{ "schemaVersion": "1.0", "item": { "slug": "create-agent-with-telegram-group", "name": "Create Agent With Telegram Group", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/Sheetaa/create-agent-with-telegram-group", "canonicalUrl": "https://clawhub.ai/Sheetaa/create-agent-with-telegram-group", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/create-agent-with-telegram-group", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=create-agent-with-telegram-group", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/init_workspace.py", "scripts/provision_config.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/create-agent-with-telegram-group" }, "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." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/create-agent-with-telegram-group", "agentPageUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent", "manifestUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent.json", "briefUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "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." ], "prompts": [ { "label": "New install", "body": "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." }, { "label": "Upgrade existing", "body": "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." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Agent Create + Dedicated Telegram Group", "body": "Create one dedicated Telegram group per agent, bind the agent to that group, and set an isolated workspace path." }, { "title": "Script-first Rule", "body": "Prefer bundled scripts for deterministic steps (more stable + lower token cost). Only do manual JSON editing when scripts cannot cover a special case.\n\nUse:\n\nscripts/provision_config.py for agent/config/binding/no-mention setup (with automatic backup of openclaw.json)\nscripts/init_workspace.py for USER.md / IDENTITY.md / SOUL.md initialization" }, { "title": "Access Scope", "body": "This skill accesses the following files on the host:\n\n~/.openclaw/openclaw.json — read (model discovery) and write (agent binding)\n~/.openclaw/cron/jobs.json — read-only (for job listing if needed)\n~/claw-/ — workspace directory created by script\n~/.openclaw/agents//agent/ — directory created (no auth files copied)" }, { "title": "Config Safety", "body": "scripts/provision_config.py reads and writes ~/.openclaw/openclaw.json.\nBy default it creates a backup file: ~/.openclaw/openclaw.json.bak..\nIt updates only:\n\nagents.list (add/update target agent) — does NOT copy auth credentials\nbindings (add target telegram group binding)\nchannels.telegram.groups..requireMention=false\ngateway.reload.mode only if missing (sets default hybrid)\n\n\nThe skill does NOT propagate API keys or auth tokens between agents.\nGateway-level auth is inherited automatically; do not manually copy auth files." }, { "title": "Inputs", "body": "Collect (before executing):\n\nagent_name (required)\nmodel (required): ask user explicitly which model to use; model options must be read live from the user’s ~/.openclaw/openclaw.json (do not hardcode examples)\nOptional telegram_group_title override (custom group name)\nInitialization preferences (required ask):\n\nwhether to create/update USER.md\nwhether to create/update IDENTITY.md\nwhether to create/update SOUL.md\n\n\nIf initialization is enabled, collect content fields before writing files:\n\nUSER.md: user name / preferred call name / language / goals / notes\nIDENTITY.md: agent display name / vibe / emoji (optional)\nSOUL.md: role/mission / tone / constraints (short bullet points)\n\nNormalize agent_name:\n\nKeep lowercase letters, digits, and hyphens only.\nReplace spaces/underscores with -.\nUse this value in paths and IDs.\n\nTelegram group title rule:\n\nIf user provides telegram_group_title, use it directly.\nIf not provided, generate default title from agent name in PascalCase.\n\nExample: test-skill -> TestSkill, bilingual-agent -> BilingualAgent." }, { "title": "Workflow", "body": "Read available models from ~/.openclaw/openclaw.json first, then confirm inputs with user (agent name, model, init-file preferences, optional telegram group title).\nBuild workspace path as ~/claw- and create it if missing.\nResolve group title:\n\ncustom telegram_group_title if provided\notherwise PascalCase(agent_name)\n\n\nCreate and bind Telegram group (use resolved group title):\n\nuse browser automation/user-account flow (Telegram bot API cannot reliably create groups)\nCONFIRM with user before triggering browser automation (explicit yes/no required)\nif browser automation is unavailable, request the minimal manual steps and resume\n\n\nCreate/update OpenClaw config via script (preferred):\n\nCONFIRM with user before modifying openclaw.json (explicit yes/no required)\npython3 scripts/provision_config.py --agent-name --model --chat-id \nthis sets: agent entry, workspace, binding, and requireMention=false\n\n\nApply config and activate it:\n\nif hot reload is enabled, verify reload logs show applied changes\nif reload is off or not applied, CONFIRM with user before restarting gateway (explicit yes/no required)\nrestart gateway only after user approval\n\n\nBootstrap agent runtime files (required for first-run stability):\n\nensure ~/.openclaw/agents//agent exists\ndo NOT copy any auth files from other agents (this prevents credential/API key propagation)\nnew agents inherit authentication from the gateway's shared auth context automatically\ndo NOT manually copy or create auth-profiles.json, auth.json, or models.json\n\n\nIf initialization is requested, ask user for file content fields first, then write files:\n\ncollect required values for USER.md / IDENTITY.md / SOUL.md\nthen run: python3 scripts/init_workspace.py --workspace --agent-name [--with-user] [--with-identity] [--with-soul]\nif user provided custom text, apply it after script initialization (overwrite placeholders)\n\n\nEnsure routing validity for current schema (no invalid allowFrom entries for groups).\nPost-provision verification:\n\nsend a test message in group and ask user to send ping\nconfirm agent responds without @mention\n\nReturn completion summary with:\n\nagent name\nmodel\nworkspace path\ngroup title\nchat_id\nno-mention reply mode (enabled/disabled)\nstatus and next step (if any)" }, { "title": "Telegram Automation Rules", "body": "Group creation/deletion and member operations should use browser automation (user-account flow).\nFor browser flow, prefer Chrome relay profile for existing logged-in Telegram sessions.\nIf no connected Chrome tab is available, ask user to attach once, then continue.\nIf Telegram shows confirmation/captcha that cannot be automated, request one manual click, then resume." }, { "title": "OpenClaw Command Discovery", "body": "Do not invent OpenClaw commands.\n\nWhen agent create/update command syntax is unknown:\n\nRun openclaw help.\nIf needed, run openclaw --help for the relevant subcommand.\nUse only discovered command forms." }, { "title": "Idempotency", "body": "If ~/claw- already exists, reuse it.\nIf a same-name group already exists, confirm whether to reuse or create a fresh one.\nIf agent already exists, update model/binding/workdir instead of duplicating." }, { "title": "Reliability Checks (must do)", "body": "Verify requireMention=false for the bound group.\nVerify gateway config actually applied:\n\ncheck reload mode/status logs (config hot reload applied, restarting telegram channel)\nif reload is off or not applied, restart gateway and re-check logs.\n\n\nSend one bot-originated test message to the new group, then require one live user ping.\nVerify agent replies without @mention.\nDo not claim success before ping -> pong verification passes." }, { "title": "Failure Handling", "body": "If group creation succeeds but binding fails:\n\nKeep created group.\nReport exact failed step.\nProvide one-command resume instruction for the next run.\n\nIf chat_id cannot be resolved automatically:\n\nReport that as a partial success.\nProvide the shortest fallback step to fetch chat_id, then continue binding." }, { "title": "Output Template", "body": "Return concise status:\n\nagent: \nmodel: \nworkspace: ~/claw-\ntelegram_group: \nchat_id: <id or PENDING>\nbinding: <done|pending>\nreply_without_mention: <enabled|disabled>\ninitialized_files: <USER.md, IDENTITY.md, SOUL.md or subset>\nverification: <passed|failed>\nnext_step: <none or exact minimal action>" } ], "body": "Agent Create + Dedicated Telegram Group\n\nCreate one dedicated Telegram group per agent, bind the agent to that group, and set an isolated workspace path.\n\nScript-first Rule\n\nPrefer bundled scripts for deterministic steps (more stable + lower token cost). Only do manual JSON editing when scripts cannot cover a special case.\n\nUse:\n\nscripts/provision_config.py for agent/config/binding/no-mention setup (with automatic backup of openclaw.json)\nscripts/init_workspace.py for USER.md / IDENTITY.md / SOUL.md initialization\nAccess Scope\n\nThis skill accesses the following files on the host:\n\n~/.openclaw/openclaw.json — read (model discovery) and write (agent binding)\n~/.openclaw/cron/jobs.json — read-only (for job listing if needed)\n~/claw-<agent-name>/ — workspace directory created by script\n~/.openclaw/agents/<agent-id>/agent/ — directory created (no auth files copied)\nConfig Safety\nscripts/provision_config.py reads and writes ~/.openclaw/openclaw.json.\nBy default it creates a backup file: ~/.openclaw/openclaw.json.bak.<timestamp>.\nIt updates only:\nagents.list (add/update target agent) — does NOT copy auth credentials\nbindings (add target telegram group binding)\nchannels.telegram.groups.<chat_id>.requireMention=false\ngateway.reload.mode only if missing (sets default hybrid)\nThe skill does NOT propagate API keys or auth tokens between agents.\nGateway-level auth is inherited automatically; do not manually copy auth files.\nInputs\n\nCollect (before executing):\n\nagent_name (required)\nmodel (required): ask user explicitly which model to use; model options must be read live from the user’s ~/.openclaw/openclaw.json (do not hardcode examples)\nOptional telegram_group_title override (custom group name)\nInitialization preferences (required ask):\nwhether to create/update USER.md\nwhether to create/update IDENTITY.md\nwhether to create/update SOUL.md\nIf initialization is enabled, collect content fields before writing files:\nUSER.md: user name / preferred call name / language / goals / notes\nIDENTITY.md: agent display name / vibe / emoji (optional)\nSOUL.md: role/mission / tone / constraints (short bullet points)\n\nNormalize agent_name:\n\nKeep lowercase letters, digits, and hyphens only.\nReplace spaces/underscores with -.\nUse this value in paths and IDs.\n\nTelegram group title rule:\n\nIf user provides telegram_group_title, use it directly.\nIf not provided, generate default title from agent name in PascalCase.\nExample: test-skill -> TestSkill, bilingual-agent -> BilingualAgent.\nWorkflow\nRead available models from ~/.openclaw/openclaw.json first, then confirm inputs with user (agent name, model, init-file preferences, optional telegram group title).\nBuild workspace path as ~/claw-<agent-name> and create it if missing.\nResolve group title:\ncustom telegram_group_title if provided\notherwise PascalCase(agent_name)\nCreate and bind Telegram group (use resolved group title):\nuse browser automation/user-account flow (Telegram bot API cannot reliably create groups)\nCONFIRM with user before triggering browser automation (explicit yes/no required)\nif browser automation is unavailable, request the minimal manual steps and resume\nCreate/update OpenClaw config via script (preferred):\nCONFIRM with user before modifying openclaw.json (explicit yes/no required)\npython3 scripts/provision_config.py --agent-name <agent_name> --model <model> --chat-id <chat_id>\nthis sets: agent entry, workspace, binding, and requireMention=false\nApply config and activate it:\nif hot reload is enabled, verify reload logs show applied changes\nif reload is off or not applied, CONFIRM with user before restarting gateway (explicit yes/no required)\nrestart gateway only after user approval\nBootstrap agent runtime files (required for first-run stability):\nensure ~/.openclaw/agents/<agent-id>/agent exists\ndo NOT copy any auth files from other agents (this prevents credential/API key propagation)\nnew agents inherit authentication from the gateway's shared auth context automatically\ndo NOT manually copy or create auth-profiles.json, auth.json, or models.json\nIf initialization is requested, ask user for file content fields first, then write files:\ncollect required values for USER.md / IDENTITY.md / SOUL.md\nthen run: python3 scripts/init_workspace.py --workspace <workspace> --agent-name <agent_name> [--with-user] [--with-identity] [--with-soul]\nif user provided custom text, apply it after script initialization (overwrite placeholders)\nEnsure routing validity for current schema (no invalid allowFrom entries for groups).\nPost-provision verification:\nsend a test message in group and ask user to send ping\nconfirm agent responds without @mention\nReturn completion summary with:\nagent name\nmodel\nworkspace path\ngroup title\nchat_id\nno-mention reply mode (enabled/disabled)\nstatus and next step (if any)\nTelegram Automation Rules\nGroup creation/deletion and member operations should use browser automation (user-account flow).\nFor browser flow, prefer Chrome relay profile for existing logged-in Telegram sessions.\nIf no connected Chrome tab is available, ask user to attach once, then continue.\nIf Telegram shows confirmation/captcha that cannot be automated, request one manual click, then resume.\nOpenClaw Command Discovery\n\nDo not invent OpenClaw commands.\n\nWhen agent create/update command syntax is unknown:\n\nRun openclaw help.\nIf needed, run openclaw <subcommand> --help for the relevant subcommand.\nUse only discovered command forms.\nIdempotency\nIf ~/claw-<agent-name> already exists, reuse it.\nIf a same-name group already exists, confirm whether to reuse or create a fresh one.\nIf agent already exists, update model/binding/workdir instead of duplicating.\nReliability Checks (must do)\nVerify requireMention=false for the bound group.\nVerify gateway config actually applied:\ncheck reload mode/status logs (config hot reload applied, restarting telegram channel)\nif reload is off or not applied, restart gateway and re-check logs.\nSend one bot-originated test message to the new group, then require one live user ping.\nVerify agent replies without @mention.\nDo not claim success before ping -> pong verification passes.\nFailure Handling\n\nIf group creation succeeds but binding fails:\n\nKeep created group.\nReport exact failed step.\nProvide one-command resume instruction for the next run.\n\nIf chat_id cannot be resolved automatically:\n\nReport that as a partial success.\nProvide the shortest fallback step to fetch chat_id, then continue binding.\nOutput Template\n\nReturn concise status:\n\nagent: <agent-name>\nmodel: <selected-model>\nworkspace: ~/claw-<agent-name>\ntelegram_group: <title>\nchat_id: <id or PENDING>\nbinding: <done|pending>\nreply_without_mention: <enabled|disabled>\ninitialized_files: <USER.md, IDENTITY.md, SOUL.md or subset>\nverification: <passed|failed>\nnext_step: <none or exact minimal action>" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Sheetaa/create-agent-with-telegram-group", "publisherUrl": "https://clawhub.ai/Sheetaa/create-agent-with-telegram-group", "owner": "Sheetaa", "version": "0.1.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group", "downloadUrl": "https://openagent3.xyz/downloads/create-agent-with-telegram-group", "agentUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent", "manifestUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent.json", "briefUrl": "https://openagent3.xyz/skills/create-agent-with-telegram-group/agent.md" } }