pm-skills (Python)
206 professional Agent Skills — PRDs, launch plans, postmortems, rubrics, contracts, pitch decks and more, across 21 professions — as importable building blocks for Python AI agents. The skills are bundled with the package, so there's no network call and no API key to read them.
pip install pm-skills # core
pip install "pm-skills[langchain]" # + LangChain tools
pip install "pm-skills[crewai]" # + CrewAI tools
Core (no dependencies)
import pm_skills
pm_skills.search_skills("customer churn") # -> [skill dicts]
pm_skills.get_skill("prd-template")["description"] # -> "..."
pm_skills.bundles() # -> ['pm-creator', 'pm-engineering', ...]
# A ready-to-send prompt for any model:
prompt = pm_skills.skill_prompt("incident-postmortem", task="API outage, 42 min, bad deploy")
As LangChain tools
from langchain.agents import create_react_agent
from pm_skills import as_langchain_tools
tools = as_langchain_tools() # [search_pm_skills, get_pm_skill]
# give `tools` to your agent — it can search the library and pull a skill's framework on demand
As CrewAI tools
from crewai import Agent
from pm_skills import as_crewai_tools
analyst = Agent(role="Product Analyst", tools=as_crewai_tools(), goal="...", backstory="...")
Any other framework works too — skill_prompt(name, task) returns plain text you can drop into
any LLM call. Same skills run live in the browser playground,
over MCP, or via npx pm-claude-skills.
1 maintainer
Metadata
1 maintainer
Release files for pm-skills 0.49.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pm_skills-0.49.0.tar.gz | 2.4 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pm_skills-0.49.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 4.9 MB
Release files / pm_skills-0.49.0.tar.gz
| Download URL | pm_skills-0.49.0.tar.gz |
|---|---|
| Size | 2.4 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d1dca9d63986482b34711c689718770bd8067d802bf6480edc4629b0f346e5f0
|
|
BLAKE2b-256 checksum How to use checksums |
26c3e87ac9f06ff51794368bac0d2909b4ce0e5476f6c2b56632a7b23e2ca866
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 28, 2026.
Transparency logRelease files / pm_skills-0.49.0-py3-none-any.whl
| Download URL | pm_skills-0.49.0-py3-none-any.whl |
|---|---|
| Size | 2.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
aa321a58709d9aeabd53aa49ce2a2dc4306bd58f42671958e2bea9e1818a99be
|
|
BLAKE2b-256 checksum How to use checksums |
f988ad7fc16318bb4f6cd3dbc112765b5fd780256dbb8e00a623fb6d5a1c8a37
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 28, 2026.
Transparency log
