Context-dependent editorial style rules for academic writing — APA7, Chicago, MLA judgment calls

Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.

Generate and verify integrity manifests for AI agent plugins and tools -- detect tampering, enforce version pinning, and establish supply chain provenance (the SLSA/Sigstore gap for agent ecosystems).

This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming conventions, actionable error recovery messages, MCP server design, tool-set consolidation, and deciding when to add or remove an individual tool. Use this when the unit of work is a single tool or a set of tools. Route project-shape, pipeline architecture, and task-model-fit decisions to project-development; route deciding whether to introduce sub-agents to multi-agent-patterns.

Recognize and prevent confabulation — when you don't know, say so.

Calibrated human-AI collaboration with creative latitude — trust calibrated to reliability, creativity preserved with validation.

Assess active Markdown brain files in a local AI agent project or plugin source without changing it. Use before modifying a brain or reviewing declared instructions, skills, prompts, agents, bundled Markdown resources, and research documentation.

In PowerShell, inline JSON for Cost Management API causes "Unsupported Media Type" errors:

Time Saved: 1-2 hours debugging identity and RBAC

Azure OpenAI API patterns for rate limiting, function calling, error handling, and token optimization

Time saved: 2-4 hours per issue

Markdown-to-PDF pipeline via Pandoc and LuaLaTeX with emoji rendering, dual output, and print-ready formatting

Brand hierarchy, visual identity, asset deployment, platform-specific branding guidelines

Convert a Marp Markdown file to HTML, PDF, or PowerPoint using marp-cli. Use when asked to "build slides", "export presentation", "convert to PDF", "generate PPTX", "marp build", or "export deck". ...

VS Code Chat API patterns.

GROW model, active listening, developmental feedback, and team growth approaches

When extracting hardcoded data to JSON, field values silently drift:

Template-driven layouts require code changes for structural updates:

Data pipeline quality assurance — anomaly detection, schema drift, null ratio monitoring, freshness checks, and safe-write protection for reliable data engineering

Ingestion patterns for CSV, JSON, REST API, SQL, Excel, and Parquet -- guides an LLM through loading data from any common source