Real Skill packageSource verifiedClawHub registry

Claude Code 接入第三方模型

将本地 Claude Code 连接到第三方兼容 Anthropic 或 OpenAI 模型端点，支持实测模型名、环境变量优先级判定和多配置源排查。

Identity and source

Publisher attributionrobinregistry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 57% rule confidence
Package forminstruction with code7 recorded files
Canonical sourceClawHub registryclawhub:oracis:claude-code-third-party-model
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codeissues found
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/29/2026.claude/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 9, column 14: description: 把本地 Claude Code 接到第三方端点——分两路：① 原生 Anthropic 兼容端点（DeepSeek / Kimi /… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexissues found
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/29/2026.agents/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 9, column 14: description: 把本地 Claude Code 接到第三方端点——分两路：① 原生 Anthropic 兼容端点（DeepSeek / Kimi /… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawissues found
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/29/2026skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 9, column 14: description: 把本地 Claude Code 接到第三方端点——分两路：① 原生 Anthropic 兼容端点（DeepSeek / Kimi /… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @oracis/claude-code-third-party-model
clawhub inspect @oracis/claude-code-third-party-model --version 1.1.1

Security evidence

SkillVetAI static result: medium signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
6 / 7 inspected as text
Checked
9/29/2026, 6:09:17 PM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumSKILL.md YAML frontmatter is invalidSKILL.md:1 · confidence 100%Nested mappings are not allowed in compact mappings at line 9, column 14: description: 把本地 Claude Code 接到第三方端点——分两路：① 原生 Anthropic 兼容端点（DeepSeek / Kimi /… ^
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
9 dependency and API indicators
  • api: api.aimlapi.com
  • api: api.deepseek.com
  • api: api.z.ai
  • api: clawhub.ai
  • api: github.com
  • api: json.schemastore.org
  • api: open.bigmodel.cn
  • api: opencode.ai
  • api: openrouter.ai
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/29/2026, 9:28:32 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:a748a5a594d330a20a6a521617c5d999c1c35af377afc0d1d5b67471d7d77d1d
Show up to 7 recorded paths
  • claude-code-third-party-model.png
  • examples/profiles/deepseek.json
  • examples/profiles/spacebunny.json
  • scripts/ccproxy.py
  • scripts/ccswitch.py
  • skill-card.md
  • SKILL.md

Source changelog

Rewrite wording flagged by the scanner: drop unrelated privilege-escalation/sandbox-event notes, use the standard loopback no_proxy list instead of a wildcard, describe proxy handling as normal no_proxy configuration.