add-provider

Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

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

A high-quality, well-structured instruction skill body that is lean, concrete, and easy to navigate, with explicit validation commands and checklists. Its one notable gap is the absence of an explicit validate-then-fix-then-revalidate feedback loop in the workflow.

Suggestions

Add an explicit error-recovery loop to the Workflow: after running format/i18n/lint and focused tests, state that on failure Claude should fix the reported issues and re-run the failing command before proceeding (e.g. 'If lint or tests fail, fix the reported issues and re-run until clean').

Make the validation checkpoint a hard gate: note that the Output Checklist should only be reported once format, i18n, lint, and the focused provider tests all pass, mirroring the rubric's 'only proceed when validation passes' pattern.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational — specific file paths, terse imperatives, and a copy-paste command block — with no explanation of concepts Claude already knows (e.g., what a provider or OAuth is); every section earns its place.	3 / 3
Actionability	It gives concrete, executable guidance: exact files to read and touch (e.g. src/main/provider/providerRegistry.ts), runnable commands (pnpm run format/i18n/lint), a classification into three supported paths, and specific test obligations — actionable without needing inline code samples for an instruction skill.	3 / 3
Workflow Clarity	The Workflow is a clear numbered 7-step sequence with explicit validation (step 7 runs format/i18n/lint plus focused tests) and supporting checklists, but it lacks an explicit error-recovery feedback loop stating what to do when validation fails, which the rubric's top anchor requires.	2 / 3
Progressive Disclosure	The body is well-organized into clearly signaled single-level sections (Goal, Required Inputs, Supported Paths, Guardrails, Workflow, Output Checklist) with easy header-based navigation and no nested or dangling references; no bundle files exist, and the inline content is appropriately self-contained.	3 / 3
	Total	11 / 12 Passed

Description

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.

A concise, well-structured description in third person that pairs a concrete capability statement with an explicit, enumerated "Use when" trigger clause scoped to the repository. It closely matches the rubric's own good examples and carries no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	It states a concrete action ("Add a DeepChat LLM provider through explicit reviewed source changes") and enumerates multiple distinct concrete capabilities the skill handles — provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, and special provider adapter — rather than vague language.	3 / 3
Completeness	It explicitly answers both what ("Add a DeepChat LLM provider through explicit reviewed source changes") and when (an explicit "Use when..." clause with enumerated triggers), matching the rubric's strong what-plus-when pattern.	3 / 3
Trigger Term Quality	The explicit "Use when a developer asks Codex to add a provider, provider profile, ... in this repository" clause gives good coverage of natural domain terms its target audience would say ("add a provider", "add a provider profile", "add a special provider adapter"), scoped to the repository.	3 / 3
Distinctiveness Conflict Risk	The narrow niche (DeepChat LLM provider in this repository) plus the enumerated, architecture-specific triggers make it clearly distinguishable and unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ThinkInAIXYZ/deepchat
Path: .agents/skills/add-provider/SKILL.md
Commit: b8dbc89

Reviewed: about 7 hours 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.