Algorithm Filing Assistant for Openclaw

Openclaw Skills turns AI product details into the right CAC filing path, required materials, submission steps, and ongoing compliance actions.

bettermen
v1.0.0
Jul 10, 2026
0
490
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install algorithm-filing

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install algorithm-filing using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Algorithm Filing Assistant?

Openclaw Skills is a regulatory filing assistant for AI large models and algorithms under China CAC requirements. It analyzes your product scenario, determines whether you need a large model filing, large model registration, algorithm filing, dual-new assessment, or no filing, then converts that decision into an actionable compliance plan.

It is built for teams shipping public-facing AI services, wrapped third-party model APIs, personalization/recommendation systems, and other algorithm-driven products. Openclaw Skills helps you prepare the filing materials, generate a security assessment report framework, guide system submission on beian.cac.gov.cn, and maintain post-filing compliance across changes, annual checks, logging, and content review.

Algorithm Filing Assistant Use Cases

  • You built or fine-tuned a self-developed large model and plan to offer public API access.
  • You wrapped a third-party filed model into a standalone application and need to confirm whether large model registration plus algorithm filing applies.
  • You provide AI-generated text, image, audio, or video services and need the correct algorithm filing type.
  • You run recommendation, ranking, filtering, search, or personalization logic that may require algorithm filing.
  • You need a CAC-ready materials checklist, including legal entity documents, responsible person records, ICP/permit information, and filing commitments.
  • You need a security assessment report outline aligned to the filing type and current regulatory expectations.
  • You are submitting through beian.cac.gov.cn and want a step-by-step workflow for registration, algorithm information upload, and review.
  • Your filing was rejected and you need a structured remediation plan based on common rejection reasons.
  • Your filing is already approved and you need a post-filing compliance plan for changes, annual self-checks, logs retention, and public notice requirements.

How Algorithm Filing Assistant Works

  1. Collect the product profile: company identity, model source, deployment mode, whether the service is public-facing, the output types it generates, and whether it performs ranking, recommendation, filtering, or other algorithmic decisions.
  2. Classify the compliance path: Openclaw Skills maps the scenario to large model filing, large model registration, algorithm filing, dual-new assessment, or no filing, and explains the legal and operational rationale.
  3. Generate the materials checklist: it assembles the required base materials plus any model-specific, algorithm-specific, or product-linked attachments needed for submission.
  4. Draft the security assessment framework: it produces a structured outline for the relevant report, including the data, evidence, risk dimensions, and controls expected by the filing process.
  5. Guide the filing workflow: it walks through account registration, subject review, algorithm information entry, product binding, commitment confirmation, and review submission on beian.cac.gov.cn.
  6. Support post-filing operations: it outputs ongoing compliance actions for public notice, change reporting, annual self-checks, log retention, content review, and re-filing when the product changes.
  7. Handle rejections and revisions: if the submission is bounced back, Openclaw Skills maps the issue to common rejection reasons and generates a targeted correction plan.

Algorithm Filing Assistant Setup

  • No local package installation is required; this is a prompt-driven Openclaw Skills workflow.
  • Prepare a concise product description before invocation: company type, model type, public exposure, API/app form, algorithm behavior, output type, and content safety controls.
  • If you have Tencent Docs or Tencent Docs Enterprise connected, enable the connector so generated filing docs can be exported directly; otherwise, outputs stay in Markdown.
  • Use the skill by describing your AI product and asking for filing classification, materials, and submission guidance.
# No CLI installation is required.
# Provide the agent with a product summary such as:
# "I have a self-developed text generation model serving the public via API."
# Then request:
# "Determine the filing type, required materials, and security assessment framework."

Algorithm Filing Assistant Data Schema & Taxonomy

Layer Artifact Purpose Source Rules / Taxonomy
Input profile Product and organization description Captures the facts needed to determine compliance scope entity type, public-facing status, model origin, API/app wrapping, personalization, ranking/filtering, output media, internal-only use
Filing classification Compliance decision matrix Maps the scenario to the correct filing path large model filing, large model registration, algorithm filing (generative synthesis, other), dual-new assessment, no filing, change filing, annual review, cancellation
Materials package Material checklist Produces the required submission attachments business license, legal rep ID, responsible person ID/work proof, ICP filing/permit, commitment letter, algorithm responsibility statement, product-linked evidence
Report framework Security assessment outline Structures the filing report by required dimensions large model: data safety, model safety, generated content safety, protective measures; algorithm: template-based multi-dimension risk assessment and defenses
Filing workflow Submission playbook Guides form completion and review steps subject registration, algorithm info submission, product-function binding, approval waiting, revision after rejection
Post-filing compliance Ongoing control plan Tracks obligations after approval public notice, change reporting within 10 working days, termination cancellation within 20 working days, annual self-checks, log retention, content review
Rejection remediation Correction log Converts review feedback into a revised submission rejection reason, impacted section, evidence gap, fix plan, resubmission status
Reference files Markdown knowledge assets Standardizes reusable guidance references/material-checklist.md, references/security-assessment-framework.md, references/filing-workflow.md, references/common-rejection-reasons.md

Metadata taxonomy

  • filing_type: large_model_filing, large_model_registration, algorithm_filing_generative, algorithm_filing_other, dual_new_assessment, no_filing
  • stage: planning, material_prep, document_drafting, system_submission, review, post_filing, remediation
  • risk_area: data_legality, content_filtering, copyright, personal_information, training_safety, prompt_injection, minors_protection, public_opinion
  • control_metric: external_data_share, risk_coverage, content_test_count, refusal_test_count, manual_review_rate, log_retention_months, compliance_threshold

Key numeric checks used in outputs

Metric Target
External data share <= 30%
Risk coverage >= 17 categories
Content test questions >= 2000
Refusal test questions >= 500
Sensitive-scene refusal rate >= 95%
Manual review rate >= 10%
Log retention >= 6 months
Security assessment report length 60-90 pages
Personal information detection after masking 0
Model safety test coverage 31 risk scenarios
Overall compliance threshold >= 90%

Algorithm Filing Assistant Advanced Features

  • Multi-path compliance classification for large model filing, algorithm filing, large model registration, dual-new assessment, and no-filing scenarios.
  • Auto-generated materials checklists tailored to the product type, deployment form, and current filing stage.
  • Security assessment report frameworks aligned to the current filing template and GB/T 45654-2025 expectations for large models.
  • Step-by-step submission guidance for beian.cac.gov.cn, including account registration, algorithm information entry, and review readiness.
  • Rejection analysis and remediation planning based on common CAC review failure patterns.
  • Post-filing compliance playbooks covering public notice, change management, annual self-checks, and log retention.
  • Threshold-based risk checks that surface missing evidence, weak controls, or insufficient coverage before submission.
  • Tencent Docs connector support for exporting generated filing documents directly into collaborative workspaces when available.
  • Markdown-first fallback output for environments without external document connectors.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*