BB telegram-compose
Format and deliver rich Telegram messages with HTML formatting via direct Telegram API. Auto-invoked by the main session for substantive Telegram output — no other skills need to call it. Decision rule: If your Telegram reply is >3 lines or contains structured data (lists, stats, sections, reports), spawn this as a Haiku sub-agent to format and send. Short replies (<3 lines) go directly via OpenClaw message tool. Handles: research summaries, alerts, status updates, reports, briefings, notifications — anything with visual hierarchy.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Exfiltration
exfil-webhook-urlSKILL.md:112Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \placeholder -
low Exfiltration
net-credential-useSKILL.md:112Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \vendor-host -
low Exfiltration
exfil-webhook-urlSKILL.md:125Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \placeholder -
low Exfiltration
net-credential-useSKILL.md:125Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -s -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \vendor-host
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "model-preference" - note
frontmatter-keyunknown frontmatter key "subagent"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 31 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2093 tokens
- 100Progress reporting. Reports progress
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +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
- +3Description length 537: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.