@nicolailassen/agent-skills
AAdd dynamic skills to orxhestra agents. Covers Skill, InMemorySkillStore, and skill discovery/loading tools.
Install
agr install @nicolailassen/agent-skills --target claudeWrites 1 file into .claude/skills/, pinned to git-7c31a053.
- .claude/skills/agent-skills/SKILL.md
Document
name: agent-skills description: Add dynamic skills to orxhestra agents. Covers Skill, InMemorySkillStore, and skill discovery/loading tools.
Agent Skills
Skills are reusable instruction blocks that an agent can load dynamically at runtime.
Setup
from orxhestra import Skill, InMemorySkillStore
from orxhestra.skills.load_skill_tool import make_load_skill_tool, make_list_skills_tool
store = InMemorySkillStore([
Skill(
name="summarization",
description="How to write concise summaries.",
content="Extract the 3-5 most important points. Use bullet points. Be concise.",
),
Skill(
name="code_review",
description="How to conduct a thorough code review.",
content="Check correctness, readability, test coverage, and security.",
),
])
agent = LlmAgent(
name="SkillfulAgent",
model=model,
tools=[
make_list_skills_tool(store), # lets agent discover available skills
make_load_skill_tool(store), # lets agent load a skill's full content
],
)
The agent calls list_skills to discover what's available, then load_skill("summarization") to get the full instruction text.
Custom backends
Implement BaseSkillStore for any backend (database, file system, API).
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-7c31a053bf8c2026-07-31