AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Basecred

skill-kernel8901-ai-agent-skills-classification-basecred · by Kernel8901

Fetch onchain reputation profiles via BaseCred SDK (Ethos, Talent Protocol, Farcaster/Neynar). Use when the user wants to check wallet reputation, builder score, creator score, Ethos credibility, or Farcaster account quality for any 0x address. Supports multi-source unified profiles with level derivation and recency tracking.

↗ Repository
— No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-kernel8901-ai-agent-skills-classification-basecred

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ● Environment & secrets Used
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Basecred? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

BaseCred — Onchain Reputation Queries

Prerequisites

  1. Package installed in workspace: npm i basecred-sdk
  2. API keys in workspace .env:

`` TALENT_PROTOCOL_API_KEY= NEYNAR_API_KEY= # optional — enables Farcaster scoring `` Ethos Network requires no key.

Quick workflow

  1. Run the query script from the workspace:

``bash node /path/to/skills/basecred/scripts/query.mjs ` The script auto-locates node_modules/basecred-sdk and .env` by walking up from cwd. Run it with cwd set to the workspace.

  1. Parse the JSON output and present results to the user. Use the level tables in references/output-schema.md to translate raw scores into human-readable levels.

Presenting results

Summarize the three facets clearly:

  • Ethos — score + credibility level + review sentiment + vouches. Flag hasNegativeReviews if true.
  • Talent Protocol — builder score/level + creator score/level. Note verified status.
  • Farcaster — quality score (0–1) and whether it passes threshold.
  • Recency — recent / stale / dormant. Mention if stale or dormant as a caveat.

Highlight actionable signals: e.g. zero vouches on Ethos is an easy win, or a dormant Talent score that needs activity.

Reference

  • Output schema + all level tables: references/output-schema.md — read when you need to map scores → levels or explain the shape of a response.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills