calixto-research-workspace

Toolkit-side handoff for Calixto research preparation. Use when starting from the toolkit root and the user's topic needs clarification, normalization, or a durable brief before source gathering. This skill triages the raw question, asks targeted clarification only when needed, creates or selects a standalone workspace boundary, writes notes/research-brief.md, and hands off to the workspace-local preparation or downstream research skill.

Performs structured, reproducible research with full source-to-claim traceability inside a standalone Calixto workspace. Use when the user asks for a research report, comparison, literature scan, or any task that needs multiple cited sources. Workflow: confirm the workspace question, search the web and the right scholarly provider, extract findings (fnd_NNN), synthesize insights (ins_NNN), write a report with inline [src_NNN] citations, run strict traceability checks, and generate a manual citation-review artifact.

Produces a structured academic literature review inside a standalone Calixto workspace with full citation tracking and methodology assessment. Use when the user asks for a literature review, related-work section, systematic survey, or scholarly analysis. Emphasizes domain-appropriate scholarly search, venue assessment, citation count, quality tiers, and explicit gaps.

Normalizes a raw or underspecified research topic inside a standalone Calixto workspace before source gathering. Use when the question is ambiguous, too broad, high-stakes, time-sensitive, subjective, or missing a clear output shape. The workflow triages the request, asks targeted clarification only when needed, writes notes/research-brief.md, updates config.json.question when approved or safely assumed, and then hands off to deep-research or literature-review.

Performs a user-mediated two-agent retrospective of a completed Calixto research workspace. Use when Agent B must independently audit Agent A's research, derive a case-specific but non-leading questionnaire from that adversarial report, pause while the user gives it to Agent A in the original research session, then synthesize the report, questionnaire, and returned answers into prioritized improvements for Calixto tooling, setup, runtime, skills, scaffold, audits, documentation, or product behavior.

Teaches an agent how to create a new Calixto skill (a research workflow packaged as a directory of markdown with a SKILL.md file). Use when the user wants to add a new research skill, formalize a recurring pattern, or build a domain-specific variant of an existing skill (e.g., competitive analysis, bug triage, codebase archaeology). Covers the Agent Skills spec, skill file structure, ID conventions, validation, and examples.

Toolkit-side handoff for Calixto deep research. Use when starting from the toolkit root and the user needs a structured, cited research workflow. This skill creates a standalone workspace snapshot, switches into it, and then continues with the bundled workspace-local deep-research skill.

Toolkit-side handoff for Calixto literature reviews. Use when starting from the toolkit root and the user needs a paper-heavy review workflow. This skill creates a standalone workspace snapshot, switches into it, and then continues with the bundled workspace-local literature-review skill.

Teaches an agent how to add a new search provider, scrape backend, or data source to Calixto Research Workspace. Use when the user asks to add support for Brave, Tavily, Google Scholar, Semantic Scholar, PubMed, GitHub, a custom API, or any new data source. Covers the SearchProvider and ScrapeProvider interfaces, registration in the script dispatchers, optional dependency groups, testing, and documentation. Also useful for adding new CLI scripts.