Skip to content

sandbaseai/sandbase-skills / agent-plugin/skills/multi-source-search

multi-source-search

Verified

Portable multi-source research with cross-source validation and an offline evidence ledger. Use for fact-checking, comprehensive research, or any question requiring multiple independent perspectives; work with the host agent's search tools and optionally add SandBase Tavily, Exa, Scholar, and Cloudsway coverage.

FileKindSize
SKILL.mdskill md6.2 KB
agents/openai.yamlconfig273 B
references/report-schema.mdmarkdown1.7 KB
references/sandbase-api-map.mdmarkdown1.2 KB
scripts/validate_report.pyscript7.6 KB

references/report-schema.md

View on GitHub
# Research report schema

Save the research ledger as one UTF-8 JSON object:

```json
{
  "question": "What is being investigated?",
  "searched_at": "2026-08-15",
  "providers": ["host_web_search", "host_page_open", "scholar_search_mixed"],
  "unavailable_providers": [],
  "sources": [
    {
      "id": "s1",
      "url": "https://example.org/primary-study",
      "publisher": "Example Institute",
      "source_type": "primary"
    }
  ],
  "claims": [
    {
      "id": "c1",
      "text": "A bounded, checkable claim.",
      "kind": "sourced",
      "confidence": "low",
      "source_ids": ["s1"],
      "independent_source_count": 1,
      "conflict": false
    }
  ],
  "gaps": ["Independent replication is not available."]
}
```

Rules:

- Record the actual capability names used, including native host tools. Record at least
  two unique capabilities; repeated queries to one capability still count as one. List
  unavailable capabilities separately.
- Source IDs and URL identities must be unique. The offline validator treats host and
  scheme case, default ports, fragments, and common tracking parameters (`utm_*`,
  `gclid`, `fbclid`, `mc_cid`, `mc_eid`) as non-distinguishing while preserving
  meaningful query parameters. Source type is `primary`, `secondary`, or `aggregator`.
- Claims reference existing source IDs and declare `kind` as `sourced` or `inference`.
- High confidence requires at least three independent sources; medium requires two; low requires one.
- A conflicting claim cannot be high confidence.
- Every source must support at least one claim, and every evidence gap must be explicit.

The validator does not fetch URLs, follow redirects, judge credibility, detect hidden
shared sources, or prove claims true.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall