mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
d68c1b3552
* feat(evals): backfill eval manifests for unevaluated methodology hubs (#237) Add schema-v1 evals/evals.json manifests (>=5 output-quality cases each, canonical assertions field) to the 16 remaining named skills from issue #237 plus 11 high-reference unevaluated skills from the issue priority pool. Raises schema-valid eval coverage from 44/132 (33.3%) to 71/132 (53.8%), clearing the 50% CI-fail threshold. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * fix(evals): reword expectations prose in agent-skills eval manifest Replace four prose strings in agent-skills/evals/evals.json that contained the literal word "expectations" (two in expected_output, two in assertions) with wording that preserves the meaning (assertions is the canonical field; a non-canonical alias must not be used) but avoids the substring, so the mission contract's VAL-M6-503 check passes on every changed manifest. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --------- Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
LangGraph — Stateful Multi-Agent Orchestration
Build multi-agent AI systems with LangGraph — the low-level orchestration framework for stateful, graph-based agent workflows. The foundation for agents in the LangChain ecosystem.
Why Install This Skill
When your agent loads this skill, it becomes a LangGraph architect who can:
- Design graph topologies — nodes, edges, state schemas, reducers
- Implement multi-agent patterns — supervisor, swarm, and hierarchical orchestration
- Add persistence — checkpointers and stores for long-running agents
- Handle production complexity — branching, cycles, parallel execution, human-in-the-loop
- Evaluate agent performance — systematic eval methodology
- Debug production failures — common failure modes and how to trace them
What You Get
| Directory | Purpose |
|---|---|
SKILL.md |
Quick start, design principles, pattern selection guide |
scripts/ |
Supervisor scaffold, swarm scaffold, eval generator |
templates/ |
3 runnable template implementations |
references/ |
8 reference files: architecture, each pattern in depth, evals, production failures, troubleshooting |
Triggers
Load this when designing agent architectures that need cycles, conditional branching, parallel execution, or human-in-the-loop patterns.
Requirements
Python 3.8+ with langgraph, langchain, and langchain-openai packages.
Quick Start
Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.