[KGKallasmaa]

Adds a keenable-web-search skill that lets Copilot search the web and read pages as markdown through Keenable, with no API key.

Why: Copilot often needs information newer than its training data, such as a library's latest breaking changes, a changelog entry or a CVE note. Today there's no skill in this repo for live web search. Keenable has a keyless public tier, so the skill works on a fresh machine without anyone signing up for anything.

What it does:

• Prefers the Keenable MCP server (https://api.keenable.ai/mcp, tools search_web_pages / fetch_page_content) and includes the .vscode/mcp.json snippet.
• Falls back to two curl calls against the keyless HTTP endpoints (/v1/search/public, /v1/fetch/public) when MCP isn't configured.
• Gives a short workflow: describe the target page, narrow by site/date, read before citing, prefer primary sources, list URLs.
• States the limits (1,000 requests/hour per IP without a key) and that an optional KEENABLE_API_KEY lifts the cap. It never asks for a key in chat.

npm run skill:validate and npm run build were run. The curl examples were tested against the live endpoints.

Docs: https://docs.keenable.ai · MCP: https://docs.keenable.ai/mcp-server

[github-actions]

🚦 Submission status: 👀 Ready for review

Risk tier: merge-risk:high — Privileged execution, automation, or review-policy change
Required to merge: passing submission-gate checks plus 1 approval from reviewers with write access, including a maintainer with admin or maintain permission.

Why this tier

• Label needs-review:HIGH flags a high contributor-risk signal

Automated checks

Check	Status	Details
Line endings	✅ Passed	Passed · logs
Spelling	✅ Passed	Passed · logs
Generated README consistency	✅ Passed	Passed · logs
Skill validation	✅ Passed	Passed · logs
Skill lint (vally)	✅ Passed	Passed · logs
Risk scan	✅ Passed	Passed · logs
Contributor reputation	✅ Passed	Passed · logs
Duplicate resource scan	✅ Passed	Passed · logs
PR quality signal	⏭️ Skipped	Skipped by its workflow · logs

Review

• Approvals: 0/1
• Assigned reviewer: not assigned yet — comment /request-review to ask for one
• Review target date: not set
• Still needed: 1 more approval(s); an approval from a maintainer with admin or maintain permission
• The core-maintainers pool is not staffed yet; an approver with admin or maintain permission is required instead.

Commands

Command	Who	What it does
/rerun-checks	PR author, maintainers	Re-runs failed or incomplete checks and re-evaluates this gate
/request-review	PR author, maintainers	Asks the review rotation to assign a reviewer (adds needs-reviewer)

_{Updated for 7702134 · gate run · This comment is maintained automatically — see submission gate docs.}

[github-actions]

🔴 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]

🔒 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]

🔍 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	✅ keenable-web-search (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/keenable-web-search
✅ keenable-web-search (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

[KGKallasmaa]

/request-review

[github-actions]

🙋 Added needs-reviewer. Reviewer routing is assigning a reviewer now.

[aaronpowell]

Thanks for contributing. This skill’s execution path is Keenable-specific: it asks users to configure https://api.keenable.ai/mcp or call Keenable’s /v1/search/public and /v1/fetch/public endpoints, then points to a Keenable API key to lift the hourly cap (skills/keenable-web-search/SKILL.md, “Option A/B” and “Limits”). The workflow advice—writing focused queries, preferring primary sources, and listing URLs—is generic, while Copilot already provides web search. As submitted, this functions primarily as setup for a vendor search service rather than adding standalone Copilot capability, so we can’t include it.