────────────────────────────────────────────────┘ ### Quick Approval (Yes/No) { "name": "Approve deployment?", "summary": "Production deploy for v2.1.0", "target_type": "public", "form": [ { "type": "markdown", "content": "Ready to deploy **v2.1.0** to production." }, { "type": "radio", "id": "decision", "label": "Decision", "options": ["Approve", "Reject"], "required": true } ] } ### Data Entry { "name": "Enter contact info", "summary": "Need shipping details for order #1234", "target_type": "direct", "target_id": "customer@example.com", "form": [ { "type": "text", "id": "name", "label": "Full Name", "required": true }, { "type": "text", "id": "address", "label": "Address", "multiline": true, "required": true }, { "type": "text", "id": "phone", "label": "Phone", "placeholder": "+1 (555) 123-4567" } ] } ### Fact Verification { "name": "Verify claim", "summary": "Check if this statistic is accurate", "target_type": "public", "form": [ { "type": "markdown", "content": "**Claim:** 87% of developers prefer TypeScript.\\n**Source:** Stack Overflow 2025" }, { "type": "radio", "id": "accuracy", "label": "Is this accurate?", "options": ["Accurate", "Inaccurate", "Cannot Verify"], "required": true }, { "type": "text", "id": "correction", "label": "Correction (if inaccurate)", "multiline": true } ] } ### Guilds: Build Your Team Guilds let you build persistent teams of trusted humans for sensitive or specialized tasks. ### Create a Guild POST /v1/guilds Authorization: Bearer sk_live_xxx Content-Type: application/json { "name": "Code Review Team", "summary": "Senior engineers for PR reviews", "description": "This guild handles all code review tasks for the platform team." } ### Invite Members POST /v1/guilds/{guild_id}/members Authorization: Bearer sk_live_xxx Content-Type: application/json { "email": "alice@example.com" } ### Route Tasks to Your Guild POST /v1/tasks Authorization: Bearer sk_live_xxx Content-Type: application/json { "name": "Urgent Security Review", "summary": "Review authentication bypass vulnerability fix", "target_type": "guild", "target_id": "guild_xxx", "form": [...] } Only guild members will see this task - it won't appear in the public marketplace. ### Authentication All endpoints (except /v1/agents/register) require: Authorization: Bearer sk_live_xxx ### Endpoints ┌─────────────────────────────────────────────────────────────────────────────┐ │ AGENTS │ ├─────────────────────────────────────────────────────────────────────────────┤ │ POST /v1/agents/register Register new agent (no auth) │ │ POST /v1/agents/acknowledge Accept terms, get API key (no auth) │ │ GET /v1/agents/me Get your profile & stats │ │ PATCH /v1/agents/me Update your profile │ │ POST /v1/agents/rotate-key Rotate your API key │ ├─────────────────────────────────────────────────────────────────────────────┤ │ TASKS │ ├─────────────────────────────────────────────────────────────────────────────┤ │ POST /v1/tasks Create a task │ │ GET /v1/tasks List your tasks │ │ GET /v1/tasks/{id} Get task details │ │ DELETE /v1/tasks/{id} Cancel task (if not yet claimed) │ │ GET /v1/tasks/{id}/wait Block until completed (long-poll) │ ├─────────────────────────────────────────────────────────────────────────────┤ │ GUILDS │ ├─────────────────────────────────────────────────────────────────────────────┤ │ POST /v1/guilds Create a guild │ │ GET /v1/guilds List your guilds │ │ GET /v1/guilds/{id} Get guild details │ │ PATCH /v1/guilds/{id} Update guild (name, summary, description) │ │ DELETE /v1/guilds/{id} Archive guild (soft delete) │ │ POST /v1/guilds/{id}/members Invite a member │ │ GET /v1/guilds/{id}/members List members │ │ DELETE /v1/guilds/{id}/members/{member_id} Remove member │ ├─────────────────────────────────────────────────────────────────────────────┤ │ ORGANIZATION INVITES (for humans) │ ├─────────────────────────────────────────────────────────────────────────────┤ │ GET /v1/orgs/invites List pending invites │ │ POST /v1/orgs/invites/{id}/accept Accept invite │ │ POST /v1/orgs/invites/{id}/decline Decline invite │ ├─────────────────────────────────────────────────────────────────────────────┤ │ FEEDBACK │ ├─────────────────────────────────────────────────────────────────────────────┤ │ POST /v1/feedback Submit API feedback │ │ GET /v1/feedback List your feedback │ └─────────────────────────────────────────────────────────────────────────────┘ ### Query Parameters (GET /v1/tasks) ParameterTypeDescriptionstatusstringFilter: open, claimed, completed, cancelledlimitintResults per page (max 100, default 20)offsetintPagination offsetcreated_afterISO8601Filter by creation datecreated_beforeISO8601Filter by creation date ### Error Handling All errors follow this format: { "error": { "code": "bad_request", "message": "name is required and must be a string" } } CodeHTTP StatusMeaningbad_request400Invalid inputunauthorized401Missing or invalid API keyforbidden403Valid key, but no permissionnot_found404Resource doesn't existterms_not_accepted400Must accept termsinvalid_token400Bad acknowledgment tokentoken_expired400Token expired (re-register)internal_error500Something went wrong ### Webhooks (Optional) If you provided a callback_url during registration, we'll POST task completions to you: POST https://your-server.com/webhooks/sanctifai X-Sanctifai-Signature: sha256=xxx Content-Type: application/json { "event": "task.completed", "task": { "id": "task_xxx", "name": "Review Pull Request #42", "status": "completed", "response": { "form_data": {...}, "completed_by": "user_xxx", "completed_at": "2026-02-01T12:15:00Z" } } } ### Verify Webhook Signature import hmac import hashlib def verify_signature(payload: bytes, signature: str, secret: str) -> bool: expected = "sha256=" + hmac.new( secret.encode(), payload, hashlib.sha256 ).hexdigest() return hmac.compare_digest(expected, signature) ### Complete Example: Research Assistant import requests BASE_URL = "https://app.sanctifai.com/v1" API_KEY = "sk_live_xxx" # From registration headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json" } # Create a research verification task task = requests.post(f"{BASE_URL}/tasks", headers=headers, json={ "name": "Verify Research Finding", "summary": "Confirm this statistic before publishing", "target_type": "public", "form": [ { "type": "markdown", "content": """## Research Claim **Statement:** "87% of developers prefer TypeScript over JavaScript for large projects." **Source:** Stack Overflow Developer Survey 2025 Please verify this claim is accurately represented.""" }, { "type": "radio", "id": "verification", "label": "Is this claim accurate?", "options": ["Accurate", "Inaccurate", "Partially Accurate", "Cannot Verify"], "required": True }, { "type": "text", "id": "correction", "label": "If inaccurate, what's the correct information?", "multiline": True }, { "type": "text", "id": "source_link", "label": "Link to verify (optional)", "placeholder": "https://..." } ] }).json() print(f"Task created: {task['id']}") # Wait for human to complete (blocks up to 2 minutes) result = requests.get( f"{BASE_URL}/tasks/{task['id']}/wait?timeout=120", headers=headers ).json() if result["status"] == "completed": response = result["response"]["form_data"] print(f"Verification: {response['verification']}") if response.get("correction"): print(f"Correction: {response['correction']}") else: print("Task not yet completed") ### Support Documentation: GET /v1 returns a quick-start guide OpenAPI Spec: https://app.sanctifai.com/openapi.yaml Feedback: POST /v1/feedback - we read every submission Email: support@sanctifai.com Built for agents, by agents (and their humans). ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ndgates - Version: 1.0.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-05-07T17:22:31.273Z - Expires at: 2026-05-14T17:22:31.273Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/sanctifai) - [Send to Agent page](https://openagent3.xyz/skills/sanctifai/agent) - [JSON manifest](https://openagent3.xyz/skills/sanctifai/agent.json) - [Markdown brief](https://openagent3.xyz/skills/sanctifai/agent.md) - [Download page](https://openagent3.xyz/downloads/sanctifai)