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

85%

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

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 well-structured, token-efficient instruction skill with concrete file targets, explicit guardrails, and a validation-backed workflow. The main improvements would be adding a validate→fix→retry feedback loop and de-duplicating the repeated typical-file listings across supported paths.

Suggestions

Add an explicit validation feedback loop after the pnpm command block (e.g., on lint/typecheck failure: fix the reported issues, then re-run until clean) to reach the workflow_clarity 5 anchor.

De-duplicate the typical-files listings shared across the three Supported Paths by factoring common files (defaults.ts, providerRegistry.ts) into a single base list and noting per-path additions.

For actionability, include one minimal concrete edit skeleton (e.g., a providerRegistry entry shape or a defaults.ts snippet) so the source-change step is copy-paste ready rather than path-only.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no padding or explanations of concepts Claude already knows; dense input/file lists and a command block where every token earns its place, matching the 5 anchor.	5 / 5
Actionability	Concrete file paths (src/main/provider/defaults.ts, providerRegistry.ts, etc.) and exact validation commands (pnpm run format/i18n/lint/typecheck) give mostly executable guidance, but as an instruction-style skill it lacks copy-paste edit snippets for the actual source changes, leaving minor gaps.	4 / 5
Workflow Clarity	A clear 7-step workflow with inspection-before-edit, path classification, smallest-change guidance, test assessment, and an explicit validation command block; it stops short of a full validate→fix→retry feedback loop, so it does not reach the 5 anchor.	4 / 5
Progressive Disclosure	Well-organized sections (Goal, Required Inputs, Supported Paths, Guardrails, Workflow, Output Checklist) with clearly signaled one-level references to spec.md/plan.md; minor gaps include repeated file listings across the three supported paths and absence of a skill bundle to offload detail.	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, third-person description that clearly states both capability and explicit use-when triggers with concrete enumerated scopes. It is distinct and well-targeted; the only mild gap is that specificity rests on one core action rather than a broad list of operations.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Add a DeepChat LLM provider through explicit reviewed source changes") and enumerates specific scopes (provider profile, upstream provider config, model catalog mapping, auth behavior, special adapter), but the core action is a single add-provider operation rather than a list of multiple distinct operations, so it sits just below the comprehensive 5 anchor.	4 / 5
Completeness	It explicitly states both what ("Add a DeepChat LLM provider through explicit reviewed source changes") and when ("Use when a developer asks Codex to add a provider...") with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	"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" provides good natural trigger phrasing and several synonyms, missing only a few common variations a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped to "DeepChat LLM provider" within "this repository" with distinct enumerated triggers (provider profile, catalog mapping, special adapter), giving a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 20 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: fa769d4

Reviewed: 2 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.