Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Val1813/Deepseekapiexpert — measured AI agent skill | DecimalAI

val1813/DeepSeekAPIExpert

NewSkillScoreMaintained

- 国产LLM统一用 OpenAI 兼容接口格式（/v1/chat/completions）

AI/MLby val1813

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/val1813-deepseekapiexpert/SKILL.md

decimalai skills pull val1813-deepseekapiexpert --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/val1813-deepseekapiexpert/SKILL.md https://app.decimal.ai/s/val1813-deepseekapiexpert/SKILL.md

Raw file: /s/val1813-deepseekapiexpert/SKILL.md ↗ · machine-readable summary at /s/val1813-deepseekapiexpert.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

Yes — +18% lift+2% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-4%	0%
case-02	✗→✓	▲ Improved	33%	0%
case-06	✗→✓	▲ Improved	-7%	0%
case-08	✗→✓	▲ Improved	3%	0%
case-17	✗→✓	▲ Improved	-20%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

val1813 / kwcode

kaiwu/builtin_experts/deepseekapi/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

领域知识

国产LLM统一用 OpenAI 兼容接口格式（/v1/chat/completions）
DeepSeek base_url: https://api.deepseek.com，Qwen: https://dashscope.aliyuncs.com/compatible-mode/v1
流式响应：stream=True + SSE解析，逐chunk拼接content字段
token计费：输入/输出分别计价，用tiktoken或API返回的usage字段统计
限流处理：捕获429状态码，指数退避重试（1s/2s/4s），最多3次
超时设置：连接超时10s，读取超时60s（长文本生成可加到120s）
prompt工程：system message定角色，few-shot放user/assistant交替
温度参数：代码生成用0.0-0.3，创意文本用0.7-1.0
错误处理：区分可重试错误（429/500/503）和不可重试错误（400/401）
长文本：超过模型max_tokens时自动截断或分段处理

经验规则（自动生成）

Want to see if val1813/DeepSeekAPIExpert would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.