发现 Skills

Contract review skill that adds comment-based issue annotations without changing original text. Enforces a three-layer review (basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and generates a contract summary, consolidated opinion, and Mermaid business flowchart (with rendered image). Output language must follow the contract’s language.

Use when building knowhere from source, configuring build options (CPU/GPU/DISKANN/ASAN), or troubleshooting compilation errors

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Visually validate frontend changes in a PR by capturing screenshots and analyzing them with Claude Vision. Use when a PR modifies page or React component files (.tsx, .css) and requires visual approval before merge.

ChatGPT use cases and prompts for IT teams | Part of naiba-openai-work-assistant

Use when listing, renaming, deleting, pruning, exporting, or cleaning up Hermes Agent sessions. Includes ghost/orphan detection, consistency checks, lineage-aware operations, and starred-session protection.

LLM-maintained knowledge wiki — ingest papers, query knowledge, lint for consistency

Infer transcription-factor regulons and per-cell TF activity from single-cell RNA-seq using pySCENIC (GRNBoost2 + cisTarget + AUCell). Use when you have ≥500 cells of scRNA-seq, want de-novo TF→target relationships supported by motif evidence, and have 16GB+ RAM and a few hours of runtime.

Queries Tilt resource status, logs, and manages dev environments. Use when checking deployment health, investigating errors, reading logs, or working with Tiltfiles.

Execute SQL queries against IDA databases with idasql (direct CLI, HTTP, MCP).

Copy or move a file

Implementation patterns for on-device FoundationModels, quantization, optimization, and privacy-aware inference.

Use when you want a standard run_id folder (manifest + stdout/stderr logs) for a command under trace/runs/, plus an optional ledger entry (default: trace/TRACE_RUNS_LOCAL.md).

(1) B2B outbound prospecting — ICP definition, account targeting, cold outreach sequencing, and pipeline generation for consistent top-of-funnel growth.

Read-only: Calculates Days of Supply (DoS) and sell-through rate per SKU and location for replenishment planning.

Run accessibility audits with axe-core and screen reader testing for desktop applications

Anaplan connected planning for territory and quota management

Deep integration with axe-core for automated accessibility testing. Execute accessibility scans, interpret WCAG violations, generate compliance reports, and integrate with Playwright/Cypress for comprehensive a11y testing.

Specialized skill for generating C4 model architecture diagrams. Supports Structurizr DSL, PlantUML, and Mermaid formats with multi-level abstraction (Context, Container, Component, Code).

Manage care transitions across settings, including discharge planning, medication reconciliation, follow-up scheduling, and coordination of post-acute care.

Static code analysis, technical debt assessment, engineering velocity metrics

AI-powered content optimization and SEO writing assistance

CVE and CWE database querying and management

Distillation column design skill for tray/packing selection, hydraulic analysis, and column optimization