voice-call

Start voice calls via the OpenClaw voice-call plugin.

1.17x

Quality

76%

Does it follow best practices?

Impact

100%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/voice-call/SKILL.md

The canonical home for this skill is voice-call in openclaw/openclaw

Quality

Content

100%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.

The body is an exemplary lean skill: executable CLI examples, a concrete tool action API, and dense provider-config notes with zero filler. It fully leverages Claude's existing knowledge and adds only plugin-specific facts.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — no explanation of concepts Claude already knows, no padding; every line is a concrete command, action signature, or config fact that earns its place.	5 / 5
Actionability	The CLI section is copy-paste ready ("openclaw voicecall call --to \"+15555550123\" --message \"Hello from OpenClaw\"") and the tool section lists exact action names with parameter signatures, covering the common initiate-and-check-status cases.	5 / 5
Workflow Clarity	This is a simple single-task skill and the action is unambiguous: concrete CLI commands plus tool actions, with a clear rule for choosing between them ("Use `voice_call` for agent-initiated calls"). No destructive or batch operations, so no validation cap applies.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ exist and none are required), and the content is organized into clear CLI, Tool, and Notes sections — the simple-skill exception for a full score applies.	5 / 5
	Total	20 / 20 Passed

Description

53%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.

The description is short, third-person, and names a concrete action, but it is minimal: only one capability is mentioned and there is no 'when to use' trigger guidance at all. It reads more like a label than a trigger-rich description.

Suggestions

Add a 'when' clause, e.g. "Use when the user asks to make a phone call, place a voice call, or check on a running call."

Mention the other concrete capability from the body — inspecting call status — so the 'what' is more comprehensive: e.g. "Start or inspect voice calls...".

Include natural trigger synonyms such as "phone call" or "dial" so the skill surfaces when users phrase the request differently.

Dimension	Reasoning	Score
Specificity	"Start voice calls" names the domain and one concrete action, but the description stops there — it omits inspecting call status and provider setup that the skill actually supports, so coverage is not comprehensive enough for 4.	3 / 5
Completeness	The 'what' is clear ("Start voice calls via the OpenClaw voice-call plugin"), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"voice calls" is a natural phrase users would say, but common variations and synonyms ("phone call", "make a call", "dial") are missing, matching the anchor for some relevant keywords without common variations.	3 / 5
Distinctiveness Conflict Risk	"voice calls" is a fairly distinct niche with the plugin name adding specificity, but there is minor overlap risk with closely related telephony/messaging skills and no trigger phrases to sharpen the boundary, so it falls short of a 5.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/voice-call/SKILL.md
Commit: 9bb1c42

Reviewed: 5 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.