library-skills
Adds Agent Skills support to MAS Lab. A skill is a directory with a SKILL.md file that the agent loads on demand ("progressive disclosure"): the prompt carries only a catalog, and the model fetches full instructions when it needs them.
Use it when an agent needs specialised instructions, reference files or scripts without paying for them in every prompt.
Quick start
uv add library-skills
# agent.yaml
apiVersion: mas/v1
kind: Agent
metadata:
name: my-agent
spec:
models:
- model: gpt-4o-mini
context:
role: "Answer questions helpfully."
skills:
- answer-formatting # points to ./skills/answer-formatting/SKILL.md
tools:
- ref: skills:tools/skill-access.tool.yaml
mas-ctl chat agent.yaml -q "What is the speed of light?"
# or add skills with an overlay; the base manifest never changes
mas-ctl chat agent.yaml -o skills:overlays/skills.yaml -q "What is the speed of light?"
spec.skills is the only place a manifest declares an agent's skills. It is a flat list; the context-manager plugin (which only picks a context-window strategy such as stack or sliding window) has no skills setting. Each entry is a bare name, resolved through the standard locator chain (app-local skills/, declared libraries, installed packages), or @library/name for an explicit source.
Components
| Component | Kind | Description |
|---|---|---|
SkillCatalogPlugin |
ContextContract |
Injects the skill catalog (name + description) into the SYSTEM_SKILLS band |
SkillToolsPlugin |
ToolContract |
activate_skill, list_skill_files, read_skill_file |
RunSkillScriptPlugin |
ToolContract |
run_skill_script: executes scripts in scripts/ |
ContextPart.skills() |
runtime shorthand | ContextPart constructor for SYSTEM_SKILLS placement |
PluginCollection |
runtime utility | collect_results() dispatch matching the ContextAssemblerPlugin interface |
Skills are not a manifest-level contract. spec.skills supplies the content (which skills exist); the two plugins above serve it through existing runtime contracts:
| Plugin | Contract | Role |
|---|---|---|
SkillCatalogPlugin |
ContextContract |
Injects the tier-1 catalog (name + description) into SYSTEM_SKILLS |
SkillToolsPlugin |
ToolContract |
activate_skill / list_skill_files / read_skill_file (tiers 2-3) |
Engines
Three interchangeable engines do discovery, frontmatter parsing and script execution. SkillPluginRegistry(impl="native" | "adk" | "langchain") selects one and imports the matching plugin_skills_*.py module. In overlay or manifest tool entries, set impl (and optionally base_dir); bootstrap passes the choice to both catalog injection and skill tool execution.
| Engine | Framework wrapped | Sandboxing | Notes |
|---|---|---|---|
| native (default) | bundled agentskills parser + script runner |
best-effort environment filtering, timeout, POSIX rlimits | for cooperative local scripts; not a security sandbox |
| adk | google.adk.skills (google-adk) |
none (delegated to ADK) | loads resources eagerly in memory |
| langchain | deepagents (LangGraph agent harness) |
none (delegated to deepagents) | about 70 lines of adapter code, because deepagents is tool-call-oriented and has no plain "give me the skill body" API |
The base install includes the agentskills.io parser and the skill sandbox. The ADK and LangChain engines wrap optional third-party frameworks:
uv add "library-skills[adk]" # google-adk
uv add "library-skills[langchain]" # deepagents
uv add "library-skills[all]" # both
task install-dev, task ci and task verify install the [all] extra, so the full test suite (including tests/test_skill_plugins_functional.py, which exercises the real frameworks) runs by default.
Security boundary
The native script runner is not a security boundary. It runs a local subprocess with a filtered environment, a timeout and best-effort CPU and address-space limits. It provides no filesystem isolation, network isolation, container boundary or complete syscall policy. Do not execute untrusted skill code with it; use Docker or another externally enforced isolation boundary.
Further reading
- docs/user-guide.md: writing skills, tools, overlays.
- docs/developer-guide.md: the plugin interface.
- docs/spec-coverage.md: agentskills.io specification coverage matrix.
examples/quickstart/: runnable before/after example.tests/test_skill_plugins_functional.pycompares the engines.
Metadata
Release files for mas-lab-library-skills 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mas_lab_library_skills-0.2.0.tar.gz | 75.0 kB | With provenance | Details for mas_lab_library_skills-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mas_lab_library_skills-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for mas_lab_library_skills-0.2.0-py3-none-any.whl |
Total release size: 134.7 kB
Release files / mas_lab_library_skills-0.2.0.tar.gz
| Download URL | mas_lab_library_skills-0.2.0.tar.gz |
|---|---|
| Size | 75.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
87661b0af00e815f814d905c6bec48341a41a16c3768f37f149ae8e29c933691
|
|
BLAKE2b-256 checksum How to use checksums |
150baba32ed37a9b4c71f86be83ed425a481e10abc56e753641c9218a83442aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 5, 2026.
Transparency logRelease files / mas_lab_library_skills-0.2.0-py3-none-any.whl
| Download URL | mas_lab_library_skills-0.2.0-py3-none-any.whl |
|---|---|
| Size | 59.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
afa338fbc5d40124352053c7bee52cf18553c46db7f9e9e6e9a73cd83958a20d
|
|
BLAKE2b-256 checksum How to use checksums |
d7ade7d8a6eff1aaf595698319c99ecabe50738194df2e4c93e28dd108c3f1e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 5, 2026.
Transparency logSecurity for mas-lab-library-skills 0.2.0
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for mas_lab_library_skills-0.2.0.tar.gz
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 Nov 5, 2026.
Transparency logA 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.