voice-call
Start voice calls via the OpenClaw voice-call plugin.
70
56%
Does it follow best practices?
Impact
100%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/voice-call/SKILL.mdQuality
Discovery
40%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 extremely brief and identifies a narrow, distinctive capability (starting voice calls via a specific plugin), which helps with distinctiveness. However, it lacks a 'Use when...' clause, provides minimal detail on what actions are supported, and misses common natural language trigger terms users might employ when requesting voice call functionality.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to make a call, dial a number, start a voice conversation, or mentions OpenClaw.'
Include common natural language variations users might say, such as 'phone call', 'dial', 'ring someone', 'make a call', 'call someone'.
Expand the capability description to cover additional actions if applicable, e.g., 'Start, manage, and end voice calls via the OpenClaw voice-call plugin.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (voice calls) and one action (start), but lacks detail on additional capabilities like ending calls, transferring, managing call settings, etc. It mentions the specific plugin name 'OpenClaw' which adds some specificity. | 2 / 3 |
Completeness | Describes what it does (start voice calls) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also quite thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'voice calls' and 'OpenClaw' as keywords, but misses common variations users might say like 'phone call', 'dial', 'ring', 'call someone', or 'make a call'. Coverage of natural trigger terms is limited. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'OpenClaw voice-call plugin' creates a very distinct niche. It's unlikely to conflict with other skills due to the specific plugin name and the narrow domain of initiating voice calls. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise and well-structured skill that efficiently communicates the voice-call plugin interface. Its main weakness is the lack of concrete tool invocation examples and a sequenced workflow showing a typical call lifecycle (initiate → check status → speak → end), which would make it more actionable for Claude.
Suggestions
Add a concrete tool call example showing a full `voice_call` invocation with the `initiate_call` action and its parameters, so Claude can copy the pattern directly.
Add a brief workflow sequence showing a typical call lifecycle (e.g., 1. initiate_call → 2. get_status to confirm connected → 3. speak_to_user → 4. end_call) to clarify the expected multi-step usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what voice calls are or how Twilio works. Configuration is presented as terse bullet points. The skill assumes Claude knows these providers and focuses only on the specific tool/CLI interface. | 3 / 3 |
Actionability | The CLI examples are concrete and copy-paste ready, and the tool actions list parameters clearly. However, the tool usage lacks concrete examples showing how to actually invoke the `voice_call` tool with specific parameters (e.g., a full tool call example with JSON), and the config notes describe structure without showing a concrete config snippet. | 2 / 3 |
Workflow Clarity | The actions are listed but there's no explicit workflow showing the sequence of a typical call (initiate → speak → end), nor any validation/error handling guidance. For a multi-step process like managing a voice call lifecycle, a sequenced workflow with status checks would improve clarity. | 2 / 3 |
Progressive Disclosure | This is a simple, single-purpose skill under 50 lines. The content is well-organized into CLI and Tool sections with clear subsections for actions and configuration notes. No bundle files exist, and none are needed for this scope. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- qsimeon/openclaw-engaging
- Commit
4467e04
- Reviewed
Table of Contents
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.