Ready to supercharge your AI agents?

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

腾讯 IMA 智能工作台 — measured AI agent skill | DecimalAI

openakita/skills@tencent-ima

SkillScore82Maintained

Tencent IMA OpenAPI skill for notes and knowledge base management. Use when user mentions knowledge base, notes, memos, file uploads, web page collection, or knowledge search. Supports notes CRUD, knowledge base file upload, web link addition, and content search.

Documentationby openakita

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

Automatic

Knowledge Management pack

decimalai skills pull openakita-skills-tencent-ima

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/openakita-skills-tencent-ima/SKILL.md

Raw file: /s/openakita-skills-tencent-ima/SKILL.md ↗ · machine-readable summary at /s/openakita-skills-tencent-ima.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

—-19% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-08	✗→✓	▲ Improved	-41%	0%
case-07	✗→✓	▲ Improved	0%	0%
case-10	✗→✓	▲ Improved	-36%	0%
case-11	✗→✓	▲ Improved	-53%	0%
case-12	✗→✓	▲ Improved	-16%	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

openakita / openakita

skills/tencent-ima/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 4 files · scripts

Skill contents

scripts/

references/

SKILL.md

腾讯 IMA 智能工作台

统一的 IMA OpenAPI 技能，支持笔记管理和知识库操作。

配置

打开 https://ima.qq.com/agent-interface 获取 Client ID 和 API Key
存储凭证：

方式 A — 配置文件： mkdir -p ~/.config/ima echo "your_client_id" > ~/.config/ima/client_id echo "your_api_key" > ~/.config/ima/api_key

方式 B — 环境变量： export IMA_OPENAPI_CLIENTID="your_client_id" export IMA_OPENAPI_APIKEY="your_api_key"

API 调用模板

ima_api() { local path="$1" body="$2" curl -s -X POST "https://ima.qq.com/$path" \ -H "ima-openapi-clientid: $IMA_CLIENT_ID" \ -H "ima-openapi-apikey: $IMA_API_KEY" \ -H "Content-Type: application/json" \ -d "$body" }

模块决策表

| 用户意图 | 模块 | |---------|------| | 搜索/浏览/创建/编辑笔记 | notes | | 上传文件/添加网页/搜索知识库 | knowledge-base |

预置脚本

scripts/ima_notes.py

IMA 笔记 API 封装，需设置 IMA_OPENAPI_CLIENTID 和 IMA_OPENAPI_APIKEY。

bash
python3 scripts/ima_notes.py search "会议纪要"
python3 scripts/ima_notes.py folders
python3 scripts/ima_notes.py create --content "# 新笔记\n内容"
python3 scripts/ima_notes.py read --doc-id xxx

scripts/ima_kb.py

IMA 知识库 API 封装。

bash
python3 scripts/ima_kb.py search --kb-id xxx "关键词"
python3 scripts/ima_kb.py browse --kb-id xxx
python3 scripts/ima_kb.py import-url --kb-id xxx --url "https://example.com"

Want to see if openakita/skills@tencent-ima 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.