Agent skill

Deepseek Provider Contract

by AnastasiyaW in AnastasiyaW/codex-claude-code-config

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

MITAuto-check passedBackend & APIs

Install Deepseek Provider Contract

skills CLI
$ npx skills add AnastasiyaW/codex-claude-code-config --skill deepseek-provider-contract -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AnastasiyaW/codex-claude-code-config deepseek-provider-contract --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/operational/deepseek-provider-contract .claude/skills/deepseek-provider-contract && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deepseek-provider-contract
GitHub stars
154
Token cost
~1.2k tokens
SKILL.md length
540 words
Files
3 (incl. scripts)
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

  • Works in 5 steps: Classify the proposed prompt/data.… → Freeze the provider model, endpoint,… → Save a redacted request-history fixture… → …
  • Integrating DeepSeek
  • SKILL.md covers Use It In This Order, Required Invariants, Adoption Decision and Gotchas, plus 2 more sections
  • Runs Python scripts from its folder; needs DEEPSEEK_API_KEY

What it does

Deepseek Provider Contract is an agent skill from AnastasiyaW/codex-claude-code-config. Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Use when integrating DeepSeek, adding DeepSeek tool calls or streaming, debugging DeepSeek 400 after a tool call, or evaluating a DeepSeek harness/MCP. Do NOT use for a generic model comparison, ordinary local coding, or to send a repository transcript to a provider by default.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/test_validate_deepseek_history.py` and `scripts/validate_deepseek_history.py`).

It sits in Backend & APIs, covering Third-party API integration. It works with DeepSeek and Model Context Protocol. The repository describes itself as: Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development. The licence is MIT.

When your agent uses it

  • Integrating DeepSeek
  • Adding DeepSeek tool calls
  • Debugging DeepSeek 400 after a tool call
  • Evaluating a DeepSeek harness/MCP

Example prompts

  • “/deepseek-provider-contract”

Requirements

  • Python 3
  • A credential in DEEPSEEK_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Classify the proposed prompt/data. Private archive, credentials, customer
  2. Freeze the provider model, endpoint, request budget, and fallback in the
  3. Save a redacted request-history fixture that explicitly declares whether the
  4. Run the provider only in a bounded, opt-in experiment. Record model, endpoint,
  5. Compare against the incumbent on the same frozen task before adding any route

What it can do on your machine

Read from SKILL.md and the folder at commit 3601289. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • api-docs.deepseek.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • DEEPSEEK_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deepseek Provider Contract loads about 1.2k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 540 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from AnastasiyaW/codex-claude-code-config at commit 3601289, republished under its MIT licence (© AnastasiyaW). 540 words, ~1,161 tokens.

Download SKILL.mdSave it as .claude/skills/deepseek-provider-contract/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
deepseek-provider-contract
description
Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Use when integrating DeepSeek, adding DeepSeek tool calls or streaming, debugging DeepSeek 400 after a tool call, or evaluating a DeepSeek harness/MCP. Do NOT use for a generic model comparison, ordinary local coding, or to send a repository transcript to a provider by default.

DeepSeek Provider Contract

This is a local, offline contract check. It neither reads DEEPSEEK_API_KEY nor sends code, transcripts, or secrets. A third-party harness is an implementation candidate, not a trusted route.

Use It In This Order

  1. Classify the proposed prompt/data. Private archive, credentials, customer data, and whole transcripts stay local unless the user explicitly authorizes that provider and scope.

  2. Freeze the provider model, endpoint, request budget, and fallback in the integration plan. Do not inherit defaults from a community wrapper.

  3. Save a redacted request-history fixture that explicitly declares whether the outbound request carries tools, then run:

    The fixture shape is {"outbound_request":{"tools":[...]},"messages":[...]}; use "tools": [] only for an outbound tools-free request.

    text
    python skills/operational/deepseek-provider-contract/scripts/validate_deepseek_history.py fixture.json
  4. Run the provider only in a bounded, opt-in experiment. Record model, endpoint, max output, cache-usage fields, request digest, and observed result.

  5. Compare against the incumbent on the same frozen task before adding any route to a workflow. A passing history fixture proves message lifecycle only; it does not prove quality, price, availability, or data handling.

Required Invariants

  • In thinking mode with tools, preserve the provider's complete assistant message, including reasoning_content and tool_calls. Do not rebuild a reduced assistant message from content alone.
  • Each tool result has the exact prior tool_call_id.
  • While a request carries tools, retain the documented reasoning_content from prior assistant turns in its history. Do not reduce this to only the most recent tool-call turn; check the current provider documentation because model and endpoint semantics change.
  • Use strict schema only with the beta endpoint and only after validating the supported JSON Schema subset. Never call a schema "strict" merely because it looks valid locally.
  • Set output bounds explicitly and make cache hits/misses observability, not a correctness promise.

Adoption Decision

Adopt a DeepSeek route only when all are true:

  1. The offline history validator and its regression tests pass.
  2. A redacted live canary succeeds with the exact frozen integration.
  3. The frozen benchmark beats or materially supplements the current route.
  4. Provider data scope and failure fallback are written down.

Otherwise keep this skill and the fixture only; do not install a global MCP.

Show full SKILL.md (190 more words)Show less

Gotchas

  • For a tools-bearing request, the current DeepSeek documentation requires the prior assistant reasoning_content; a tools-free request has different context semantics. Treat the offline validator as a narrow fixture check, not a substitute for the live API contract.
  • A response can say cache-hit while quality or latency still changes; measure those separately.
  • A history normalizer that strips reasoning_content can make the next tools-bearing request request fail with HTTP 400 even if the first request succeeded.
  • Model names, limits, pricing, and beta semantics are provider facts: re-check the official documentation at the integration date.

Troubleshooting

SymptomLikely causeFix
HTTP 400 after a tool resultAssistant reasoning was discardedPreserve the complete assistant tool-call message and rerun the validator
Tool JSON is rejected in strict modeWrong endpoint or unsupported schemaUse the beta endpoint, validate the schema subset, or turn strict mode off
Wrapper works once then loses contextHistory was normalized too aggressivelyCompare its persisted fixture with the provider contract
Temptation to add global MCPScope and data boundary were skippedKeep it opt-in until a frozen canary and benchmark pass

Sources

© AnastasiyaW, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/operational/deepseek-provider-contract of AnastasiyaW/codex-claude-code-config.

  • SKILL.md
  • scripts/test_validate_deepseek_history.py
  • scripts/validate_deepseek_history.py

Open the folder on GitHubat commit 3601289

Compare with similar skills

Deepseek Provider Contract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deepseek Provider Contract compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deepseek Provider Contract this skillAnastasiyaW/codex-claude-code-config154—~1.2kAutomated safety check: PassMIT
MCP API Key AuthenticationYourdaylight/stock_datasource189—~1.2kAutomated safety check: PassMIT
LangBot EBA Adapter Developmentlangbot-app/LangBot18k—~4kAutomated safety check: PassApache-2.0
DisCatSharp Discord DevelopmentAiko-IT-Systems/DisCatSharp140—~1.2kAutomated safety check: PassMIT
Cdesktopcdesktop-ai/cdesktop158—~697Automated safety check: PassApache-2.0
Apify Integration Developmentapify/agent-skills2.4k—~3.4kAutomated safety check: PassNone

Similar skills

  • MCP API Key Authentication

    Yourdaylight/stock_datasource

    Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.

    189 GitHub stars~1.2k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Guides building, migrating and testing LangBot messaging-platform adapters for the Event-Based Agents layout, with unified event and message conversion.

    18k GitHub stars~4k tokensUpdated today
    Backend & APIsAuto-check passed
  • DisCatSharp Discord Development

    Aiko-IT-Systems/DisCatSharp

    Helps build, explain and troubleshoot C# Discord apps on DisCatSharp, answering from the project's installed version and the library's documentation rather than guesses.

    140 GitHub stars~1.2k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Cdesktop

    cdesktop-ai/cdesktop

    Operate the cdesktop coding-session environment — agent teams, session management, file conventions.

    158 GitHub stars~697 tokensUpdated 4 mo ago
    Backend & APIsAuto-check passed
  • Official

    Guides designing and building an official Apify integration for a company's product: workflow-automation apps, AI agent plugins, AI framework packages or direct API clients.

    2.4k GitHub stars~3.4k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Atlassian MCP Expert

    Jeffallan/claude-skills

    Queries and edits Jira issues and Confluence pages through an MCP server, covering JQL and CQL queries, server setup, authentication and sprint or backlog workflows.

    12k GitHub stars~1.3k tokensUpdated 8 days ago
    Backend & APIsAuto-check passed

More from AnastasiyaW/codex-claude-code-config

All 50 skills in this repo
  • Bug Reproducer

    AnastasiyaW/codex-claude-code-config

    Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.

    154 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Motion Framer

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation.

    154 GitHub starsUsed in 1 repo~5.2k tokens
    Auto-check passed
  • Proof Verify

    AnastasiyaW/codex-claude-code-config

    Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).

    154 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Workflow Orchestration

    AnastasiyaW/codex-claude-code-config

    Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

    154 GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Notebooklm Grounded Research

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.

    154 GitHub stars~2.4k tokensUpdated today
    Auto-check: warnings
  • Desktop Sessions Discovery

    AnastasiyaW/codex-claude-code-config

    Discover, search, and selectively restore Claude desktop app sessions hidden across multiple accountIds.

    154 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Deepseek Provider Contract

What does Deepseek Provider Contract do?

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Deepseek Provider Contract is an agent skill from AnastasiyaW/codex-claude-code-config. Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

When should I use Deepseek Provider Contract?

Deepseek Provider Contract fits situations like: integrating DeepSeek; adding DeepSeek tool calls; debugging DeepSeek 400 after a tool call; evaluating a DeepSeek harness/MCP.

How do I install Deepseek Provider Contract in Claude Code?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill deepseek-provider-contract -a claude-code`. Or copy the skill folder (skills/operational/deepseek-provider-contract in AnastasiyaW/codex-claude-code-config) into .claude/skills/deepseek-provider-contract in your project. Claude Code loads it when a task matches its description.

How do I install Deepseek Provider Contract in Codex?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill deepseek-provider-contract -a codex`. Or copy the skill folder (skills/operational/deepseek-provider-contract in AnastasiyaW/codex-claude-code-config) into .agents/skills/deepseek-provider-contract in your project. Codex loads it when a task matches its description.

Can I use Deepseek Provider Contract in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AnastasiyaW/codex-claude-code-config --skill deepseek-provider-contract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepseek-provider-contract, .gemini/skills/deepseek-provider-contract, .github/skills/deepseek-provider-contract and .opencode/skills/deepseek-provider-contract in your project.

What does Deepseek Provider Contract need to run?

Going by SKILL.md and its folder, Deepseek Provider Contract needs Python for the scripts in its folder and credentials named DEEPSEEK_API_KEY. Our summary lists: Python 3; A credential in DEEPSEEK_API_KEY.

Does Deepseek Provider Contract access the network?

SKILL.md names 1 domain. As links in the text: api-docs.deepseek.com. This is read from the text; nothing was executed.

Is Deepseek Provider Contract safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Deepseek Provider Contract use?

Deepseek Provider Contract is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepseek Provider Contract use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deepseek Provider Contract?

Skills that share tags, products or a category with Deepseek Provider Contract: MCP API Key Authentication (Yourdaylight/stock_datasource, 189 stars), LangBot EBA Adapter Development (langbot-app/LangBot, 18k stars), DisCatSharp Discord Development (Aiko-IT-Systems/DisCatSharp, 140 stars) and Cdesktop (cdesktop-ai/cdesktop, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepseek Provider Contract?

AnastasiyaW (a GitHub user) maintains it in AnastasiyaW/codex-claude-code-config, which has 154 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 11, 2026.

Source: AnastasiyaW/codex-claude-code-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.