agentphone
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.
63
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/agentphone/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies the domain (AgentPhone API / telephony), lists specific concrete actions, includes a comprehensive 'Use when' clause with natural trigger terms, and occupies a distinct niche. It follows the recommended pattern closely and uses third-person voice appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, check usage. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Build AI phone agents with AgentPhone API' plus the list of capabilities) and when ('Use when the user wants to...' with explicit trigger scenarios and a catch-all 'anything related to telephony, phone numbers, or voice AI'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'phone calls', 'SMS', 'phone numbers', 'voice agents', 'webhooks', 'telephony', 'voice AI'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — telephony, phone agents, and voice AI are specific domains unlikely to overlap with other skills. The mention of 'AgentPhone API' further narrows the scope. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent executable examples and clear workflow sequencing, but it is severely over-long and monolithic. It tries to be both a quick-start guide and a complete API reference in a single file, resulting in massive token consumption. The content would benefit enormously from splitting the API reference, webhook examples, and troubleshooting into separate bundle files, keeping SKILL.md as a concise overview with pointers.
Suggestions
Extract the full API reference (Agents, Phone Numbers, Calls, Messages, Webhooks sections) into a separate API_REFERENCE.md file and link to it from SKILL.md
Move the 4 complete webhook handler examples (streaming Python/Node.js, tool-calling Python/Node.js) into a WEBHOOK_EXAMPLES.md file, keeping only one minimal example inline
Remove the 'Ideas: What You Can Build' section entirely — Claude can infer use cases from the API capabilities
Remove the troubleshooting section or move it to a TROUBLESHOOTING.md file, and trim explanatory prose throughout (e.g., 'Voice calls are real-time conversations through your agent's phone numbers' is unnecessary context)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~800+ lines. It includes extensive API reference documentation that belongs in external docs, full webhook handler examples in multiple languages (Python and Node.js) duplicated for multiple patterns, a lengthy troubleshooting section, an 'Ideas' section explaining use cases Claude can infer, and explanatory prose throughout. Much of this is reference material that should be linked rather than inlined. | 1 / 3 |
Actionability | The skill provides fully executable curl commands, complete code examples in Python and Node.js, specific request/response JSON schemas, and detailed parameter tables. Every API endpoint has copy-paste ready examples with realistic payloads and responses. | 3 / 3 |
Workflow Clarity | The Quick Start provides a clear 5-step sequence (get API key → create agent → buy number → make call → check transcript). The voice call flows are well-documented with explicit steps. Destructive actions (releasing numbers, deleting agents) have clear warnings and confirmation requirements. The webhook streaming pattern includes explicit validation (interim chunks to prevent silence). | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to offload content to. The entire API reference, multiple full webhook handler examples in two languages, troubleshooting guides, voice capability tables, and use case ideas are all inlined in a single file. The API reference alone could be a separate file, and the webhook examples (4 complete implementations) should be in separate reference files. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1389 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
22710e9
- 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.