[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DWNEPTJ2Q0RWRV3KQFPN9":3,"skill-same:01M75DWNEPTJ2Q0RWRV3KQFPN9":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M75DWNEPTJ2Q0RWRV3KQFPN9","sergei-mikhailov-tg-channel-reader",null,"Read posts and comments from Telegram channels via MTProto (Pyrogram or Telethon). Fetch recent messages and discussion replies from public or private channels by time window.","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\u002Fbzsega\u002Fsergei-mikhailov-tg-channel-reader\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: sergei-mikhailov-tg-channel-reader\ndescription: Read posts and comments from Telegram channels via MTProto (Pyrogram or Telethon). Fetch recent messages and discussion replies from public or private channels by time window.\nmetadata: {\"openclaw\": {\"emoji\": \"📡\", \"requires\": {\"bins\": [\"tg-reader\", \"tg-reader-check\"], \"env\": [\"TG_API_ID\", \"TG_API_HASH\"]}, \"primaryEnv\": \"TG_API_HASH\"}}\n---\n\n# tg-channel-reader\n\nRead posts and comments from Telegram channels using MTProto (Pyrogram or Telethon).\nWorks with any public channel and private channels the user is subscribed to.\nSupports fetching discussion replies (comments) for individual posts.\n\n> **Security notice:** This skill requires `TG_API_ID` and `TG_API_HASH` from [my.telegram.org](https:\u002F\u002Fmy.telegram.org). The session file grants full Telegram account access — store it securely and never share it.\n\n---\n\n## Exec Approvals\n\n> **Just installed via `clawhub install`?** Complete Setup & Installation (below) first — the skill needs `pip install`, credentials, and a session file before exec approvals matter.\n\nOpenClaw blocks unknown CLI commands by default. The user must approve `tg-reader` commands before they can run. If the command hangs or the user says nothing is happening — exec approval is likely pending.\n\n### Quick setup (recommended)\n\nRun from the skill directory — checks prerequisites, installs pip packages if needed, and prints the approval commands to run:\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\nbash setup-tg-reader.sh\n```\n\n### Manual CLI approval\n\n```bash\nopenclaw approvals allowlist add --gateway \"$(which tg-reader)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-check)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-telethon)\"\n```\n\n### Alternative: approve on first use\n\n1. **Control UI** — open `http:\u002F\u002Flocalhost:18789\u002F`, find the pending approval for `tg-reader`, click **\"Always allow\"**. [Docs](https:\u002F\u002Fdocs.openclaw.ai\u002Fweb\u002Fcontrol-ui)\n2. **Messenger** (Telegram, Slack, Discord) — the bot sends an approval request with an `\u003Cid>`. Reply: `\u002Fapprove \u003Cid> allow-always`. Other options: `allow-once`, `deny`.\n\nThe approval prompt appears in the **Control UI or as a bot message** — not in the agent's conversation. This is a common source of confusion.\n\n---\n\n## When to Use\n\n- User asks to \"check\", \"read\", or \"monitor\" a Telegram channel\n- Wants a digest or summary of recent posts\n- Asks \"what's new in @channel\" or \"summarize last 24h from @channel\"\n- Wants to track or compare multiple channels\n- Wants channel info (title, description, subscribers) — use `tg-reader info`\n\n---\n\n## Quick Start\n\n```bash\n# 1. Run pre-flight diagnostic (fast, no Telegram connection)\ntg-reader-check\n\n# 2. Get channel info\ntg-reader info @channel_name\n\n# 3. Fetch recent posts\ntg-reader fetch @channel_name --since 24h\n```\n\n> **`tg-reader: command not found`?** Run `bash setup-tg-reader.sh` from the skill directory (it will install the package), or manually: `cd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader && pip install .`\n\n---\n\n## Commands\n\n### `tg-reader-check` — Pre-flight Diagnostic\n\n**Always run before fetching.** Fast offline check — no Telegram connection needed.\n\n```bash\ntg-reader-check\ntg-reader-check --config-file \u002Fpath\u002Fto\u002Fconfig.json\ntg-reader-check --session-file \u002Fpath\u002Fto\u002Fsession\n```\n\nReturns JSON with `\"status\": \"ok\"` or `\"status\": \"error\"` plus a `problems` array.\n\nVerifies:\n- Credentials available (env vars or `~\u002F.tg-reader.json`)\n- Session file exists on disk (with size, modification date)\n- At least one MTProto backend installed (Pyrogram or Telethon)\n- Detects stale sessions (config points to older file while a newer one exists)\n\n### `tg-reader info` — Channel Info\n\n```bash\ntg-reader info @channel_name\n```\n\nReturns title, description, subscriber count, and link.\n\n### `tg-reader fetch` — Read Posts\n\n```bash\n# Last 24 hours (default)\ntg-reader fetch @channel_name --since 24h\n\n# Last 7 days, up to 200 posts\ntg-reader fetch @channel_name --since 7d --limit 200\n\n# Multiple channels (fetched sequentially with 10s delay between each)\ntg-reader fetch @channel1 @channel2 @channel3 --since 24h\n\n# Custom delay between channels (seconds)\ntg-reader fetch @channel1 @channel2 @channel3 --since 24h --delay 5\n\n# Fetch posts with comments (single channel only, limit auto-drops to 30)\ntg-reader fetch @channel_name --since 7d --comments\n\n# More comments per post, custom delay between posts\ntg-reader fetch @channel_name --since 24h --comments --comment-limit 20 --comment-delay 5\n\n# Skip posts without text (media-only, no caption)\ntg-reader fetch @channel_name --since 24h --text-only\n\n# Human-readable output\ntg-reader fetch @channel_name --since 24h --format text\n\n# Write output to file instead of stdout (saves tokens)\ntg-reader fetch @channel_name --since 24h --output\ntg-reader fetch @channel_name --since 24h --comments --output comments.json\n\n# Use Telethon instead of Pyrogram (one-time)\ntg-reader fetch @channel_name --since 24h --telethon\n\n# Read unread mode — only fetch new (unread) posts, no --since needed\n# Requires \"read_unread\": true in ~\u002F.tg-reader.json\ntg-reader fetch @channel_name\n\n# Override read_unread mode (fetch everything, don't update state)\ntg-reader fetch @channel_name --since 7d --all\n\n# Custom state file location\ntg-reader fetch @channel_name --since 24h --state-file \u002Fpath\u002Fto\u002Fstate.json\n```\n\n### `tg-reader auth` — First-time Authentication\n\n```bash\ntg-reader auth\n```\n\nCreates a session file. Only needed once.\n\n---\n\n## Read Unread Mode\n\nOnly return new (unread) posts — the skill remembers what you've already seen. Useful for daily digests and monitoring workflows.\n\n### Setup\n\n**Option A — config file** (`~\u002F.tg-reader.json`):\n\n```json\n{\n  \"api_id\": 12345,\n  \"api_hash\": \"...\",\n  \"read_unread\": true\n}\n```\n\n**Option B — env var** (works with `~\u002F.openclaw\u002Fopenclaw.json`):\n\n```bash\nexport TG_READ_UNREAD=true\n```\n\nEnv vars take priority over the config file. This lets you enable read_unread via `openclaw.json` Docker `env` alongside `TG_API_ID`\u002F`TG_API_HASH`.\n\nState is stored in `~\u002F.tg-reader-state.json` (configurable via `\"state_file\"` in config, `TG_STATE_FILE` env var, or `--state-file` flag).\n\n### Behavior\n\n- **`--since` is not needed** when `read_unread` is enabled — the skill automatically returns all unread posts regardless of time\n- **First run** (no prior state for channel): `--since` applies as usual (default 24h); state file created\n- **Subsequent runs:** only posts newer than the last read are returned; `--since` is ignored\n- **`--all` flag:** bypasses read_unread mode — fetches everything by `--since` without updating state (preserves your position)\n- **New channel:** behaves like a first run (no prior state)\n- **No new posts:** state unchanged, `count: 0` returned\n\n### Examples\n\n```bash\n# With read_unread enabled — just fetch, no --since needed\ntg-reader fetch @channel_name\n\n# First run for a new channel — --since determines initial window\ntg-reader fetch @new_channel --since 7d\n\n# Override: fetch everything, don't update tracking state\ntg-reader fetch @channel_name --since 7d --all\n```\n\n### Output\n\nWhen read_unread mode is active, the JSON output includes a `read_unread` field:\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"read_unread\": {\"enabled\": true},\n  \"count\": 5,\n  \"messages\": [...]\n}\n```\n\nWith `--all`: `\"read_unread\": {\"enabled\": true, \"overridden\": true}`\n\n### Limitations\n\n- Tracking is **post-level only** — new comments on already-read posts are not caught\n- If a channel changes its username, tracking resets (state is keyed by username)\n- Concurrent runs for the same channel are safe but last writer wins\n\n### Diagnostic\n\n`tg-reader-check` reports tracking status:\n\n```json\n{\n  \"tracking\": {\n    \"read_unread\": true,\n    \"state_file\": \"~\u002F.tg-reader-state.json\",\n    \"state_file_exists\": true,\n    \"tracked_channels\": 3\n  }\n}\n```\n\n---\n\n## Output Format\n\n### `info`\n\n```json\n{\n  \"id\": -1001234567890,\n  \"title\": \"Channel Name\",\n  \"username\": \"channel_name\",\n  \"description\": \"About this channel...\",\n  \"members_count\": 42000,\n  \"link\": \"https:\u002F\u002Ft.me\u002Fchannel_name\"\n}\n```\n\n### `fetch`\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"fetched_at\": \"2026-02-22T10:00:00Z\",\n  \"since\": \"2026-02-21T10:00:00Z\",\n  \"count\": 12,\n  \"messages\": [\n    {\n      \"id\": 1234,\n      \"date\": \"2026-02-22T09:30:00Z\",\n      \"text\": \"Post content...\",\n      \"views\": 5200,\n      \"forwards\": 34,\n      \"link\": \"https:\u002F\u002Ft.me\u002Fchannel_name\u002F1234\",\n      \"has_media\": true,\n      \"media_type\": \"MessageMediaType.PHOTO\"\n    }\n  ]\n}\n```\n\n### `fetch` with `--comments`\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"fetched_at\": \"2026-02-28T10:00:00Z\",\n  \"since\": \"2026-02-27T10:00:00Z\",\n  \"count\": 5,\n  \"comments_enabled\": true,\n  \"comments_available\": true,\n  \"messages\": [\n    {\n      \"id\": 1234,\n      \"text\": \"Post content...\",\n      \"has_media\": false,\n      \"comment_count\": 2,\n      \"comments\": [\n        {\n          \"id\": 5678,\n          \"date\": \"2026-02-28T09:35:00Z\",\n          \"text\": \"Great post!\",\n          \"from_user\": \"username123\"\n        }\n      ]\n    }\n  ]\n}\n```\n\n**Notes:**\n- `comments_available: false` — channel has no linked discussion group (no comments possible)\n- `comments_error` on a message — rate limit hit for that post's comments\n- `from_user` may be `null` for anonymous comments\n- Images\u002Fvideos in comments are **not analyzed** — only text is captured\n- Default post limit drops to 30 when `--comments` is active (override with `--limit`)\n\n---\n\n## After Fetching\n\n1. Parse the JSON output\n2. Posts with images\u002Fvideos have `has_media: true` and a `media_type` field. Their text is in the `text` field (from the caption). **Do not skip posts just because they have media** — they often contain important text.\n3. Images and videos are **not analyzed** (no OCR\u002Fvision) — only the text\u002Fcaption is returned.\n4. Summarize key themes, top posts by views, notable links\n5. If `comments_enabled: true`, analyze comment sentiment and key themes alongside the main posts\n6. Save summary to `memory\u002FYYYY-MM-DD.md` if user wants to track over time\n\n### Saving to File (Token Economy)\n\nUse `--output` when the result is large (especially with `--comments`) and you don't need to analyze it immediately. The full data goes to a file, and stdout returns only a short confirmation — **this saves tokens**.\n\n**Periodic updates pattern:** set up a cron task that runs `tg-reader fetch @channel --comments --output comments.json` on schedule. The file gets updated regularly. When the user asks to analyze comments — read the file instead of re-fetching. This avoids consuming tokens on every fetch.\n\nWhen `--output` is used without a filename, the default is `tg-output.json`. Stdout confirmation:\n```json\n{\"status\": \"ok\", \"output_file\": \"\u002Fabsolute\u002Fpath\u002Fto\u002Ftg-output.json\", \"count\": 12}\n```\n\n### Saving Channel List\n\nStore tracked channels in `TOOLS.md`:\n\n```markdown\n## Telegram Channels\n- @channel1 — why tracked\n- @channel2 — why tracked\n```\n\n---\n\n## Error Handling\n\nErrors include an `error_type` and `action` field to help agents decide what to do automatically.\n\n### Channel Errors\n\n| `error_type` | Meaning | `action` |\n|--------------|---------|----------|\n| `access_denied` | Channel is private, you were kicked, or access is restricted | `remove_from_list_or_rejoin` — ask user if they still have access; if not, remove the channel |\n| `banned` | You are banned from this channel | `remove_from_list` — remove the channel, tell the user |\n| `not_found` | Channel doesn't exist or username is wrong | `check_username` — verify the @username with the user |\n| `invite_expired` | Invite link is expired or invalid | `request_new_invite` — ask user for a new invite link |\n| `flood_wait` | Telegram rate limit | `wait_Ns` — waits ≤ 60 s are retried automatically; longer waits return this error |\n| `comments_multi_channel` | `--comments` used with multiple channels | `remove_extra_channels_or_drop_comments` — use one channel at a time |\n\n### System Errors\n\n| Error | Action |\n|-------|--------|\n| `Session file not found` | Run `tg-reader-check` — use the `suggestion` from output |\n| `Missing credentials` | Guide user through Setup (Step 1-2 below) |\n| `tg-reader: command not found` | Run `bash setup-tg-reader.sh` from the skill directory, or manually: `pip install .` Fallback: `python3 -m tg_reader_unified` |\n| `AUTH_KEY_UNREGISTERED` | Session expired — delete and re-auth (see below) |\n\n### Session Expired\n\n```bash\nrm -f ~\u002F.tg-reader-session.session\ntg-reader auth\n```\n\n### Auth Code Not Arriving\n\nUse the verbose debug script for full MTProto-level logs:\n\n```bash\npython3 debug_auth.py\n```\n\n> **Warning:** `debug_auth.py` deletes existing session files before re-authenticating. It will ask for confirmation first.\n\n---\n\n## Library Selection\n\nTwo MTProto backends are supported:\n\n| Backend | Command | Notes |\n|---------|---------|-------|\n| **Pyrogram** (default) | `tg-reader` or `tg-reader-pyrogram` | Modern, actively maintained |\n| **Telethon** | `tg-reader-telethon` | Alternative if Pyrogram has issues |\n\nSwitch persistently: `export TG_USE_TELETHON=true`\nSwitch one-time: `tg-reader fetch @channel --since 24h --telethon`\n\n---\n\n## Setup & Installation\n\nFull details in [README.md](.\u002FREADME.md).\n\n### Step 1 — Get API Credentials\n\nGo to https:\u002F\u002Fmy.telegram.org → **API Development Tools** → create an app → copy `api_id` and `api_hash`.\n\n### Step 2 — Save Credentials\n\n**Recommended** (works in agents and servers):\n```bash\ncat > ~\u002F.tg-reader.json \u003C\u003C 'EOF'\n{\n  \"api_id\": YOUR_ID,\n  \"api_hash\": \"YOUR_HASH\"\n}\nEOF\nchmod 600 ~\u002F.tg-reader.json\n```\n\n**Alternative** (interactive shell only):\n```bash\nexport TG_API_ID=YOUR_ID\nexport TG_API_HASH=\"YOUR_HASH\"\n```\nSet these in your current shell session. Avoid writing `TG_API_HASH` to shell profiles (`~\u002F.bashrc`) — use `~\u002F.tg-reader.json` instead for persistent storage.\n\n> **Note:** Agents and servers don't load shell profiles. Use `~\u002F.tg-reader.json` (the recommended method above) for non-interactive environments.\n\n### Step 3 — Install & Configure\n\n```bash\nnpx clawhub@latest install sergei-mikhailov-tg-channel-reader\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\nbash setup-tg-reader.sh\n```\n\nThe setup script: installs Python packages (`pip install .`), checks credentials and session, runs `tg-reader-check`, and prints the exec approval commands for you to run manually.\n\nOn Linux with managed Python (Ubuntu\u002FDebian), use a venv **before** running the setup script:\n\n```bash\npython3 -m venv ~\u002F.venv\u002Ftg-reader\necho 'export PATH=\"$HOME\u002F.venv\u002Ftg-reader\u002Fbin:$PATH\"' >> ~\u002F.bashrc && source ~\u002F.bashrc\n```\n\n\u003Cdetails>\n\u003Csummary>Manual install (without setup script)\u003C\u002Fsummary>\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\npip install pyrogram tgcrypto telethon && pip install .\nopenclaw approvals allowlist add --gateway \"$(which tg-reader)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-check)\"\n```\n\u003C\u002Fdetails>\n\n### Step 4 — Authenticate\n\n```bash\ntg-reader auth\n```\n\nPyrogram will ask to confirm the phone number — answer `y`. The code arrives in the Telegram app (not SMS).\n\n### Step 5 — Verify\n\n```bash\ntg-reader-check\n```\n\nShould return `\"status\": \"ok\"`. If not — fix the reported issues and re-run `bash setup-tg-reader.sh`.\n\n---\n\n## Scheduled Tasks & Cron\n\nThis skill needs network access (MTProto connection to Telegram servers) and a session file. How you configure OpenClaw cron depends on the session target.\n\n> **Important:** When setting up a scheduled task that uses `tg-reader`, tell the user which approach you're using and what it means — so they can make an informed choice.\n\n### Option A — `sessionTarget: \"main\"` (recommended)\n\nThe cron task sends a **reminder** to the main agent session. The agent then runs `tg-reader` in the main environment where the skill, credentials, and session file are already available.\n\n**Pros:** No extra configuration — everything works out of the box.\n**Cons:** Not fully autonomous — the task sends a system event, the agent picks it up and executes. Requires `payload.kind: \"systemEvent\"` (OpenClaw cron API limitation for main target).\n\n**How to set up:**\n1. Create a cron task with `sessionTarget: \"main\"` and `payload.kind: \"systemEvent\"`\n2. In the task description, include the exact `tg-reader` command to run\n3. The agent receives the reminder and executes the command in its main session\n\n### Option B — `sessionTarget: \"isolated\"` (autonomous, complex setup)\n\nThe cron task runs in a **Docker container** — fully autonomous, no agent interaction needed. However, the container starts empty: no skill, no credentials, no session file.\n\n**Pros:** Fully autonomous — runs on schedule without agent involvement.\n**Cons:** Requires Docker setup; session file must be mounted into the container (may not work reliably — session files are tied to the machine and Telegram may invalidate them in a new environment).\n\n**Required configuration in `~\u002F.openclaw\u002Fopenclaw.json`:**\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"sandbox\": {\n        \"docker\": {\n          \"setupCommand\": \"clawhub install sergei-mikhailov-tg-channel-reader && cd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader && pip install pyrogram tgcrypto telethon && pip install .\",\n          \"env\": {\n            \"TG_API_ID\": \"YOUR_ID\",\n            \"TG_API_HASH\": \"YOUR_HASH\",\n            \"TG_READ_UNREAD\": \"true\"\n          }\n        }\n      }\n    }\n  }\n}\n```\n\n**Session file caveat:** The Telegram session file (`~\u002F.tg-reader-session.session`) must also be available inside the container. This may require Docker volume mounting and might not work reliably — Telegram can invalidate sessions when they appear from a different environment. If you encounter `AUTH_KEY_UNREGISTERED` errors in isolated mode, switch to Option A.\n\n### Explicit paths (both options)\n\nWhen `~\u002F` is not available or points to a different location, use explicit paths:\n\n```bash\ntg-reader-check \\\n  --config-file \u002Fhome\u002Fuser\u002F.tg-reader.json \\\n  --session-file \u002Fhome\u002Fuser\u002F.tg-reader-session\n\ntg-reader fetch @channel --since 6h \\\n  --config-file \u002Fhome\u002Fuser\u002F.tg-reader.json \\\n  --session-file \u002Fhome\u002Fuser\u002F.tg-reader-session\n```\n\nBoth flags work with all subcommands and both backends.\n\n---\n\n## Security\n\n- Session file (`~\u002F.tg-reader-session.session`) grants **full account access** — keep it safe\n- Never share or commit `TG_API_HASH` or session files\n- `TG_API_HASH` is a secret — store in env vars or config file, never in git\n","# tg-channel-reader\n\nRead posts and comments from Telegram channels using MTProto (Pyrogram or Telethon).\nWorks with any public channel and private channels the user is subscribed to.\nSupports fetching discussion replies (comments) for individual posts.\n\n> **Security notice:** This skill requires `TG_API_ID` and `TG_API_HASH` from [my.telegram.org](https:\u002F\u002Fmy.telegram.org). The session file grants full Telegram account access — store it securely and never share it.\n\n---\n\n## Exec Approvals\n\n> **Just installed via `clawhub install`?** Complete Setup & Installation (below) first — the skill needs `pip install`, credentials, and a session file before exec approvals matter.\n\nOpenClaw blocks unknown CLI commands by default. The user must approve `tg-reader` commands before they can run. If the command hangs or the user says nothing is happening — exec approval is likely pending.\n\n### Quick setup (recommended)\n\nRun from the skill directory — checks prerequisites, installs pip packages if needed, and prints the approval commands to run:\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\nbash setup-tg-reader.sh\n```\n\n### Manual CLI approval\n\n```bash\nopenclaw approvals allowlist add --gateway \"$(which tg-reader)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-check)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-telethon)\"\n```\n\n### Alternative: approve on first use\n\n1. **Control UI** — open `http:\u002F\u002Flocalhost:18789\u002F`, find the pending approval for `tg-reader`, click **\"Always allow\"**. [Docs](https:\u002F\u002Fdocs.openclaw.ai\u002Fweb\u002Fcontrol-ui)\n2. **Messenger** (Telegram, Slack, Discord) — the bot sends an approval request with an `\u003Cid>`. Reply: `\u002Fapprove \u003Cid> allow-always`. Other options: `allow-once`, `deny`.\n\nThe approval prompt appears in the **Control UI or as a bot message** — not in the agent's conversation. This is a common source of confusion.\n\n---\n\n## When to Use\n\n- User asks to \"check\", \"read\", or \"monitor\" a Telegram channel\n- Wants a digest or summary of recent posts\n- Asks \"what's new in @channel\" or \"summarize last 24h from @channel\"\n- Wants to track or compare multiple channels\n- Wants channel info (title, description, subscribers) — use `tg-reader info`\n\n---\n\n## Quick Start\n\n```bash\n# 1. Run pre-flight diagnostic (fast, no Telegram connection)\ntg-reader-check\n\n# 2. Get channel info\ntg-reader info @channel_name\n\n# 3. Fetch recent posts\ntg-reader fetch @channel_name --since 24h\n```\n\n> **`tg-reader: command not found`?** Run `bash setup-tg-reader.sh` from the skill directory (it will install the package), or manually: `cd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader && pip install .`\n\n---\n\n## Commands\n\n### `tg-reader-check` — Pre-flight Diagnostic\n\n**Always run before fetching.** Fast offline check — no Telegram connection needed.\n\n```bash\ntg-reader-check\ntg-reader-check --config-file \u002Fpath\u002Fto\u002Fconfig.json\ntg-reader-check --session-file \u002Fpath\u002Fto\u002Fsession\n```\n\nReturns JSON with `\"status\": \"ok\"` or `\"status\": \"error\"` plus a `problems` array.\n\nVerifies:\n- Credentials available (env vars or `~\u002F.tg-reader.json`)\n- Session file exists on disk (with size, modification date)\n- At least one MTProto backend installed (Pyrogram or Telethon)\n- Detects stale sessions (config points to older file while a newer one exists)\n\n### `tg-reader info` — Channel Info\n\n```bash\ntg-reader info @channel_name\n```\n\nReturns title, description, subscriber count, and link.\n\n### `tg-reader fetch` — Read Posts\n\n```bash\n# Last 24 hours (default)\ntg-reader fetch @channel_name --since 24h\n\n# Last 7 days, up to 200 posts\ntg-reader fetch @channel_name --since 7d --limit 200\n\n# Multiple channels (fetched sequentially with 10s delay between each)\ntg-reader fetch @channel1 @channel2 @channel3 --since 24h\n\n# Custom delay between channels (seconds)\ntg-reader fetch @channel1 @channel2 @channel3 --since 24h --delay 5\n\n# Fetch posts with comments (single channel only, limit auto-drops to 30)\ntg-reader fetch @channel_name --since 7d --comments\n\n# More comments per post, custom delay between posts\ntg-reader fetch @channel_name --since 24h --comments --comment-limit 20 --comment-delay 5\n\n# Skip posts without text (media-only, no caption)\ntg-reader fetch @channel_name --since 24h --text-only\n\n# Human-readable output\ntg-reader fetch @channel_name --since 24h --format text\n\n# Write output to file instead of stdout (saves tokens)\ntg-reader fetch @channel_name --since 24h --output\ntg-reader fetch @channel_name --since 24h --comments --output comments.json\n\n# Use Telethon instead of Pyrogram (one-time)\ntg-reader fetch @channel_name --since 24h --telethon\n\n# Read unread mode — only fetch new (unread) posts, no --since needed\n# Requires \"read_unread\": true in ~\u002F.tg-reader.json\ntg-reader fetch @channel_name\n\n# Override read_unread mode (fetch everything, don't update state)\ntg-reader fetch @channel_name --since 7d --all\n\n# Custom state file location\ntg-reader fetch @channel_name --since 24h --state-file \u002Fpath\u002Fto\u002Fstate.json\n```\n\n### `tg-reader auth` — First-time Authentication\n\n```bash\ntg-reader auth\n```\n\nCreates a session file. Only needed once.\n\n---\n\n## Read Unread Mode\n\nOnly return new (unread) posts — the skill remembers what you've already seen. Useful for daily digests and monitoring workflows.\n\n### Setup\n\n**Option A — config file** (`~\u002F.tg-reader.json`):\n\n```json\n{\n  \"api_id\": 12345,\n  \"api_hash\": \"...\",\n  \"read_unread\": true\n}\n```\n\n**Option B — env var** (works with `~\u002F.openclaw\u002Fopenclaw.json`):\n\n```bash\nexport TG_READ_UNREAD=true\n```\n\nEnv vars take priority over the config file. This lets you enable read_unread via `openclaw.json` Docker `env` alongside `TG_API_ID`\u002F`TG_API_HASH`.\n\nState is stored in `~\u002F.tg-reader-state.json` (configurable via `\"state_file\"` in config, `TG_STATE_FILE` env var, or `--state-file` flag).\n\n### Behavior\n\n- **`--since` is not needed** when `read_unread` is enabled — the skill automatically returns all unread posts regardless of time\n- **First run** (no prior state for channel): `--since` applies as usual (default 24h); state file created\n- **Subsequent runs:** only posts newer than the last read are returned; `--since` is ignored\n- **`--all` flag:** bypasses read_unread mode — fetches everything by `--since` without updating state (preserves your position)\n- **New channel:** behaves like a first run (no prior state)\n- **No new posts:** state unchanged, `count: 0` returned\n\n### Examples\n\n```bash\n# With read_unread enabled — just fetch, no --since needed\ntg-reader fetch @channel_name\n\n# First run for a new channel — --since determines initial window\ntg-reader fetch @new_channel --since 7d\n\n# Override: fetch everything, don't update tracking state\ntg-reader fetch @channel_name --since 7d --all\n```\n\n### Output\n\nWhen read_unread mode is active, the JSON output includes a `read_unread` field:\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"read_unread\": {\"enabled\": true},\n  \"count\": 5,\n  \"messages\": [...]\n}\n```\n\nWith `--all`: `\"read_unread\": {\"enabled\": true, \"overridden\": true}`\n\n### Limitations\n\n- Tracking is **post-level only** — new comments on already-read posts are not caught\n- If a channel changes its username, tracking resets (state is keyed by username)\n- Concurrent runs for the same channel are safe but last writer wins\n\n### Diagnostic\n\n`tg-reader-check` reports tracking status:\n\n```json\n{\n  \"tracking\": {\n    \"read_unread\": true,\n    \"state_file\": \"~\u002F.tg-reader-state.json\",\n    \"state_file_exists\": true,\n    \"tracked_channels\": 3\n  }\n}\n```\n\n---\n\n## Output Format\n\n### `info`\n\n```json\n{\n  \"id\": -1001234567890,\n  \"title\": \"Channel Name\",\n  \"username\": \"channel_name\",\n  \"description\": \"About this channel...\",\n  \"members_count\": 42000,\n  \"link\": \"https:\u002F\u002Ft.me\u002Fchannel_name\"\n}\n```\n\n### `fetch`\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"fetched_at\": \"2026-02-22T10:00:00Z\",\n  \"since\": \"2026-02-21T10:00:00Z\",\n  \"count\": 12,\n  \"messages\": [\n    {\n      \"id\": 1234,\n      \"date\": \"2026-02-22T09:30:00Z\",\n      \"text\": \"Post content...\",\n      \"views\": 5200,\n      \"forwards\": 34,\n      \"link\": \"https:\u002F\u002Ft.me\u002Fchannel_name\u002F1234\",\n      \"has_media\": true,\n      \"media_type\": \"MessageMediaType.PHOTO\"\n    }\n  ]\n}\n```\n\n### `fetch` with `--comments`\n\n```json\n{\n  \"channel\": \"@channel_name\",\n  \"fetched_at\": \"2026-02-28T10:00:00Z\",\n  \"since\": \"2026-02-27T10:00:00Z\",\n  \"count\": 5,\n  \"comments_enabled\": true,\n  \"comments_available\": true,\n  \"messages\": [\n    {\n      \"id\": 1234,\n      \"text\": \"Post content...\",\n      \"has_media\": false,\n      \"comment_count\": 2,\n      \"comments\": [\n        {\n          \"id\": 5678,\n          \"date\": \"2026-02-28T09:35:00Z\",\n          \"text\": \"Great post!\",\n          \"from_user\": \"username123\"\n        }\n      ]\n    }\n  ]\n}\n```\n\n**Notes:**\n- `comments_available: false` — channel has no linked discussion group (no comments possible)\n- `comments_error` on a message — rate limit hit for that post's comments\n- `from_user` may be `null` for anonymous comments\n- Images\u002Fvideos in comments are **not analyzed** — only text is captured\n- Default post limit drops to 30 when `--comments` is active (override with `--limit`)\n\n---\n\n## After Fetching\n\n1. Parse the JSON output\n2. Posts with images\u002Fvideos have `has_media: true` and a `media_type` field. Their text is in the `text` field (from the caption). **Do not skip posts just because they have media** — they often contain important text.\n3. Images and videos are **not analyzed** (no OCR\u002Fvision) — only the text\u002Fcaption is returned.\n4. Summarize key themes, top posts by views, notable links\n5. If `comments_enabled: true`, analyze comment sentiment and key themes alongside the main posts\n6. Save summary to `memory\u002FYYYY-MM-DD.md` if user wants to track over time\n\n### Saving to File (Token Economy)\n\nUse `--output` when the result is large (especially with `--comments`) and you don't need to analyze it immediately. The full data goes to a file, and stdout returns only a short confirmation — **this saves tokens**.\n\n**Periodic updates pattern:** set up a cron task that runs `tg-reader fetch @channel --comments --output comments.json` on schedule. The file gets updated regularly. When the user asks to analyze comments — read the file instead of re-fetching. This avoids consuming tokens on every fetch.\n\nWhen `--output` is used without a filename, the default is `tg-output.json`. Stdout confirmation:\n```json\n{\"status\": \"ok\", \"output_file\": \"\u002Fabsolute\u002Fpath\u002Fto\u002Ftg-output.json\", \"count\": 12}\n```\n\n### Saving Channel List\n\nStore tracked channels in `TOOLS.md`:\n\n```markdown\n## Telegram Channels\n- @channel1 — why tracked\n- @channel2 — why tracked\n```\n\n---\n\n## Error Handling\n\nErrors include an `error_type` and `action` field to help agents decide what to do automatically.\n\n### Channel Errors\n\n| `error_type` | Meaning | `action` |\n|--------------|---------|----------|\n| `access_denied` | Channel is private, you were kicked, or access is restricted | `remove_from_list_or_rejoin` — ask user if they still have access; if not, remove the channel |\n| `banned` | You are banned from this channel | `remove_from_list` — remove the channel, tell the user |\n| `not_found` | Channel doesn't exist or username is wrong | `check_username` — verify the @username with the user |\n| `invite_expired` | Invite link is expired or invalid | `request_new_invite` — ask user for a new invite link |\n| `flood_wait` | Telegram rate limit | `wait_Ns` — waits ≤ 60 s are retried automatically; longer waits return this error |\n| `comments_multi_channel` | `--comments` used with multiple channels | `remove_extra_channels_or_drop_comments` — use one channel at a time |\n\n### System Errors\n\n| Error | Action |\n|-------|--------|\n| `Session file not found` | Run `tg-reader-check` — use the `suggestion` from output |\n| `Missing credentials` | Guide user through Setup (Step 1-2 below) |\n| `tg-reader: command not found` | Run `bash setup-tg-reader.sh` from the skill directory, or manually: `pip install .` Fallback: `python3 -m tg_reader_unified` |\n| `AUTH_KEY_UNREGISTERED` | Session expired — delete and re-auth (see below) |\n\n### Session Expired\n\n```bash\nrm -f ~\u002F.tg-reader-session.session\ntg-reader auth\n```\n\n### Auth Code Not Arriving\n\nUse the verbose debug script for full MTProto-level logs:\n\n```bash\npython3 debug_auth.py\n```\n\n> **Warning:** `debug_auth.py` deletes existing session files before re-authenticating. It will ask for confirmation first.\n\n---\n\n## Library Selection\n\nTwo MTProto backends are supported:\n\n| Backend | Command | Notes |\n|---------|---------|-------|\n| **Pyrogram** (default) | `tg-reader` or `tg-reader-pyrogram` | Modern, actively maintained |\n| **Telethon** | `tg-reader-telethon` | Alternative if Pyrogram has issues |\n\nSwitch persistently: `export TG_USE_TELETHON=true`\nSwitch one-time: `tg-reader fetch @channel --since 24h --telethon`\n\n---\n\n## Setup & Installation\n\nFull details in [README.md](.\u002FREADME.md).\n\n### Step 1 — Get API Credentials\n\nGo to https:\u002F\u002Fmy.telegram.org → **API Development Tools** → create an app → copy `api_id` and `api_hash`.\n\n### Step 2 — Save Credentials\n\n**Recommended** (works in agents and servers):\n```bash\ncat > ~\u002F.tg-reader.json \u003C\u003C 'EOF'\n{\n  \"api_id\": YOUR_ID,\n  \"api_hash\": \"YOUR_HASH\"\n}\nEOF\nchmod 600 ~\u002F.tg-reader.json\n```\n\n**Alternative** (interactive shell only):\n```bash\nexport TG_API_ID=YOUR_ID\nexport TG_API_HASH=\"YOUR_HASH\"\n```\nSet these in your current shell session. Avoid writing `TG_API_HASH` to shell profiles (`~\u002F.bashrc`) — use `~\u002F.tg-reader.json` instead for persistent storage.\n\n> **Note:** Agents and servers don't load shell profiles. Use `~\u002F.tg-reader.json` (the recommended method above) for non-interactive environments.\n\n### Step 3 — Install & Configure\n\n```bash\nnpx clawhub@latest install sergei-mikhailov-tg-channel-reader\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\nbash setup-tg-reader.sh\n```\n\nThe setup script: installs Python packages (`pip install .`), checks credentials and session, runs `tg-reader-check`, and prints the exec approval commands for you to run manually.\n\nOn Linux with managed Python (Ubuntu\u002FDebian), use a venv **before** running the setup script:\n\n```bash\npython3 -m venv ~\u002F.venv\u002Ftg-reader\necho 'export PATH=\"$HOME\u002F.venv\u002Ftg-reader\u002Fbin:$PATH\"' >> ~\u002F.bashrc && source ~\u002F.bashrc\n```\n\n\u003Cdetails>\n\u003Csummary>Manual install (without setup script)\u003C\u002Fsummary>\n\n```bash\ncd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader\npip install pyrogram tgcrypto telethon && pip install .\nopenclaw approvals allowlist add --gateway \"$(which tg-reader)\"\nopenclaw approvals allowlist add --gateway \"$(which tg-reader-check)\"\n```\n\u003C\u002Fdetails>\n\n### Step 4 — Authenticate\n\n```bash\ntg-reader auth\n```\n\nPyrogram will ask to confirm the phone number — answer `y`. The code arrives in the Telegram app (not SMS).\n\n### Step 5 — Verify\n\n```bash\ntg-reader-check\n```\n\nShould return `\"status\": \"ok\"`. If not — fix the reported issues and re-run `bash setup-tg-reader.sh`.\n\n---\n\n## Scheduled Tasks & Cron\n\nThis skill needs network access (MTProto connection to Telegram servers) and a session file. How you configure OpenClaw cron depends on the session target.\n\n> **Important:** When setting up a scheduled task that uses `tg-reader`, tell the user which approach you're using and what it means — so they can make an informed choice.\n\n### Option A — `sessionTarget: \"main\"` (recommended)\n\nThe cron task sends a **reminder** to the main agent session. The agent then runs `tg-reader` in the main environment where the skill, credentials, and session file are already available.\n\n**Pros:** No extra configuration — everything works out of the box.\n**Cons:** Not fully autonomous — the task sends a system event, the agent picks it up and executes. Requires `payload.kind: \"systemEvent\"` (OpenClaw cron API limitation for main target).\n\n**How to set up:**\n1. Create a cron task with `sessionTarget: \"main\"` and `payload.kind: \"systemEvent\"`\n2. In the task description, include the exact `tg-reader` command to run\n3. The agent receives the reminder and executes the command in its main session\n\n### Option B — `sessionTarget: \"isolated\"` (autonomous, complex setup)\n\nThe cron task runs in a **Docker container** — fully autonomous, no agent interaction needed. However, the container starts empty: no skill, no credentials, no session file.\n\n**Pros:** Fully autonomous — runs on schedule without agent involvement.\n**Cons:** Requires Docker setup; session file must be mounted into the container (may not work reliably — session files are tied to the machine and Telegram may invalidate them in a new environment).\n\n**Required configuration in `~\u002F.openclaw\u002Fopenclaw.json`:**\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"sandbox\": {\n        \"docker\": {\n          \"setupCommand\": \"clawhub install sergei-mikhailov-tg-channel-reader && cd ~\u002F.openclaw\u002Fworkspace\u002Fskills\u002Fsergei-mikhailov-tg-channel-reader && pip install pyrogram tgcrypto telethon && pip install .\",\n          \"env\": {\n            \"TG_API_ID\": \"YOUR_ID\",\n            \"TG_API_HASH\": \"YOUR_HASH\",\n            \"TG_READ_UNREAD\": \"true\"\n          }\n        }\n      }\n    }\n  }\n}\n```\n\n**Session file caveat:** The Telegram session file (`~\u002F.tg-reader-session.session`) must also be available inside the container. This may require Docker volume mounting and might not work reliably — Telegram can invalidate sessions when they appear from a different environment. If you encounter `AUTH_KEY_UNREGISTERED` errors in isolated mode, switch to Option A.\n\n### Explicit paths (both options)\n\nWhen `~\u002F` is not available or points to a different location, use explicit paths:\n\n```bash\ntg-reader-check \\\n  --config-file \u002Fhome\u002Fuser\u002F.tg-reader.json \\\n  --session-file \u002Fhome\u002Fuser\u002F.tg-reader-session\n\ntg-reader fetch @channel --since 6h \\\n  --config-file \u002Fhome\u002Fuser\u002F.tg-reader.json \\\n  --session-file \u002Fhome\u002Fuser\u002F.tg-reader-session\n```\n\nBoth flags work with all subcommands and both backends.\n\n---\n\n## Security\n\n- Session file (`~\u002F.tg-reader-session.session`) grants **full account access** — keep it safe\n- Never share or commit `TG_API_HASH` or session files\n- `TG_API_HASH` is a secret — store in env vars or config file, never in git\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"requires":27,"primaryEnv":30},"📡",{"env":28,"bins":31},[29,30],"TG_API_ID","TG_API_HASH",[32,33],"tg-reader","tg-reader-check","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fbzsega\u002Fsergei-mikhailov-tg-channel-reader",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":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill sergei-mikhailov-tg-channel-reader",{"tool":49,"command":50},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill sergei-mikhailov-tg-channel-reader",{"tool":52,"command":53},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill sergei-mikhailov-tg-channel-reader","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbzsega\u002Fsergei-mikhailov-tg-channel-reader\u002FSKILL.md",true,[],[58,66,73,80,87,94],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":65},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":65},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":65},"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":65},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":65},"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",[],[]]