phone-call

Place outbound AI phone calls via Bland AI: book reservations, make appointments, ask businesses questions, then report back the transcript and summary.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/integrations/phone-call/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with complete executable signatures, a clear sequenced workflow with validation checkpoints, and clean progressive disclosure into real bundle scripts. The main weakness is minor redundancy in the approval-card guidance.

Suggestions

Deduplicate the "never ask for confirmation in chat / the Approve-Deny card is the confirmation" rule, which currently appears in Workflow step 2, Rules #1, and the step description — state it once and cross-reference.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basic concepts, but the approval-card / "never ask for confirmation in chat" guidance is repeated across Workflow step 2, the Rules section, and step wording, so it could be tightened.	2 / 3
Actionability	Every script has a complete, copy-paste-ready skill_run signature with required/optional args, defaults, and return shapes, plus a concrete task-prompt example, matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clear 5-step sequence is given with explicit checkpoints: the Approve/Deny card before placing a call, and the check-call retry loop (repeat until completed: true) for error recovery, satisfying the validation-checkpoints anchor.	3 / 3
Progressive Disclosure	The body is an overview with one-level-deep references to five real bundle scripts (place-call, check-call, stop-call, analyze-call, call-watch), all of which exist in ./scripts/, matching the well-signaled one-level-deep-references anchor.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and clearly distinct, but it states what the skill does without an explicit "when to use it" trigger clause, which caps completeness. Trigger terms are natural but lack synonym variation.

Suggestions

Add an explicit trigger clause such as "Use when the user wants an AI agent to phone a business to book, schedule, or ask questions" to satisfy the completeness 'when' requirement.

Include natural synonym variations of the core term (e.g., "call", "dial", "ring a business") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "book reservations, make appointments, ask businesses questions, then report back the transcript and summary" — matching the multiple-specific-actions anchor rather than the single-domain score-2 anchor.	3 / 3
Completeness	The "what" is explicit (place outbound AI calls and report transcript/summary), but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2 (when is only implied).	2 / 3
Trigger Term Quality	Natural action phrases like "book reservations" and "make appointments" appear, but the core domain term "phone calls" has no common variations (call, dial) and there is no explicit trigger framing, matching the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	"Place outbound AI phone calls via Bland AI" carves a clear, narrow niche with distinct triggers unlikely to overlap with other skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: Open-Curiosity/gini-agent
Path: skills/integrations/phone-call/SKILL.md
Commit: 6c5d85e

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.