Claude Skills by dangeles

Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility of new tools for startup workflows. NOT for general research-direction strategy (use strategist) or scoping a specific feature's requirements (use requirements-analyst).

Use when organizing projects - detecting clutter, enforcing naming conventions, structuring directories, managing gitignore, or assessing project expandability. Triggers on project organization requests, file naming audits, or gitignore maintenance needs.

Use when implementing data analysis pipelines, statistical tests, or bioinformatics workflows in code (Python/R), particularly for genomics, transcriptomics, proteomics, or other -omics data. NOT for non-omics Python implementation (use senior-developer), pure statistical method selection without bioinformatics context (use statistician), or biological-validity questions about an existing analysis (use biologist-commentator).

Use when evaluating biological relevance, methodological appropriateness, or scientific validity of bioinformatics approaches, or when choosing between analysis methods/software tools.

Use when orchestrating multi-perspective brainstorming sessions requiring parallel agent execution, confidence-weighted synthesis, and optional workflow handoff. Coordinates 5 parallel perspective agents through a 4-stage pipeline (framing, diverging, converging, output).

Use when PHYSICS/ENGINEERING feasibility checks are needed — order-of-magnitude estimates, mass-balance / diffusion / fluid-flow models, identifying rate-limiting steps. NOT for statistical method selection (use statistician), algorithm complexity (use mathematician), or cost estimates (use economist).

Use when user needs to simulate fluid flow through bioprocess cartridges, bioreactor geometries, or membrane devices using FEniCSx. Covers Navier-Stokes flow, O2 species transport with Michaelis-Menten kinetics, membrane permeation, mesh generation from CAD geometry, and interactive 3D visualization.

Use when invoked by cfd-bioreactor orchestrator to provide rigorous mathematical analysis of FEM variational formulations, function space selection, stability conditions (inf-sup, Lax-Milgram), convergence rate estimation, and dimensionless number analysis for bioreactor CFD simulations. Produces mathematical specifications that the orchestrator translates into FEniCSx code.

Use when invoked by cfd-bioreactor orchestrator to provide adversarial engineering review of CFD simulation plans and generated code. Challenges mesh quality, boundary conditions, solver parameters, stabilization choices, and physical plausibility. Produces severity-rated review with approval status.

Use BEFORE marking any task complete, before user handoffs, or at quality checkpoints — verifies requirements satisfied, edge cases tested, tests pass, no regressions, deliverables ready. Triggers on 'are we done', 'is this complete', 'verify completion', 'ready to ship', 'ready to merge', 'is this ready', 'mark done'. NOT for general code review (use copilot) or pre-PR comprehensive review (use /pr-review-toolkit:review-pr).

Use when parameter values appear in multiple documents and consistency must be verified, especially for quantitative values that may differ due to measurement context or require reconciliation. NOT for citation verification (use fact-checker) or essay-style factual claims (use essay-fact-checker).

Use when reviewing code INLINE during development (real-time second opinion on correctness, bugs, edge cases) in an adversarial but collaborative manner. NOT for pre-PR comprehensive review (use /pr-review-toolkit:review-pr), post-PR automation (use /code-review), or formal review of junior-developer outputs (use senior-developer).

Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol). NOT for code review (use copilot) or factual-claim citation verification (use fact-checker).

Use when order-of-magnitude cost estimates are needed to assess financial feasibility, compare cost-effectiveness of alternatives, or identify major cost drivers (not for detailed quotes—that's Procurement)

Use BEFORE implementation, when planning new features or changes, to identify failure scenarios. PRE-implementation only — NOT for debugging existing bugs (use systematic-troubleshooter), not for reviewing already-written code (use copilot).

Use when documents need prose improvement, CLAUDE.md style enforcement (prose over bullets, bridging transitions, complete sentences), or final polish before archival

Use when factual claims in a science blog essay need verification with source URLs, or when proactive research enrichment would strengthen an argument.

Use when collaboratively writing a science blog essay through interactive thesis development, essay structuring, argument development, and paragraph writing with tiered fact-checking and voice matching.

Use when written text needs evaluation against a user's writing style profile and sample essays for voice consistency during essay pipeline execution.

Use when theoretical calculations need experimental validation, protocols must be designed with clear hypotheses and success criteria, or resource requirements (equipment, materials, expertise) must be estimated for proposed experiments

Use when documents with quantitative claims need citation verification, especially when every number must trace to a specific inline superscript citation before publication. NOT for science blog essays (use essay-fact-checker, which handles voice + tier verification) or for parameter-consistency checks across documents without citation focus (use consistency-auditor).

Use BEFORE starting a non-trivial feature OR after implementation when integration strategy is non-obvious — should this be a branch or direct commit? When to push? PR or direct merge? Triggers on "how should I structure this?", "branch or commit?", "ready to ship". Recommends staging ONLY files modified during the current session; the session-scope-guard PreToolUse hook enforces this structurally at commit time (independent of this skill). NOT for routine single-commit fixes (just commit dir...

Use when implementing well-scoped Python tasks with clear requirements, writing unit tests, and producing documented code for senior-developer review within a programming-pm pipeline. NOT for unscoped feature work (use feature-dev) or production-quality code requiring autonomous component-level decisions (use senior-developer).

Use when user asks to examine, edit, proofread, or compile LaTeX documents. Triggers on mentions of .tex files, pdflatex, xelatex, lualatex, latexmk, bibtex, biblatex, CV updates, or LaTeX paper editing on macOS.

Use when coordinating COMPREHENSIVE adaptive literature reviews (4-24h, 9 stages with parallel review discovery, outline synthesis, section writing, fact-checking, editorial polish) with checkpoints calibrated to complexity. Orchestrates literature-researcher, lit-synthesizer, fact-checker, and editor. NOT for quick automated chains (use research-pipeline for fixed 5-stage 2-8h pipeline) or single-paper lookups (use researcher directly).

Senior scientific author for literature review synthesis with authority to restructure, rewrite, and add analysis across outline creation, introduction framing, and final synthesis

Specialized literature review skill with review discovery, deep targeted research (15-30 papers per section), recency surveys, and convergence tracking for comprehensive literature reviews

Use when designing DETERMINISTIC algorithms, analyzing time/space complexity, selecting numerical methods (ODEs, optimization, linear algebra), or verifying mathematical correctness. NOT for statistical/probabilistic method selection (use statistician) or physics-based engineering feasibility (use calculator).

Use when encountering Jupyter notebook errors including kernel crashes, environment conflicts, import errors, memory issues, or data pipeline failures in notebooks

Create and document Jupyter notebooks for reproducible analyses

Orchestrate multiple independent agents running simultaneously, leveraging Claude's parallel tool execution capabilities to maximize throughput on multi-task requests.

This skill should be used when the user asks to "review this patent", "check the claims", "patent draft review", "is this claim accurate", "what's missing from this patent", or when a user pastes a patent draft or provides a .docx file path with patent content. Use this skill whenever a scientist needs to review a patent draft written by a lawyer — to check technical accuracy, identify gaps in claim coverage, or propose revised or new claim language. This is a multi-phase interactive workflow...

Protocol specification for multi-perspective brainstorming via 5 parallel agents with confidence-weighted synthesis. Executed by brainstorming-pm orchestrator.

Use BEFORE writing any Python plotting code (matplotlib, seaborn, plotly) — recommends chart type, color palette, axis treatment, and accessibility choices using Tufte, Cleveland, Wong, and Wilke principles. Returns a structured checklist + a paste-ready decision card. Also lints existing figures on request. Triggers on 'plot', 'chart', 'visualize', 'graph', 'figure', 'heatmap', 'histogram', 'scatter', 'bar plot', or any mention of matplotlib/seaborn/plotly.

Use when seeking analogous solutions from other domains, when stuck on a problem and need fresh perspectives, or when evaluating whether approaches from field X might apply to field Y. Requires structured problem statement.

Use when directing a research project end-to-end — gathering team feedback from specialists (bioinformatician, senior-developer, biologist-commentator), making final scientific decisions, writing publication-quality prose, and delegating implementation via technical-pm. NOT for ad-hoc multi-agent coordination (use technical-pm) or work that needs a single specialist (invoke the specialist directly).

Use when equipment specifications need matching to potential vendors, sourcing landscape must be mapped (catalog items vs. custom orders), or lead time considerations affect project planning

Use when coordinating complex research tasks requiring literature synthesis, quantitative validation, or multi-source integration across researcher, calculator, synthesizer, and fact-checker skills

Use when coordinating Python software development with multi-specialist pipelines (systems-architect, senior-developer, junior-developer, mathematician, statistician) and quality gates (architecture review, pre-mortem, code review, testing, version control). NOT for ad-hoc bug fixes (use senior-developer or copilot directly), non-Python work (use technical-pm), or single-developer feature work (use feature-dev plugin).

Use when requirements are vague, scope undefined, or success criteria unclear — refines what should be built before implementation begins. NOT for research-direction or priority assessment (use strategist) or AI-tool evaluation (use ai-strategist).

Use when you need a QUICK automated research-to-polish chain (2-8h, fixed 5 stages — researcher -> synthesizer -> devils-advocate -> fact-checker -> editor) with no checkpoints. NOT for adaptive multi-stage reviews with parallel agents and complexity-based checkpoints (use lit-pm for 4-24h comprehensive) or custom sequences (use technical-pm).

Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions). NOT for orchestrated multi-stage literature reviews (use lit-pm, which dispatches literature-researcher) or for writing final review synthesis prose (use lit-synthesizer).

Use when planning multi-chapter scientific research analyses with expert consultation — produces markdown analysis documents with pseudocode for RNA-seq, proteomics, or other data analysis workflows. NOT for software architecture (use systems-architect) or single-component design within an existing analysis (use senior-developer).

Use when implementing production-quality Python code within an assigned scope, including component-level architecture decisions, comprehensive testing, and formal code review of junior-developer outputs within a programming-pm pipeline. NOT for general/standalone code review (use copilot for inline, /pr-review-toolkit:review-pr for pre-PR, /code-review for post-PR).

This skill should be used when creating, modifying, or refactoring any Claude Code skill in this repository. It is the default entry point for all skill work — new skills from scratch, targeted edits, refactoring, and quality review alike. Trigger on "create a skill", "add a skill", "build a skill for", "make a skill that", "edit the X skill", "modify a skill", "refactor a skill", "improve the X skill", or any time a user wants to add or change a skill in this repository. Always prefer this o...

Use when selecting STATISTICAL methods (hypothesis tests, regression), performing power analysis, guiding uncertainty quantification (Bayesian/frequentist), or validating MCMC/Monte Carlo implementations. NOT for deterministic algorithm design or complexity analysis (use mathematician), nor physics/engineering feasibility (use calculator).

Use when research direction needs assessment, critical knowledge gaps must be identified, or priorities must be recommended based on impact, dependencies, and effort (especially at project milestones or when scope questions arise). NOT for evaluating AI tools or agentic workflows (use ai-strategist) or scoping/requirements gathering for a specific feature (use requirements-analyst).

Use when multiple reviews or paper notes need integration, cross-cutting themes must be identified, or project-specific implications must be drawn from disparate sources. NOT for literature-review-specific synthesis at publication quality (use lit-synthesizer) or for prose polish (use editor).

Use when encountering errors, bugs, unexpected behavior, or any problem requiring systematic debugging with extended thinking for complex multi-layer issues. NOT for trivial syntax/build errors that have an obvious fix (just fix them) or Jupyter-specific kernel crashes, import errors, or memory issues in notebooks (use notebook-debugger).

Use when designing software architecture, defining data structures, planning scalability, or making technical design decisions for complex Python systems — including bioinformatics pipelines, services, libraries, or analysis frameworks. NOT for single-component design within an existing architecture or routine class layout (use senior-developer).