Skip to content

Add SandBase multi-source research skill - #2673

Open
denial123789 wants to merge 2 commits into
github:mainfrom
sandbaseai:feat/multi-source-research
Open

Add SandBase multi-source research skill#2673
denial123789 wants to merge 2 commits into
github:mainfrom
sandbaseai:feat/multi-source-research

Conversation

@denial123789

@denial123789 denial123789 commented Aug 15, 2026

Copy link
Copy Markdown

Pull Request Checklist

  • I have read and followed the CONTRIBUTING.md guidelines.
  • I have read and followed the guidance for submissions involving paid services.
  • My contribution adds a new skill in the correct directory.
  • The file follows the required naming convention and repository skill format.
  • The content is clearly structured and follows the example format.
  • I ran npm run skill:validate.
  • I ran npm run build with the live MCP registry and verified generated docs are up to date.
  • This pull request targets main.

Description

Adds a portable Copilot skill for source-diverse web and academic research. It starts with compatible search, page-reading, browser, or academic tools already available to the host, so a SandBase account is not required. When SandBase MCP is configured, the workflow can add Tavily, Exa, Scholar, and Cloudsway as independent provider coverage.

The skill teaches primary-source inspection, circular-reporting detection, conservative confidence labels, disagreement preservation, and citation-adjacent synthesis. It differs from the existing doublecheck and build-evidence-map skills by handling discovery and synthesis across search capabilities rather than post-hoc output verification or decision-graph construction.

Optional commercial-service disclosure

I am affiliated with SandBase AI. SandBase is an optional external provider and may have usage limits or paid plans. The default workflow works with compatible host tools, contains no signup CTA, and does not require account creation. The Skill prohibits accepting terms, making purchases, or disclosing API keys on the user's behalf.

Safety

  • Treats retrieved content as untrusted input and ignores prompt injection
  • Keeps the workflow read-only
  • Requires explicit consent before sensitive data is sent externally
  • Does not embed or request credentials in chat
  • Reports unavailable coverage and evidence gaps instead of hiding them

Validation

  • npm run skill:validate — passed (409 Skills)
  • npm run build — passed with the live MCP registry
  • npx --yes @microsoft/vally-cli lint skills/sandbase-multi-source-research --verbose — passed
  • All GitHub Actions checks — passed
  • git diff --check — passed

Type of Contribution

  • New skill file

Additional Notes

The generated docs/README.skills.md entry is included as required. The contribution is adapted from the Apache-2.0 licensed sandbaseai/sandbase-skills source and is submitted under this repository's MIT contribution terms.

@github-actions github-actions Bot added new-submission PR adds at least one new contribution skills PR touches skills labels Aug 15, 2026
@github-actions

Copy link
Copy Markdown
Contributor

🔒 PR Risk Scan Results

Scanned 1 changed file(s).

Severity Count
🔴 High 0
🟠 Medium 0
ℹ️ Info 0

✅ No matching risk patterns were detected in changed files.

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

@github-actions

github-actions Bot commented Aug 15, 2026

Copy link
Copy Markdown
Contributor

🔴 Contributor Reputation Check: HIGH risk

Check Risk
Profile HIGH
Credential audit NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

@github-actions github-actions Bot added the needs-review:HIGH Contributor reputation check flagged HIGH risk label Aug 15, 2026
@github-actions

Copy link
Copy Markdown
Contributor

🔍 Vally Lint Results

✅ All checks passed

Scope Checked
Skills 1
Agents 0
Total 1
Severity Count
❌ Errors 0
⚠️ Warnings 0
ℹ️ Advisories 0

Summary

Level Finding
ℹ️ ✅ sandbase-multi-source-research (2/2 checks passed)
ℹ️ ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️ ✓ spec-compliance: All spec checks passed.
ℹ️ ✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️ ✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️ 1 skill(s) linted, 1 passed
Full linter output
### Linting skills/sandbase-multi-source-research
✅ sandbase-multi-source-research (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

needs-review:HIGH Contributor reputation check flagged HIGH risk new-submission PR adds at least one new contribution skills PR touches skills

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants