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 ./openclaw/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 clear niche (OpenClaw voice-call plugin), which makes it distinctive. However, it lacks a 'Use when...' clause, lists only a single action ('start'), and misses natural trigger term variations users might employ when requesting voice calls.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to make a call, dial a number, start a phone call, or initiate a voice conversation.'
Include natural trigger term variations such as 'phone call', 'dial', 'ring', 'call someone', 'make a call' to improve matching.
Expand the capability list beyond 'start' — mention any other supported actions like ending calls, transferring, or checking call status if applicable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (voice calls) and one action (start), but does not list multiple concrete actions or elaborate on capabilities beyond 'start voice calls'. | 2 / 3 |
Completeness | Describes what it does (start voice calls) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also quite thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'voice calls' and 'OpenClaw' as relevant keywords, but misses common variations users might say such as 'phone call', 'dial', 'ring', 'call someone', or 'make a call'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'OpenClaw voice-call plugin' creates a very specific niche that is unlikely to conflict with other skills; the combination of the plugin name and 'voice calls' is highly 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 interface. Its main weaknesses are the lack of concrete tool invocation examples (showing actual tool call syntax) and the absence of a sequenced workflow for the call lifecycle with validation steps like checking status after initiation.
Suggestions
Add a concrete tool call example showing the full invocation syntax for `initiate_call` (e.g., with actual parameter values), so Claude knows exactly how to use the tool.
Add a brief workflow sequence showing the typical call lifecycle: initiate → check status → speak/continue → end, with a note to verify status before proceeding.
| 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 payload), 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 checkpoints (e.g., check status after initiate before continuing) would be valuable. | 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). The structure is appropriate for the scope and doesn't need external references. | 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
- trpc-group/trpc-agent-go
- Commit
9f4b734
- 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.