50 tagged trust, measured the same way as everything else here.
Browse within: quality 15AI Safety 11ai-native 11certification 11scanner 11Evaluation 10compliance 10file-format 10metadata 10provenance 10
Skill Claude CodeCodex
Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires…
Skill Claude CodeCodex
Fetches weather forecasts using a weather API key.
Skill Claude CodeCodex
Fetches weather forecasts for a city.
Skill Claude CodeCodex
Fetches weather forecasts for a city.
Skill Claude CodeCodex
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…
mohamedzhioua/agent-done-or-not
Skill Claude CodeCodex
Proof-of-done enforcement gate — records fresh evidence before any agent can claim "done". Runs your verifying command (tests, build, lint, curl) through a tamper-evident gate that records the command, exit code, and SHA-256 of the output. Blocks completion on any failing, stale, or already-consumed receipt. Works…
Skill Claude CodeCodex
End-to-end verify, simplify, and ship the current change. Use when the user says "go" or "/go" at the end of an instruction, or explicitly asks to verify and PR. Detects what was touched (capability / API route / SDK / frontend / docs), runs the right verification, invokes /simplify, and opens a PR. Refuses to PR if…
Skill Claude CodeCodex
End-of-session verification — runs the close-check, then writes the handoff file and Journal entry, and surfaces loose threads.
Skill Claude CodeCodex
Use when switching the upstream vendor for a compliance capability (sanctions, PEP, adverse media, UBO, KYB, payments, embeddings, log sink). Prevents the cert-audit RED-2 failure mode where the methodology page named OpenSanctions for 3 days after the platform had moved to Dilisense. Forces the surface-update +…
Skill Claude CodeCodex
End-to-end verification of the trustcard behavioral verification engine (lib/behavior.js and the mcp-trustcard behavior CLI).
Skill Claude CodeCodex
Verify RFC documentation and HTML mockup assets for the trustcard npm install trust check RFC.
Skill Claude CodeCodex
Resolve and check MCP servers using MCPLookup's public identity and trust evidence. Use before recommending, installing, or connecting an MCP server; when identifying an official or first-party server; when comparing similarly named servers, packages, repositories, or endpoints; or when a user asks whether an MCP…
Skill Claude CodeCodex
A skill that ships every EchoLeak exfil shape.
Skill Claude CodeCodex
Intentionally vulnerable Solana skill used by tests/testsolanaprobes.py. Touches every SOL- failure mode.
Skill Claude CodeCodex
Clean Solana skill that all SOL probes should mark PASS. Used by tests/testsolanaprobes.py.
Skill Claude CodeCodex
Agent-to-agent payments, marketplace, identity, and trust scoring. Escrow is simulated via an in-memory SQLite ledger — no real funds are held. Stripe integration handles actual payment processing.