AB esimpal-api-agent
Use when building or debugging an agent (e.g. Telegram/WhatsApp bot, AI assistant) that integrates with the eSIMPal API to buy eSIMs for end-users, create orders, and deliver activation links, QR codes, or manual-install details.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
IntegrationTelegramWhatsAppSoftware developmentAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "required_credentials" - note
frontmatter-keyunknown frontmatter key "primary_credential_env" - note
frontmatter-keyunknown frontmatter key "required_env_vars" - note
frontmatter-keyunknown frontmatter key "primaryEnv" - note
frontmatter-keyunknown frontmatter key "credentials" - note
frontmatter-keyunknown frontmatter key "approval_required_for" - note
frontmatter-keyunknown frontmatter key "autonomous_execution"
Process rating: all ten parameters 73/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 23 mutating operations with no state check
- 40Consistency. Frontmatter name (esimpal-api-agent) differs from the folder (esimpal-api)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 62 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 6 branches, has a failure section
- 100Execution cost. Instruction body is 3070 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 229: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: clean
This is an instruction-only eSIMPal integration skill that discloses its API key use and requires user approval before purchases, payments, or activations.
LLM: benign (high) · VirusTotal: · 29 May 2026