Agent skills for DeepSeek Harness

Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship…

Automates the installation, virtual host configuration, ACME TLS issuance, and Docker reverse proxy setups for N.WTF Nginx on Debian…

Use when building n8n AI Agent / LangChain clusters — tools, memory, RAG, structured output, system prompts, sub-workflow-as-tool, or…

Build, test, and deploy n8n workflows via REST API with incremental testing.

Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance.

Use when working with n8n's built-in Data Tables, designing schemas, inserting/updating/upserting rows, deduping, or querying.

Use for batching, pagination, "for each", Loop Over Items, Split Out, Aggregate, rate limits, or processing arrays in n8n.

Use when extracting reusable n8n logic, multi-step builds, sub-workflow triggers, tagging for discovery, passthrough vs Define Below…

Expert guide for interpreting and fixing n8n validation errors.

Use when packaging datasets, models, prompts, or annotation materials for a NAACL-bound submission — building the artifact around the…

Use when converting a paper accepted to NAACL Main or Findings into its final ACL Anthology version — merging promised revisions…

Use when designing or auditing the experimental program of a NAACL submission — matching evidence to language-coverage claims, keeping…

Use when deciding what goes into the content pages, the uncounted sections, the appendix, and the optional uploads of a NAACL-bound ARR…

Use when deciding whether a project should target NAACL rather than ACL, EMNLP, EACL, AACL, LREC-COLING, TACL, or an ML venue — weighing…

Use when revising the prose of a NAACL submission — scoping every claim to the languages and varieties actually tested, presenting…

Rules for identifier names that are clear and precise - describe behavior not timing, cut filler words, match the abstraction level, name…

Namely integration via Apideck's HRIS unified API — same methods work across every connector in HRIS, switch by changing `serviceId`.

Establish naming rules for components, tokens, and layers with patterns and worked examples.

Guides experimental study designs, manipulation checks, statistical reporting, and causal mechanisms tailored for Nankai Business Review…

Guides and sequences manuscript preparation, theoretical positioning, and peer review workflows tailored for Nankai Business Review…

AI image generation and editing using Google Gemini models (Nano Banana).