BB telegram
Telegram Bot API integration with managed authentication. Send messages, manage chats, handle updates, and interact with users through your Telegram bot. Use this skill when users want to send messages, create polls, manage bot commands, or interact with Telegram chats. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every `/telegram/` path goes to the Telegram Bot API and nowhere else; the methods documented here are the ones this skill uses, and the passthrough can also call other Bot API methods the bot token allows. Default to read calls, and confirm every send, edit, delete, or new connection with the user.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Grep Glob
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7339 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 52 mutating operations with no state check
- 40Consistency. Frontmatter name (telegram) differs from the folder (telegram-api)
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7339 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 54 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 793: enough signal without eating the budget
- +4Structure: 75 headings
- +3Step-by-step instructions: 54 items
- +3Output format is stated explicitly
- +4Has examples (62 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.