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 identifies a clear and distinct capability (starting voice calls via a specific plugin) but is too terse to be effective for skill selection. It lacks a 'Use when...' clause, provides only a single action, and misses common trigger term variations that users might naturally use.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to make a call, dial a number, phone someone, or initiate a voice conversation.'
Expand the capability list beyond just 'start' — mention any other supported actions like ending calls, transferring, adjusting settings, or checking call status if applicable.
Include natural language trigger variations such as 'phone call', 'dial', 'ring', 'call someone', 'make a call' to improve matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (voice calls) and one action (start), but doesn't list multiple concrete actions or elaborate on capabilities beyond initiating calls. | 2 / 3 |
Completeness | Describes what it does (start voice calls) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also quite thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'voice calls' and 'voice-call' which are relevant keywords, but misses common variations like 'phone call', 'dial', 'call someone', 'make a call', or 'ring'. | 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; voice calling via a named plugin is quite distinct. | 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 weaknesses are the lack of executable tool-call examples (only parameter signatures are listed) and the absence of an explicit workflow sequence with error handling for what is an external, potentially costly operation (making real phone calls).
Suggestions
Add a concrete tool-call example showing a full initiate_call → get_status → end_call sequence with actual parameter values.
Document the expected workflow sequence explicitly (e.g., '1. initiate_call → 2. check status → 3. speak/continue → 4. end_call') with guidance on error handling (e.g., what happens if the call fails to connect).
Specify what values the optional 'mode' parameter accepts and what the defaults are for optional parameters like 'to'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose—CLI examples, tool actions, and config notes are all lean with no unnecessary explanation of what voice calls are or how Twilio works. Claude's intelligence is respected throughout. | 3 / 3 |
Actionability | CLI commands are concrete and copy-paste ready, but the tool actions list only parameter names without executable examples showing how to invoke them (e.g., no example tool call with full parameters). Key details like what 'mode' accepts or default values for optional params are missing. | 2 / 3 |
Workflow Clarity | The actions imply a multi-step workflow (initiate → continue/speak → end), but the sequence is not explicitly stated and there's no guidance on checking status between steps or handling errors (e.g., what to do if initiate_call fails). For a potentially destructive/external operation like making phone calls, validation checkpoints are missing. | 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 walls of text. 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
- trpc-group/trpc-agent-go
- Commit
af8bd5f
- 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.