Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Provider Apis

ASecurity

Use when building against model-provider APIs or choosing request shapes, streaming, tools or caching for Mercury's providers. Not for account sign-in or unrelated SDKs.

6 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgitapidocumentation

Works with

cliapi

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add Whq02/MercuryCLI --skill provider-apis --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Provider Apis?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Provider Apis
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/whq02-provider-apis/badge)](https://www.skillsdirectory.com/skills/whq02-provider-apis)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: provider-apis
description: Use when building against model-provider APIs or choosing request shapes, streaming, tools or caching for Mercury's providers. Not for account sign-in or unrelated SDKs.
argument-hint: "[question or task]"
---
# Provider APIs

- Identify the provider, account route and served model before writing a request.
- Check `references/live-sources.md` for current documentation and `references/models.md` for catalogue guidance.
- Separate public API requirements from Mercury's implementation; retain documented differences rather than copying a transport defect.

## Choose the dialect
- Read `references/anthropic-messages.md` for Anthropic Messages: block content, tool results and cache breakpoints.
- Read `references/openai-responses.md` for OpenAI Responses: input/output items, stateless replay and response events.
- Read `references/chat-completions.md` for Moonshot/Kimi, DeepSeek, Z.AI, OpenRouter, Gemini, Hugging Face and local/compatible servers.

## Resolve Mercury's route
- Resolve `compat/`, `openrouter/`, `huggingface/` and `local/` namespaces before native prefixes.
- Strip Mercury's carrier prefix, not the provider's own model slug, before sending.
- Route `gpt-` to OpenAI; `kimi-`/`moonshot-` to Moonshot; `deepseek-` to DeepSeek; `glm-` to Z.AI; `gemini-` to Gemini.
- Use Anthropic's declared IDs and aliases for Messages; do not treat arbitrary unknown IDs as Anthropic models.
- Preserve explicit gateway/model-pin admission; never fall through to another provider after a route failure.
- Use `/login` and `/accounts` for credentials; select the actual API-key or subscription endpoint rather than substituting one for the other.

## Verify
- Check every model ID, capability, price and limit against today's catalogue or provider page.
- Test tool/result pairing, stream termination and usage against a fixture before a live request.
- Report unsupported parameters and code/documentation differences explicitly.

Checked: 2026-09-15. [Mercury transports](https://github.com/Whq02/MercuryCLI/tree/fc81e29e4129a56b1bfb3beca9819ebfb29875f9/src/services/providers); provider sources are in the references.

Attribution

Whq02Whq02
View sourceMore from Whq02 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →