🧠 Agent Skill SDK
Build modular, intelligent agents with event triggers, retry logic, memory, LLM planning (Amazon Bedrock), and a live dashboard.
🚀 Features
- ✅ Skill-based programming with
@skilldecorators - 🔁 Retry, backoff, and fallback on skill failure
- 🧠 LLM reasoning via Amazon Bedrock
- 🧩 Triggers: Timer, MQTT, HTTP, Cron, File Watcher, CoAP
- 📜 Memory tracing + export (CSV/JSON)
- ⚙️ CLI and 🧪 FastAPI-based dashboard
- 📚 Full developer documentation with MkDocs
📦 Install
pip install agent-skill-sdk
🧪 Example: Define a Skill
from agent_skill_sdk import skill
@skill(trigger="on_temp_high", retries=2, backoff="exponential")
def turn_on_fan(context):
print("Turning on fan:", context.get("location"))
⚡ Trigger from CLI
agent register examples.fan_control.turn_on_fan
agent trigger on_temp_high --data '{"location": "lab"}'
🧠 LLM Planning (Amazon Bedrock)
@skill(trigger="on_goal")
def bedrock_planner(context):
response = run_reasoning(context.get("goal"))
action = response.get("action")
context.agent.trigger(action)
Supports:
- Prompt templates
- Memory recall
- Fallback actions
🌐 Dashboard
uvicorn dashboard.app:app --reload
Visit http://localhost:8000 to:
- View registered skills
- Trigger events manually
- Inspect LLM trace logs
🔌 Trigger Plugins
| Trigger | File | Event |
|---|---|---|
| Timer | timer.py |
on_timer |
| MQTT | mqtt.py |
on_mqtt_message |
| HTTP/Webhook | http.py |
on_http |
| Cron | cron.py |
on_cron |
| File Watcher | file_watcher.py |
on_file_change |
| CoAP (IoT) | coap.py |
on_coap |
📚 Documentation
Visit your deployed docs here:
➡️ https://subhashtalluri.github.io/agent-skill-sdk/
Or build locally:
mkdocs serve
📤 Deployment
Use Docker or deploy with Uvicorn:
uvicorn dashboard.app:app --host 0.0.0.0 --port 8000
🧠 Trace Export
agent.export_trace("json")
agent.export_trace("csv")
🧩 Contributions Welcome
Build a trigger plugin, skill library, or submit a PR!
📜 License
MIT – do anything, just give credit ✨
Metadata
Release files for agent-skill-sdk 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_skill_sdk-0.1.1.tar.gz | 11.0 kB | Without provenance | Details for agent_skill_sdk-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_skill_sdk-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for agent_skill_sdk-0.1.1-py3-none-any.whl |
Total release size: 25.3 kB
Release files / agent_skill_sdk-0.1.1.tar.gz
| Download URL | agent_skill_sdk-0.1.1.tar.gz |
|---|---|
| Size | 11.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
685ef2b94035fb26691cf3937ed7f0dda06702a6d6c348a045b91fdff773d233
|
|
BLAKE2b-256 checksum How to use checksums |
c4c32b4bc61332858e88559ba83e876c25ed02e94cc25562c2d45a2de569c24b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.0
|
Release files / agent_skill_sdk-0.1.1-py3-none-any.whl
| Download URL | agent_skill_sdk-0.1.1-py3-none-any.whl |
|---|---|
| Size | 14.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
56c20decc0b53ef510cffb7a8fbc6f648d15d1dbeb3b433337c412081e61a540
|
|
BLAKE2b-256 checksum How to use checksums |
191d68a0dfeb21ae817d71f73c815ca1250901ac39e6172858aebe2474ff65dd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.0
|
Security for agent-skill-sdk 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.