Forked clean from public hackathon repo (Starfire-AgentTeam, BSL 1.1) with full rebrand to Molecule AI under github.com/Molecule-AI/molecule-monorepo. Brand: Starfire → Molecule AI. Slug: starfire / agent-molecule → molecule. Env vars: STARFIRE_* → MOLECULE_*. Go module: github.com/agent-molecule/platform → github.com/Molecule-AI/molecule-monorepo/platform. Python packages: starfire_plugin → molecule_plugin, starfire_agent → molecule_agent. DB: agentmolecule → molecule. History truncated; see public repo for prior commits and contributor attribution. Verified green: go test -race ./... (platform), pytest (workspace-template 1129 + sdk 132), vitest (canvas 352), build (mcp). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
924 B
924 B
| name | description | license | metadata | ||||
|---|---|---|---|---|---|---|---|
| example-skill | Short description — what this does and when to use it. | MIT |
|
Example Skill
Write the skill instructions as plain Markdown below the frontmatter.
Agents load this entire file when the skill activates, so keep it focused
and under ~500 lines. Move deep-dive docs to references/ and large
assets to assets/ — they're loaded on demand.
When to use
- Describe the triggering situation
- Describe what the agent should output
Steps
- First step
- Second step
Files under this skill
scripts/— executable code the agent can runreferences/REFERENCE.md— detailed docs (loaded only when needed)assets/— templates, images, data files
Notes
- This file is validated against the agentskills.io open standard.
- Run
python -m molecule_plugin validate <plugin-dir>before publishing.