add-dial-tool

Give chosen NanoClaw agents a real phone number as a container tool — the `dial` CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial channel; idempotent; re-run to change which agents may use it. Use when the user wants agents to text, call, or run `dial …` from a chat, without wiring Dial as a messaging channel.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced procedural skill with strong validation and error-recovery guidance for a risky operation. Its main weakness is progressive disclosure: the REMOVE.md reference is broken and no supporting bundle files exist.

Suggestions

Create the referenced REMOVE.md (or remove the link) so the one external reference resolves — currently it points at a missing file.

Consider moving the Troubleshooting section and the long block-rule/credential shell one-liners into a references/ file that SKILL.md points to, reducing body length while keeping the procedural spine inline.

Add a short 'What this skill does / does not do' summary near the top so the overview is scannable before the directive-heavy steps begin.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence about NanoClaw/OneCLI/ncl; the prose present is mostly non-obvious domain rationale (vault semantics, block-rule naming) rather than generic padding, though a few explanatory passages could still be trimmed.	4 / 5
Actionability	Fully executable throughout: concrete shell commands with real flags and jq pipelines, directive fences with variable substitution, and copy-paste-ready examples covering the common install/sign-in/scope cases.	5 / 5
Workflow Clarity	Clear multi-step sequence with explicit validation checkpoints (`effect:check`, `validate:` regexes, signed_in branching) and feedback loops (stop-and-retry on pre-flight failure, a full Troubleshooting section) — appropriate for a money-spending, real-people-reaching operation.	5 / 5
Progressive Disclosure	Well-sectioned structure with a clearly signaled one-level reference to REMOVE.md, but no bundle files exist and the referenced REMOVE.md is missing (broken link), and most detail (troubleshooting, credential logic) is inlined rather than offloaded.	3 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that clearly states what the tool does and when to use it, with explicit trigger phrases and a clear distinction from the related Dial channel skill. Written in third person with no fluff.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'send SMS, place AI voice calls, and receive verification codes', plus 'the `dial` CLI baked into the agent image plus OneCLI credential injection' — giving comprehensive coverage of what the tool does.	5 / 5
Completeness	Explicitly answers both 'what' (installs the dial CLI + OneCLI credential injection, scoped per agent) and 'when' ('Use when the user wants agents to text, call, or run `dial …` from a chat, without wiring Dial as a messaging channel').	5 / 5
Trigger Term Quality	Good natural-term coverage ('text, call', 'SMS', 'voice calls', 'verification codes', 'run `dial …`') that users would actually say; a few synonyms or phrasings are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche — explicitly 'Independent of the Dial channel' and contrasted with `/add-dial` — with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-dial-tool/SKILL.md
Commit: 7902716

Reviewed: 1 day 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.