/SKILL.md
Query builder reputation data via Talent Protocol API. Get Builder Rank, verify humans, resolve identities (Twitter/Farcaster/GitHub/wallet), search by location/country, get credentials, and enrich with GitHub data.
npx skillsauth add talentprotocol/talent-powers builder-dataInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Query professional data from Talent - a platform that tracks builders
| Variable | Required | Description | Get it at |
|----------|----------|-------------|-----------|
| TALENT_API_KEY | Yes | Talent API key | https://talent.app/~/settings/api |
| GITHUB_TOKEN | No | GitHub PAT for higher rate limits (60/hr → 5,000/hr) | https://github.com/settings/tokens |
Base URL: https://api.talentprotocol.com
Auth header: X-API-KEY: $TALENT_API_KEY
builder_score. Never blindly use the first result. If no result has a meaningful score, report that no confident match was found./accounts, then follow github-enrichment.mdrank_position; only show points when explicitly asked. If rank_position is null, fall back to points.| Endpoint | Purpose |
|----------|---------|
| /search/advanced/profiles | Search by identity, tags, rank, verification |
| /profile | Get profile by ID |
| /accounts | Get connected wallets, GitHub, socials |
| /socials | Get social profiles + bios |
| /credentials | Get data points (earnings, hackathons, etc.) |
| /scores | Get ranks/scores. Slugs: builder_score, builder_score_2025, creator_score |
| /human_checkmark | Check if human-verified. Response field: humanity_verified |
| /data_points | List available data point slugs |
| /data_issuers_meta | List all data issuers and credential slugs |
builder_score.rank_position. Only show points when explicitly asked. rank_position is often null — fall back to points.builder_score slug. API also returns builder_score_2025 (legacy) and creator_score.customQuery fail (302). Search broadly and filter client-side by standardized_location / location.builder_score. If no result has a meaningful score, report that no confident match was found.[ = %5B, ] = %5D, Space = %20per_page values above 25. Paginate with page param for broader searches.If talent-agent is installed (npm install -g talent-agent), it provides natural language search without manual API calls. It can also run as an MCP server (talent-agent --serve) for use in Cursor, Claude, and other MCP-compatible clients.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.