add-tavily-tool

Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.

Quality

83%

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

Quality

Content

78%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 well-structured, highly actionable install runbook with clear phases and concrete commands. Its main weakness is progressive disclosure: three referenced bundle files (upgrade-instructions.md, REMOVE.md, tavily-manifest.test.ts) are not present in the bundle, leaving broken links.

Suggestions

Ship the missing bundle files referenced by the body — upgrade-instructions.md, REMOVE.md, and tavily-manifest.test.ts (expected under .claude/skills/add-tavily-tool/) — so the one-level-deep links resolve.

Weave a brief 'if this fails, fix X then re-run Y' note into Phase 2 (guard) and Phase 4 (verify) so the validation feedback loops are inline rather than only in Troubleshooting.

Trim the provider-agnostic rationale paragraph in the intro to the one sentence that affects when to apply the skill, to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly lean and purpose-built with copy-paste commands and brief, NanoClaw-specific rationale rather than generic concept explanations; a few explanatory asides (e.g. the provider-agnostic paragraph) could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout (ncl groups config add-mcp-server with complete args, build.sh, vitest, docker inspect, curl), covering the common install and verification cases concretely.	5 / 5
Workflow Clarity	Clear five-phase sequence with explicit checkpoints (Phase 2 build+guard, Phase 4 verify) and a Phase 5 checklist, but the fix→retry feedback loops live in the separate Troubleshooting section rather than inline in each phase, a minor gap versus a 5.	4 / 5
Progressive Disclosure	The body is well-sectioned and signals one-level-deep references (REMOVE.md, upgrade-instructions.md), but those referenced bundle files do not exist in the bundle and tavily-manifest.test.ts is also absent, so the navigated paths are dead links rather than working progressive disclosure.	3 / 5
	Total	16 / 20 Passed

Description

87%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 tight, third-person description that clearly states both what the skill does and when to use it, with concrete trigger terms and a distinct niche. It is specific and well-targeted, with only minor room to enumerate more granular actions or synonyms.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Add Tavily Search and Extract as keyless remote MCP tools') with the specific install mechanism, listing two named tools; slightly below a 5 because it is essentially one install action across two tools rather than a comprehensive list of actions.	4 / 5
Completeness	Explicitly states what it does ('Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups') and when to use it ('Use when installing Tavily web search or URL extraction without an API key'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('Tavily web search', 'URL extraction', 'without an API key'); a few common synonyms (e.g. 'scrape', 'fetch URL content') are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche (Tavily, keyless remote MCP, NanoClaw agent groups) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: 2 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-tavily-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.