Skill llm deepseek
Skill joeylu/runtime-free-llm-integration-skills/LLM/skill-llm-deepseek
Runtime-free skills for coding agents to build fail-fast LLM provider integrations across OpenAI, Aliyun Bailian / DashScope, DeepSeek, and Gemini.
npx -y skills add joeylu/runtime-free-llm-integration-skills --skill skill-llm-deepseekAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Runtime contract for the direct DeepSeek API. Use it to resolve exact DeepSeek model IDs, Chat Completions and beta request URLs, thinking controls, reasoning history, JSON output, caller tools, strict function schemas, streaming, response mapping, pricing references, and logging. Model choice remains with the user or host project.
SKILL.md
3.1 KB, as published. Nobody here has run it
Skill LLM DeepSeek
Purpose
Define how an agent integrates a DeepSeek model already named by the user or host project.
Read Order
Read shared contracts first:
../_shared/route-key-schema.md../_shared/model-catalog-schema.md../_shared/pricing-matrix-schema.md../_shared/capability-matrix-schema.md../_shared/connection-profile-schema.md../_shared/request-url-matrix-schema.md../_shared/request-envelope.md../_shared/response-envelope.md../_shared/error-contract.md../_shared/progress-contract.md../_shared/ui-binding.md../_shared/sync-policy.md../_shared/logging-fields.md
Then read:
references/connection-profiles.mdreferences/request-urls.mdreferences/model-catalog.mdreferences/pricing-matrix.mdreferences/capability-matrix.md- the transport for the requested kind
references/logging-contract.mdwhen logging is implementedreferences/model-sync.mdonly for an explicit update or verification task
Runtime Rules
- Send the exact model ID from
model-catalog.md. - Resolve connection profile, request kind, API surface, API version, endpoint kind, full route key, base URL, and request URL before capability lookup.
- Match capabilities by the exact full
RouteKeyrow, including API version and endpoint kind. - The normal Chat Completions surface and the beta strict-function surface are separate rows. Strict function schemas require the documented beta endpoint.
- Thinking mode returns
reasoning_contentalongsidecontent. - During tool-call continuation in thinking mode, preserve prior assistant
reasoning_content, preserve tool-call identity, and keep assistantcontentnon-null. - DeepSeek V4 thinking mode rejects
tool_choice; do not send it when effective thinking is enabled. - Use the exact documented thinking and
reasoning_effortfields. Do not invent OpenAI Responses fields for DeepSeek. - Reject requested fields marked
unsupportedorunknown. - Do not silently switch models, surfaces, URLs, or providers.
- Store API-key references only and redact authorization data from logs.
Request Flow
- Read the requested model, request kind, and surface.
- Resolve the connection profile and exact request URL row.
- Resolve the exact catalog and capability rows.
- Determine effective thinking before validating tool and structured-output fields.
- Apply the Chat Completions transport, including history-preservation rules.
- Normalize response, errors, progress, and logs through the shared contracts.
Out of Scope
- vision, imaging, or music without documented rows
- non-official DeepSeek gateways unless their compatibility is re-verified
- model ranking or permission policy
- non-DeepSeek providers