Use when reviewing, designing, or modifying Java enterprise systems that may support intermediary services, hosting services, online platforms, marketplaces, content moderation, recommender systems, advertising delivery, complaint workflows, transparency reporting, or systemic-risk evidence under the EU Digital Services Act. This should trigger for requests such as Review a Java online platform for DSA controls; Design notice-and-action or appeal workflows; Add recommender, ad transparency, moderation, audit, researcher access, or privacy-safe observability evidence; Assess online-platform transparency controls before production release. Part of Plinth Toolkit
npx skills add https://github.com/jabrena/plinth --skill 807-regulations-eu-digital-services-act
Use this Skill to review Java enterprise applications, online platforms, marketplaces, hosting services, content moderation tools, recommender systems, advertising systems, complaint workflows, transparency reporting pipelines, operational dashboards, or audit evidence that may require Digital Services Act-aware engineering controls.
Apply this Skill to determine what engineering controls, operational evidence, and escalation paths are needed before a Java system is released, connected to production traffic, used for online platform operations, or relied on for content moderation, recommender, advertising, complaint, or systemic-risk workflows.
This Skill is not legal advice. It helps Java engineers, architects, tech leads, platform teams, trust-and-safety teams, and reviewers identify when Digital Services Act concerns may apply and how to translate online platform expectations into enterprise architecture controls such as content decision audit logs, moderation workflow state, notice intake and response tracking, recommender and ranking explanation evidence, advertising transparency metadata, user controls, complaint and appeal workflows, risk assessment evidence, incident escalation, data access for auditors or researchers where applicable, and privacy-safe observability.
The purpose of this Skill is to increase awareness of potential gaps in the system and create engineering evidence for qualified review. The response produced by this Skill does not represent legal advice, a legal opinion, or a final regulatory determination.
The main question is:
> When does a Java enterprise system require Digital Services Act-aware online platform controls, and what should developers build differently?
External reference: Regulation (EU) 2022/2065 Digital Services Act.
Digital Services Act chapters summary reference: Digital Services Act chapters summary.
Java engineering examples reference: Digital Services Act engineering examples.
Report template asset: Digital Services Act engineering review report template.
This Skill applies to:
Treat intermediary classification, hosting or online-platform classification, very-large-online-platform or very-large-online-search-engine scope, illegal-content policy, advertising or recommender interpretation, audit or researcher access duties, systemic-risk conclusions, and regulatory interpretation as governance decisions for legal, compliance, trust-and-safety, privacy, security, product, risk, and executive accountability owners.
Engineering teams should still create evidence that makes those decisions reviewable:
Translate Digital Services Act concerns into engineering controls for Java enterprise systems. Do not provide legal advice or replace review by legal, compliance, trust-and-safety, privacy, security, product, risk, audit, research-access, or executive accountability owners.
Read references/807-regulations-eu-digital-services-act-chapters-summary.md, references/807-regulations-eu-digital-services-act-engineering-examples.md, and assets/reports/807-eu-digital-services-act-engineering-review-report-template.md in that order. Use the chapters summary for Digital Services Act chapter, article, scope, liability, due diligence, transparency, online platform, marketplace, VLOP/VLOSE, supervision, enforcement, and owner-handoff context. Use the engineering examples for Java control patterns such as content decision audit logs, moderation workflow state, notice intake and response tracking, recommender and ranking explanation evidence, ad transparency metadata, user controls, complaint and appeal workflows, risk assessment evidence, incident escalation, data access for auditors or researchers where applicable, and privacy-safe observability. Do not start implementation review until the chapters summary, examples reference, and report template are understood.
Identify service context, possible intermediary-service signals, hosting signals, online-platform or marketplace signals, online search or recommender signals, advertising workflows, trader interactions, user-generated content, terms and policy owners, content moderation decisions, user-redress paths, active-recipient evidence, VLOP/VLOSE indicators, deployment geography, data stores, observability systems, and governance owners. Escalate unclear intermediary or platform classification, VLOP/VLOSE status, illegal-content interpretation, advertising or recommender interpretation, audit or researcher access duties, systemic-risk conclusions, and regulatory interpretation to legal, compliance, trust-and-safety, privacy, security, product, risk, audit, research-access, or executive accountability owners.
Review Java code, configuration, controllers, DTOs, moderation services, policy engines, workflow state machines, persistence models, message schemas, search or ranking code, recommender configuration, ad delivery metadata, user-control settings, complaint and appeal records, transparency reporting jobs, logs, metrics, traces, audit exports, runbooks, tests, deployment workflows, and provider documentation. Check for gaps between claimed DSA controls and reviewable evidence.
Map Digital Services Act concerns to engineering actions: scope inventory, content decision audit logs, notice-and-action tracking, statement-of-reasons records, moderation workflow state, trusted flagger routing, misuse protections, complaint and appeal workflows, recommender explanation evidence, ranking controls, user controls, ad transparency metadata, trader traceability, transparency reporting, minor-protection controls, privacy-safe observability, incident escalation, and VLOP/VLOSE risk, audit, and researcher-access evidence where applicable.
Use assets/reports/807-eu-digital-services-act-engineering-review-report-template.md to produce a concise engineering review with scope, evidence reviewed, Digital Services Act risk signals, potential violation or non-compliance signals, engineering gaps, recommended controls, owner handoffs, residual risks, release decision, and validation steps. State explicitly that intermediary classification, platform classification, VLOP/VLOSE status, illegal-content determinations, advertising or recommender interpretation, audit or researcher access duties, systemic-risk conclusions, and regulatory interpretation require qualified owner review.
For detailed guidance, examples, and constraints, see:
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says \"resubmit pipeline\", \"重投流程\", \"port paper to <new venue>\", \"resubmit to <venue>\", \"tighten paper for resubmission\", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says \"resubmit pipeline\", \"重投流程\", \"port paper to <new venue>\", \"resubmit to <venue>\", \"tighten paper for resubmission\", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
This skill should be used when user encounters "paper-search MCP error", "Docker not found", "Docker not running", "paper search not working", or needs help configuring paper search integration.
Submit recoverable SSH-direct research Runs with live progress cards and model-free monitoring.
公众号选题|爆款标题|热点追踪|系列策划 — 公众号 AI 选题与标题生成,覆盖热点调研、选题策划、起标题、写摘要、系列排期。面向自媒体编辑、内容运营。触发词(**单独触发仅限对已有标题/摘要的修改**):「改标题」「换个标题」「重起标题」「优化标题」「标题再想想」「换个标题试试」「改摘要」「重写摘要」「优化摘要」「摘要再优化下」。新做选题、起新标题、策划系列/内容日历、追热点都请走 aws-wechat-article-main;需要多环节串联(写+审+排+配图+发)也走 main。
Take jabrena/807-regulations-eu-digital-services-act from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.