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 specific plugin and action but lacks comprehensiveness in both capabilities listed and trigger guidance. The absence of a 'Use when...' clause is a significant gap that would make it harder for Claude to know when to select this skill. The specificity of the OpenClaw plugin name does help with distinctiveness.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'Use when the user wants to make a phone call, dial someone, start a voice conversation, or mentions OpenClaw.'
Expand the capability description to cover more actions if applicable, such as 'Start, manage, and end voice calls via the OpenClaw voice-call plugin.'
Include common user phrasings and synonyms like 'phone call', 'dial', 'ring', 'call someone' to improve trigger term coverage.
| 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 | It answers 'what' (start voice calls via OpenClaw) but completely lacks a 'when should Claude use it' clause. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also minimal, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'voice calls' and 'voice-call' as natural keywords, plus the specific plugin name 'OpenClaw'. However, it misses common variations users might say 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' creates a clear niche that is unlikely to conflict with other skills. Voice calling via a named plugin is quite distinctive. | 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 capabilities. Its main weakness is the lack of concrete tool invocation examples and a sequenced workflow showing a typical call lifecycle with status checking. The config notes are a nice touch for provider setup.
Suggestions
Add a concrete example of a tool invocation (e.g., showing the full parameters for `initiate_call` and a follow-up `get_status` check) to improve actionability.
Add a brief workflow sequence showing a typical call lifecycle: initiate_call → get_status to confirm connected → speak_to_user → end_call, with guidance on checking status before proceeding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what voice calls are or how Twilio works. The config notes are terse but informative, listing only what Claude needs to know to configure each provider. | 3 / 3 |
Actionability | The CLI commands are concrete and copy-paste ready, but the tool actions lack executable examples showing how to actually invoke them (e.g., a JSON tool call or code snippet). The parameter descriptions use '?' notation without explaining what defaults apply or what the parameters accept. | 2 / 3 |
Workflow Clarity | The actions are listed but there's no sequenced workflow showing a typical call lifecycle (initiate → speak → end) or any validation/error handling guidance. For a multi-step process like managing a voice call, explicit sequencing with status checks would improve clarity. | 2 / 3 |
Progressive Disclosure | For a simple, focused skill under 50 lines with no bundle files, the content is well-organized into clear sections (CLI, Tool, Notes) that are easy to scan. No need for external references 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
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.