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 very brief and identifies a narrow, distinct capability (starting voice calls via a specific plugin), which helps with distinctiveness. However, it lacks a 'Use when...' clause, covers only a single action, and misses common trigger term variations that users might naturally use when requesting voice call functionality.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to make a phone call, dial a number, or initiate a voice conversation.'
Include common natural language variations as trigger terms: 'phone call', 'dial', 'ring', 'call someone', 'make a call', 'voice chat'.
Expand the capability description to cover additional actions if applicable, such as managing call settings, ending calls, or transferring calls.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (voice calls) and one action (start), but only describes a single action. It mentions the specific plugin name 'OpenClaw voice-call plugin' which adds some specificity, but lacks detail on what starting a call entails or additional capabilities. | 2 / 3 |
Completeness | It answers 'what' (start voice calls) but has no explicit 'when' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also minimal, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'voice calls' which is a natural term users might say, and 'OpenClaw' for users who know the plugin. However, it misses common variations like 'phone call', 'dial', 'ring', 'call someone', or 'make a call'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'voice calls' and the specific 'OpenClaw voice-call plugin' name creates a clear niche that is unlikely to conflict with other skills. Voice calling is a distinct domain. | 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.
This is a concise, well-structured skill that efficiently communicates the voice-call plugin's interface. Its main weakness is the lack of concrete tool invocation examples and an explicit call lifecycle workflow. The provider configuration notes are a useful addition that avoids over-explanation.
Suggestions
Add a concrete tool invocation example showing the full call to `voice_call` with `initiate_call` action including example parameters and expected response shape.
Add an explicit workflow sequence for the call lifecycle (e.g., 1. initiate_call → 2. get_status to confirm connected → 3. speak_to_user/continue_call → 4. end_call) to clarify the expected multi-step process.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose—CLI examples, tool actions with parameters, and provider config are all essential information Claude wouldn't inherently know. No unnecessary explanations of what voice calls are or how Twilio works. | 3 / 3 |
Actionability | CLI commands are concrete and copy-paste ready, but the tool actions list only parameter names without showing actual tool invocation syntax or example payloads. A concrete example of calling `voice_call` with `initiate_call` action would make this fully actionable. | 2 / 3 |
Workflow Clarity | The actions imply a workflow (initiate → continue/speak → end), but the sequence is not explicitly stated. For a multi-step process like managing a voice call lifecycle, an explicit sequence with validation (e.g., check status after initiation) would improve clarity. | 2 / 3 |
Progressive Disclosure | For a simple, focused skill under 50 lines, the content is well-organized into clear sections (CLI, Tool, Notes) with no unnecessary nesting or monolithic blocks. No external references are needed given the 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.