add-provider

Guide for adding new AI providers to ClaudeBar using TDD patterns. Use this skill when: (1) Adding a new AI assistant provider (like Antigravity, Cursor, etc.) (2) Creating a usage probe for a CLI tool or local API (3) Following TDD to implement provider integration (4) User asks "how do I add a new provider" or "create a provider for X"

Quality

85%

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

82%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-structured TDD workflow skill with executable templates and real, clearly signaled reference files. It is efficient but could push more of the full implementation detail into references to tighten the SKILL.md body and add explicit inter-phase validation checkpoints.

Suggestions

Add an explicit validation checkpoint between phases (e.g., 'Run parsing tests; only proceed to Phase 2 when green') to strengthen the workflow feedback loop.

Move the complete Provider and Probe implementation templates into the antigravity-example reference and keep only the skeleton/contract inline in SKILL.md to improve token efficiency and progressive disclosure.

Tighten or relocate the ISP sub-protocol section detail to a reference, since it is only needed for providers with special config.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code templates and structural tables with little padding of concepts Claude already knows; a few inline templates (e.g., full Provider class) could be trimmed or moved to the reference, but it is largely efficient.	4 / 5
Actionability	Provides copy-paste-ready Swift templates with explicit file paths for tests, probe, provider, registration, and theming, covering the common end-to-end cases concretely.	5 / 5
Workflow Clarity	Five clearly sequenced TDD phases labeled Red → Green plus a final checklist (including 'All 300+ existing tests still pass') provide a clear sequence with verification; minor gaps exist as no explicit 'run tests before proceeding' checkpoint sits between phases.	4 / 5
Progressive Disclosure	Good structure with one-level-deep, well-signaled references to real bundle files (antigravity-example.md, provider-icon-guide.md) and an external architecture doc; however, substantial inline implementation templates keep the body fairly monolithic when some could live in references.	4 / 5
	Total	17 / 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 strong, well-scoped description that clearly answers both 'what' and 'when' with concrete, user-natural trigger phrases and a distinct niche. Minor improvement could come from naming the icon/visual-identity work and a few more synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('adding new AI providers to ClaudeBar using TDD patterns') and lists several concrete actions — adding a provider, creating a usage probe, following TDD to implement integration — with only minor coverage gaps (e.g., visual identity/icon work is not mentioned).	4 / 5
Completeness	Explicitly states what the skill does ('Guide for adding new AI providers to ClaudeBar using TDD patterns') and when to use it via a numbered 'Use this skill when' list with concrete trigger phrases, satisfying both requirements.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say, such as '"how do I add a new provider"' and '"create a provider for X"', plus named examples (Antigravity, Cursor); a few common synonyms are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (adding AI providers to a specific app, ClaudeBar) with product-specific named examples, making overlap with unrelated skills minimal.	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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: tddworks/ClaudeBar
Path: .claude/skills/add-provider/SKILL.md
Commit: e9862db

Reviewed: 4 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.