AC telegram-autopilot
Manage a Telegram userbot autopilot that responds to private messages as the user using AI. Use when the user wants to set up auto-replies on their personal Telegram account, manage allowed contacts, configure AI response style, or send messages/media as themselves. Triggers on "telegram autopilot", "auto reply telegram", "manage my telegram", "respond for me", "telegram userbot", "paid media telegram". Requires secrets — Telegram API credentials (api_id, api_hash), phone number, optional 2FA password, AI provider API key (Anthropic or OpenAI-compatible), optional Telegram bot token for owner notifications.
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
exfil-webhook-urlscripts/autopilot.py:44Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{token}/sendMessage"vendor-hostquoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 30 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1171 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 614: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.