agent-skills-hub

Agent Skills Hub appears to be a web app and API that periodically syncs GitHub repositories, cleans/deduplicates and classifies them, computes multi-dimensional quality scores (including an “Agent Readiness” dimension), stores results in Supabase, and serves listings, trending/rising/top-rated views, RSS/sitemap, plus endpoints for submitting skills and subscribing to a newsletter.

Evaluated Mar 30, 2026 (0d ago)

Repo ↗ DevTools ai-ml devtools api directory github-integration scoring mcp

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

The README shows use of environment variables for secrets (GITHUB_TOKEN, RESEND_API_KEY, ADMIN_TOKEN) which is generally good, but it does not specify transport/security controls (TLS requirements, header formats, token storage/logging), nor does it describe authorization rules per endpoint or error responses. No dependency/SBOM/CVE practices are stated in the provided content.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You want a continuously refreshed catalog of agent-related open-source projects with automated scoring and filters.

Avoid When

You need strong contractual guarantees (SLA, strong stability guarantees) or fully specified error/auth/retry behaviors for API consumers.

Use Cases

• Finding and comparing open-source agent skills, MCP servers, and related AI tools
• Building a “recommended tools” page or directory with quality scoring
• Discovering trending or high-rated repositories by velocity and composite scores
• Generating RSS feeds and sitemaps for directory SEO
• Submitting a GitHub repo for inclusion in the directory

Not For

• Acting as an execution environment for agent tools (it is primarily a discovery/scoring/catalog system)
• Providing guaranteed up-to-date truth about third-party projects between sync intervals
• Enterprise-grade compliance/data governance workflows without additional documentation

Interface

REST API

Yes

GraphQL

gRPC

MCP Server

SDK

Webhooks

Authentication

Methods: Admin token for API operations (ENV: ADMIN_TOKEN) (exact mechanism not specified in README)

OAuth: No Scopes: No

README lists ADMIN_TOKEN=sk-xxx but does not specify which endpoints require it (e.g., /api/submit-skill) or how it is presented (header/cookie/body). Most data endpoints appear public.

Pricing

Free tier: No

Requires CC: No

No pricing information provided in the supplied README content.

Agent Metadata

Pagination

offset/limit (implied by “Paginated list” but not specified)

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ README does not document request/response schemas or error codes for each endpoint.
⚠ Rate-limit handling is described for GitHub sync jobs, not for the public API endpoints.
⚠ Sync cadence (every 8 hours) means directory data may be stale during gaps.

Alternatives

GitHub search + curated lists (manual curation) General-purpose indexers/catalogs for open-source tools (directory websites) Custom pipelines using GitHub API + your own scoring/indexing logic

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for agent-skills-hub.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-30.