Skip to content

nanocoai/nanoclaw / .claude/skills/add-telegram

add-telegram

Verified

Add Telegram channel integration via Chat SDK.

FileKindSize
REMOVE.mdmarkdown1.3 KB
SKILL.mdskill md16.1 KB
apply-fixtures.jsonconfig2.3 KB

apply-fixtures.json

View on GitHub
{
  "notes": "Conformance fixtures for scripts/skill-conformance.test.ts: shaped fake values only, never real credentials. Two scenarios: a first install (the TELEGRAM_BOT_TOKEN probe answers 'no', add_another derives to 'no', the first-bot steps run, the default pairing step runs) and a rerun that adds a second bot (the probe answers 'yes', add_another derives to 'ask' and the prompt answers yes, name mega, a second token; the getMe stubs answer both bot_username captures with different usernames so the same-bot check passes, the tr/echo stubs answer bot_name_env and instance, the set-env writes are effect:step and need no stdout). stepFields feed every effect:step's terminal block (the pairing step's capture:platform_id=PLATFORM_ID,owner_handle=ADMIN_USER_ID).",
  "coverageExclude": [
    "add_another=ask"
  ],
  "coverageExcludeReason": "add_another=ask is the probe's rerun answer that only gates the add_another prompt, which re-binds the same var to yes or no before the run ends, so no scenario can finish with vars.add_another='ask'. The add-another scenario exercises the guard at runtime (its prompt only runs under it).",
  "scenarios": [
    {
      "name": "pairing",
      "inputs": {
        "bot_token": "123456789:AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
      },
      "exec": [
        { "match": "^TELEGRAM_BOT_TOKEN=.+' .env", "stdout": "no" },
        { "match": "echo ask || echo no", "stdout": "no" },
        { "match": "getMe", "stdout": "nanoclaw_bot" }
      ],
      "stepFields": { "PLATFORM_ID": "telegram:123456789", "ADMIN_USER_ID": "987654321" }
    },
    {
      "name": "add-another",
      "inputs": {
        "bot_token": "123456789:AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA",
        "add_another": "yes",
        "bot_name": "mega",
        "bot_token_2": "987654321:BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB"
      },
      "exec": [
        { "match": "^TELEGRAM_BOT_TOKEN=.+' .env", "stdout": "yes" },
        { "match": "echo ask || echo no", "stdout": "ask" },
        { "match": "bot123456789:AAAA", "stdout": "nanoclaw_bot" },
        { "match": "bot987654321:BBBB", "stdout": "mega_bot" },
        { "match": "tr 'a-z-' 'A-Z_'", "stdout": "MEGA" },
        { "match": "echo telegram-", "stdout": "telegram-mega" }
      ],
      "stepFields": { "PLATFORM_ID": "telegram:123456789", "ADMIN_USER_ID": "987654321", "INSTANCE": "telegram-mega" }
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall