phone

Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill body: complete request/response examples, explicit error-recovery loops, and clear sequencing for both lookup and calling workflows. The main improvement opportunities are trimming the agentic-flow examples, isolating the time-sensitive verification date, and splitting the API reference detail into reference files for better progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and gateway-specific (endpoints, payloads, error codes) and assumes Claude's competence — it never explains what Twilio, SIM swap, or E.164 are. It falls short of 5 because the "Example Agentic Flows" and "Notes" sections have some padding, and a raw verification date ("verified 2026-09-05") is time-sensitive info embedded inline rather than isolated in a deprecated/old-patterns section.	4 / 5
Actionability	Every section is copy-paste ready: exact localhost endpoints, complete JSON request/response bodies, a CLI transcript, a parameter table with defaults and presets, tool-call names with arguments, and specific error-handling guidance (402 → check /health authMode → fund wallet or top up credits). This fully matches the anchor-5 'copy-paste ready, covers common cases' example.	5 / 5
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints: fire-and-forget call → poll every 10–30s → status progression queued/in_progress/completed/failed; fraud check required before sensitive SMS; renew before lease expiry; from auto-pick rules with 403/400 recovery paths (retry with explicit from, or buy via buy_endpoint). Destructive/costly operations (voice call, release, buy) each carry explicit user-confirmation warnings, so no cap applies.	5 / 5
Progressive Disclosure	Sections are well-organized and self-contained with no nested or dangling references, which is good structure. It does not reach 5 because the skill is ~185 lines with everything inlined — material like the voice preset list, the full parameter/error reference, and the example flows are plausible candidates for one-level-deep reference files rather than the main SKILL.md.	4 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what and when clauses, third-person voice, natural trigger phrases, and concrete named capabilities. The only improvements are slightly broader action coverage (renew/release, call status) and a few more colloquial trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Verify phone numbers (carrier + SIM-swap fraud signals)" and "place AI-powered outbound voice calls" name the domain plus several concrete actions (look up, check fraud risk, buy/rent a number, place a call). It stays at 4 rather than 5 because wallet-number lifecycle actions (list, renew, release) and call status polling are absent, leaving minor coverage gaps.	4 / 5
Completeness	The 'what' is explicit ("Verify phone numbers... and place AI-powered outbound voice calls via BlockRun's gateway") and the 'when' is explicit with concrete trigger phrases ("Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call"), matching the anchor-5 example pattern. Third person voice is used throughout.	5 / 5
Trigger Term Quality	Natural user phrasings like "look up a number", "check fraud risk", "buy/rent a phone number", and "place an AI voice call" are exactly what a user would say. Not 5 because common variations such as "call my client", "caller ID", or "SIM swap check" as a bare phrase are not covered within the description itself.	4 / 5
Distinctiveness Conflict Risk	The niche (carrier/fraud verification plus AI outbound calling through a specific paid gateway) is distinct with service-specific names (BlockRun, Twilio, Bland.ai, x402). Not 5 because generic phrases like "place an AI voice call" or "buy/rent a phone number" could also match a broader telephony or Twilio-administration skill.	4 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BlockRunAI/ClawRouter
Path: skills/phone/SKILL.md
Commit: 14d20ac

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.