What this resource does
Core uses
This package combines a persistent agent runtime with bundled Skills
OpenSquilla is an agent package with a persistent workspace, tools, and on-demand Skills. This page highlights its bundled paper and research components rather than treating the whole runtime as one Skill.
The cards below show the bundled components that are most directly relevant to academic research and paper production.
Paper-related bundled Skills
Includes separate components for research, paper planning, abstracts, sections, references, and LaTeX compilation.
- Typical inputs
- Research topic or paper materials; Selected bundled Skill
- Output
- Component-dependent research notes or manuscript text.
Best for: Trying a paper-related workflow inside the OpenSquilla runtime.
Components for this task
deep-research
Runs a multi-round investigation with explicit planning, evidence tracking, persistent state, and citation-tagged synthesis.
Suggested requests (3)
Take a deep dive into [research topic] and produce a citation-tagged report.
Create a literature review on [research topic] using evidence from multiple sources.
Investigate [research question] across multiple sources and track the evidence over several rounds.
Adapted into complete requests from official trigger wording in src/opensquilla/skills/bundled/deep-research/SKILL.md frontmatter.
paper-preference-planner
Extracts paper-writing preferences and records conservative defaults before research and drafting begin.
paper-section-author
Writes one citation-grounded research-paper section as a bounded LaTeX fragment from a writing plan and citation plan.
latex-compile
Compiles an assembled LaTeX paper through xelatex and bibtex and reports the log tail; the source labels it demo-only.
Persistent agent workspace
Provides a local agent runtime with memory, provider configuration, channels, scheduling, and file tools.
- Typical inputs
- Configured model provider; Workspace task and local files
- Output
- Agent responses and files created by enabled tools or Skills.
Best for: Users who need a general persistent agent that can also load selected research Skills.
Component for this task
OpenSquilla runtime
Provides the persistent workspace, agent loop, tools, and on-demand Skill loading used by the bundled components.
Use boundaries
Limits and checks
Runtime permissions
Enabled capabilities may change local state or send data externally.
Review configuration, tools, and provider permissions before use.
Remote installer
Third-party code is installed and executed locally.
Inspect release files and use the documented source route when greater control is needed.
Academic subset
Runtime-wide claims may overstate academic coverage.
Evaluate the named bundled Skill separately.
More boundaries
- The runtime is not a dedicated academic method or evidence-synthesis system.
- Paper components cannot access private sources or services without legitimate user configuration.
- Generated research text and references require checking against original evidence.
Technical details
- Resource type
- Agent Package
- Author or maintainer
- opensquilla
- Version
- v0.4.1
- Latest release
- v0.4.1
- Source last updated
- 13 Jul 2026
- Last verified
- 13 Jul 2026
- Documented applications
- OpenSquilla
- Licence
- Apache-2.0
- Access
- Publicly available
- Additional costs
- Platform terms or usage limits may apply. API usage fees may apply for selected components. External services, software, compute, or data access may have separate costs.
- Skill instruction language
- English
- Documentation language
- English
- Repository languages
- Python, Markdown, JavaScript or TypeScript
- Dependencies
- Python 3.12 for the documented quick install; uv; Selected model provider
- Review status
- Not tested
Continue exploring