sumsub-create-cross-check-preset
Create or update a Sumsub cross-check preset (name/address comparison rules between POI and POA documents) via POST/PATCH /resources/api/agent/crossCheckPresets and GET /resources/api/agent/crossCheckPresets/{id}. TRIGGER ONLY when the user EXPLICITLY asks to override how cross-checks compare names or addresses — e.g. "switch name match to strict", "allow fuzzy address match", "ignore middle-name mismatch", "create a custom cross-check preset". SKIP by default — Sumsub ships sensible defaults tuned for the best conversion and approval rate, so most clients should NOT create a custom preset. SKIP for level creation (the default cross-check preset auto-applies to every level), for general KYC config, or any request that doesn't specifically name "cross-check rules", "name comparison", or "address comparison".
- Installs
- 1.2K
- Last 24h
- +16
- Trending rank
- #6725
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/sumsub/agent-skills --skill sumsub-create-cross-check-preset- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads sumsub-create-cross-check-preset automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Sumsub — Create / Update Cross-Check Preset
⚠️ Read this before running this skill.
Sumsub's default cross-check preset is tuned for the best balance of conversion and approval rate. Most clients should not override it. If the user hasn't named a specific comparison they want to change, stop and say:
"Cross-check rules are already configured for the best approval rate. We strongly recommend keeping the defaults. Tell me a specific tweak you need (e.g. 'allow fuzzy address match', 'ignore middle name') and we'll create a minimal override."
Only proceed if the user has a concrete, named tweak.
What is a cross-check preset
A cross-check preset controls how Sumsub compares the name and address that appear on the proof-of-identity (POI) document with the same fields on the proof-of-address (POA) document. The preset decides whether small differences ("Jonathan" vs "Jon", "Apt 4" vs "Apartment 4") are accepted or flagged as mismatches.
Don't confuse with PoA preset's
crossValidator. Thesumsub-create-poa-presetskill has an internal block calledcrossValidator(CrossValidatorSettingsonPoaDocumentSettings) withnameMode/addressMode/fuzzyThreshold— that's a per-PoA-preset override for the same comparison. A workspace-level CrossCheckPreset (this skill) supplies the default when no PoA-preset override applies. When a PoA preset'scrossValidatoris set, it wins for documents handled by that preset.
There are two preset modes:
basic— what this skill creates. PicksnameComparisonModeandaddressComparisonModefrom a small enum, plus optional ignore-flags. Best for almost everyone.advanced— per-rule manual configuration. Not supported via the public API (POSTreturns403 Forbidden — Advanced cross-check presets cannot be managed via API). Has to be done in the dashboard.
Endpoints
| Method | Path | When |
|---|---|---|
POST | /resources/api/agent/crossCheckPresets | Create a new preset. Body must NOT include id. |
PATCH | /resources/api/agent/crossCheckPresets | Update an existing preset. Body MUST include id. |
GET | /resources/api/agent/crossCheckPresets/{id} | Read one preset back (verify what landed; resolve title from a known id). |
All require permission manageClientSettings. Body shape is the
cross-check preset schema —
client-settable fields only.
Auth — App Token + secret (sandbox only)
This skill talks to the public Sumsub API and signs each request per
the authentication reference.
The full how-it-works writeup lives in the sumsub-api-auth
skill — read it if you hit 401 Invalid signature.
⚠️ Sandbox tokens only. Do not accept or use a production App Token here — cross-check rules affect every verification on the workspace. If the user offers a prod token, refuse and ask them to generate a sandbox pair at https://cockpit.sumsub.com/checkus/home?sbx=true (Connect Sumsub to your AI agent -> Build & configure -> Generate token). Token + secret are shown once — copy both before closing the dialog. The helper scripts enforce this — they reject tokens that don't start with
sbx:.
| Var | Example |
|---|---|
SUMSUB_APP_TOKEN | sbx:... — sandbox App Token from the dashboard. |
SUMSUB_SECRET_KEY | The paired secret shown once at token creation. |
SUMSUB_BASE | Optional. Defaults to https://api.sumsub.com. |
If the user has already supplied credentials in conversation, reuse them; otherwise ask once before running. Never echo the secret back.
Procedure
- Confirm necessity — Restate the user's request in one sentence and re-state the recommendation to keep defaults. If they have a specific named tweak, proceed. Otherwise stop.
- Translate the user's intent into the compact spec (below). Map their
ask to
nameComparisonMode/addressComparisonMode/ ignore-flags. - Validate —
titlenon-empty (≤256 chars);modeisbasic(advanced is forbidden via API); every comparison mode is a valid enum. - Generate payload — run
${CLAUDE_SKILL_DIR}/scripts/build_cross_check_preset.pywith the compact spec on stdin → full payload on stdout. - Create vs. update:
- New preset — POST via
${CLAUDE_SKILL_DIR}/scripts/post_cross_check_preset.sh. Payload must NOT includeid. - Update existing — first GET via
${CLAUDE_SKILL_DIR}/scripts/get_cross_check_preset.shso the user sees the diff, then PATCH via${CLAUDE_SKILL_DIR}/scripts/patch_cross_check_preset.sh. Payload must includeid.
- New preset — POST via
- GET the preset back and verify what landed.
- Report — lead with the human-readable summary, end with the id:
titleand a one-line summary of what was tweaked vs. the default.- Reminder: "Default cross-check rules are recommended for the highest approval rate; you've now overridden them for these comparisons — monitor conversion before rolling to production."
- Final line:
Preset ID (for level wiring / future PATCH): <id>.
Compact spec format (JSON or YAML on stdin)
title: "Strict address, lenient name"
description: "Allow nickname variants but require exact address."
mode: basic # ONLY basic — advanced is forbidden via API
basicSettings:
nameComparisonMode: weakContainment # one of: strict | weakContainment | def | ai
addressComparisonMode: strict # one of: strict | fuzzy
ignoreMiddleNameMismatch: true
ignoreProvidedInfoMismatch: false # if true, don't flag user-typed info that disagrees with the doc
Comparison-mode meaning
nameComparisonMode:
strict— exact match required.weakContainment— token-level containment (e.g. "Jon Smith" ⊆ "Jonathan Andrew Smith").def— Sumsub's recommended default; balances strictness and conversion.ai— ML-based comparison; tolerant of common variants and transliterations.
addressComparisonMode:
strict— character-level match (after normalisation).fuzzy— tolerant of abbreviations and word order.
The deprecated values (fuzzy, containment, fuzzyContainment on names)
are NOT accepted via this skill.
Outputs
On success, lead with the human-readable info:
titleand a one-line summary of what was tweaked vs. the workspace default.- Reminder: "Default cross-check rules are recommended for the highest approval rate; you've now overridden them — monitor conversion before rolling to production."
- Final line:
Preset ID (for level wiring / future PATCH): <id>.
On failure: HTTP status + Sumsub's description / errorName. Common causes:
403 Advanced cross-check presets cannot be managed via API—mode: advancedis dashboard-only. Switch tobasicmode.400with a validation message — one of the comparison-mode enums is wrong (e.g. a deprecatedfuzzy/containment/fuzzyContainmentname mode).
Worked examples
examples/strict-name-only.json— tighten name match, leave address on defaults.examples/lenient-for-emerging-markets.json— fuzzy address + ai name, ignore middle-name mismatch.
Hand-off — attaching the preset to a level
Cross-check presets are workspace-scoped. The default preset
auto-applies to every level; if you've created a custom one, you have to
attach it to specific levels by setting crossCheckPresetId on the level.
That's done with sumsub-create-level (or a direct PATCH on the level via
sumsub-api-generic).
See also
- references/cross-check-preset-schema.md — full schema, every enum, gotchas.
- Sumsub cross-check docs.
FAQ
What does the sumsub-create-cross-check-preset skill do?
Create or update a Sumsub cross-check preset (name/address comparison rules between POI and POA documents) via POST/PATCH /resources/api/agent/crossCheckPresets and GET /resources/api/agent/crossCheckPresets/{id}. TRIGGER ONLY when the user EXPLICITLY asks to override how cross-checks compare names or addresses — e.g. "switch name match to strict", "allow fuzzy address match", "ignore middle-name mismatch", "create a custom cross-check preset". SKIP by default — Sumsub ships sensible defaults tuned for the best conversion and approval rate, so most clients should NOT create a custom preset. SKIP for level creation (the default cross-check preset auto-applies to every level), for general KYC config, or any request that doesn't specifically name "cross-check rules", "name comparison", or "address comparison".
How do I install sumsub-create-cross-check-preset?
Run npx skills add https://github.com/sumsub/agent-skills --skill sumsub-create-cross-check-preset in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/sumsub-create-cross-check-preset/ (personal) or .claude/skills/sumsub-create-cross-check-preset/ (project).
Which AI agents can use sumsub-create-cross-check-preset?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is sumsub-create-cross-check-preset safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains sumsub-create-cross-check-preset?
It is published by sumsub in sumsub/agent-skills. It has 1,186 recorded installs.
More from sumsub/agent-skills
sumsub-api-auth
sumsub/agent-skills
Authenticate to the Sumsub API with an App Token + secret key (HMAC-SHA256 request signing). TRIGGER when the user asks to "call / sign / authenticate Sumsub API requests", debugs 401 Unauthorized / signature errors against api.sumsub.com, or needs a working request example with X-App-Token / X-App-Access-Sig / X-App-Access-Ts headers. SKIP only when a more specific skill in this repo (questionnaire/level/workflow/POA-preset/generic) already covers the user's actual task — those skills sign requests the same way and only need this one for auth deep dives.
sumsub-api-generic
sumsub/agent-skills
Catch-all fallback for any Sumsub API task that does NOT match a more specific skill (e.g. create-sumsub-level, sumsub-create-questionnaire, sumsub-api-auth). TRIGGER when the user wants to call, inspect, or debug a Sumsub API endpoint not otherwise covered — fetching applicants, listing levels, reviewing AML hits, exporting data, generating SDK tokens, anything against api.sumsub.com. The procedure — locate the right endpoint in the OpenAPI schema, read its request/response shape, build the payload, sign with App Token, and validate. SKIP whenever a narrower Sumsub skill already covers the request.
sumsub-check-skills-version
sumsub/agent-skills
Verify that the locally installed Sumsub agent-skills package is compatible with the published version before doing any Sumsub work. TRIGGER at the start of any task that touches Sumsub — Sumsub Dev MCP tools (mcpSumsubDev), KYC/AML workflows, applicants, checks, transactions, verification levels, verification links, questionnaires, fraud network, VASP lists, or anything Sumsub-related — so the user is warned before a stale skills package produces wrong results. Also use this skill when the user explicitly asks "are my Sumsub skills up to date / current", "is there a newer version of the Sumsub skills", or similar. Skip the actual update (the user runs npx skills add sumsub/agent-skills --all themselves) and skip any other Sumsub API or entity task — those have their own skills.
sumsub-create-poa-preset
sumsub/agent-skills
Create or update a Sumsub Proof-of-Address (POA) preset. POST /resources/api/agent/poaStepSettings to create new, PATCH same path to update (id in body), GET /resources/api/agent/poaStepSettings/{id} to read one back. TRIGGER when the user asks to "create / add / build / configure / update / edit a POA preset" or "PoA step settings", configure which proof-of-address document types are accepted (utility bills, bank statements, tax bills, etc.), set validity periods per provider type, enable POI-as-POA (accept identity doc as proof of address), tune the cross-validator (name/address fuzzy match between POI and POA), or add per-country POA overrides. SKIP for attaching a preset to a level (set poaStepSettingsId on the level instead, via sumsub-create-level), or for non-POA presets (cross-check presets, permission presets, etc.).
sumsub-manage-webhooks
sumsub/agent-skills
Manage Sumsub clientWebhooks (event subscriptions for applicantReviewed / applicantPending / kytTxn / etc.) — reads via /resources/api/clientWebhooks, writes via /resources/api/agent/clientWebhooks. Sandbox only — production webhooks must be created by a human directly in the Sumsub dashboard. TRIGGER when the user asks to "list / retrieve / show webhooks", "create / add / register a webhook", or "update / edit / change a webhook target / event list / secret / signature algorithm" against their sandbox tenant. SKIP for production webhook setup (refer the user to the dashboard), for unrelated webhook surfaces (Stripe / videoIdent / Fireblocks / NFC / partner-specific receive paths under /resources/webhooks/...), for testing one-off delivery (use the inspectionCallbacks/testWebhook endpoint directly), and for KYT-only webhook routing (that's managed in the Sumsub dashboard's KYT section). The public API does not expose delete or per-webhook delivery stats — for those, refer
sumsub-integrate-websdk
sumsub/agent-skills
End-to-end recipe for adding Sumsub KYC to a website or web app via the Sumsub WebSDK. TRIGGER when the user asks to "integrate / embed / add Sumsub", "show the KYC widget", "add WebSDK", "verify users with Sumsub on the frontend", supplies an existing levelName they want to plug into a page, or asks how to wire up access tokens / lifecycle events / webhooks for Sumsub verification in an arbitrary project. Covers the whole loop — level setup, server-side access-token signing, snsWebSdk init (vanilla canonical, React recipe), client lifecycle events, token refresh, source-of-truth via webhooks + applicant GET, sandbox testing, go-live checklist. SKIP for building the level/questionnaire/POA-preset payload itself (use the sibling skills), or for backend-only API calls with no frontend (use sumsub-api-generic).
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.