shakestzd

wipnote orchestration patterns for AI-assisted development. Use when working on code in an wipnote project — provides delegation patterns, model selection, quality gates, and work tracking guidance. Activate when planning work, delegating to agents, debugging, building features, or managing tasks.

wipnote orchestration patterns for AI-assisted development. Use when working on code in an wipnote project — provides delegation patterns, model selection, quality gates, and work tracking guidance. Activate when planning work, delegating to agents, debugging, building features, or managing tasks.

wipnote orchestration patterns for AI-assisted development. Use when working on code in an wipnote project — provides delegation patterns, model selection, quality gates, and work tracking guidance. Activate when planning work, delegating to agents, debugging, building features, or managing tasks.

Plan development work using a triage-gated, blocks-first interview. Classify scope as trivial/standard/complex, then run 0/3/4 staged interview rounds through the current harness native ask-user tool when available, or plain conversation when it is not. Each stage elicits the VISUAL block first (file-tree, api-endpoint, data-model, wireframe/diagram) and derives the prose slice fields (what/why/done_when) from it — blocks are authored inline as the YAML is built, not in a post-pass. Produces slice-card YAML with grounded visual blocks and visible research provenance for external claims; pauses for human review; promotes approved slices to features. Use when asked to plan, create a development plan, or build a feature with design clarity first.

SECONDARY enrichment path — add or revise structured visual blocks (data-model, api-endpoint, file-tree, wireframe, diagram, tabs) on an EXISTING wipnote plan. Use for legacy plans drafted before blocks-first existed, or for ad-hoc later block additions/revisions — NOT for primary planning. New plans get blocks authored inline during the wipnote:plan interview (blocks-first); only reach for this skill when a plan already exists and needs blocks added or changed after the fact. Reads the live block catalog from wipnote plan blocks, adds grounded blocks to slices, regenerates the plan HTML, and links to the dashboard.

Generate a grounded visual recap for a work item, git range, or session. Runs wipnote recap to produce a self-contained HTML artifact grounded in the real diff, reads the artifact, writes an outcome narrative (secrets redacted), and links to the dashboard recap URL. Use when asked to recap, summarize, or visualize completed work.

Dual-critic review pass for a drafted plan. Runs DESIGN CRITIC and FEASIBILITY CRITIC agents in parallel against the plan YAML, then writes findings as critic_revisions on the affected slices. Use when asked to critique this plan, review plan, run plan critic pass, or before human review of a multi-slice plan.

Execute a parallel plan using dependency-driven dispatch. Checks file overlap among unblocked tasks, partitions into non-conflicting waves, and dispatches simultaneously. Merges completed work, then dispatches newly unblocked tasks. No manual wave sequencing.

USMLE Step 1 domain knowledge for generating NotebookLM podcast prompts. Contains the proven prompt template, chapter-to-vignette mapping, high-yield topic patterns, and pedagogical strategies that produce 100% source coverage in NotebookLM's Audio Overview. Load this skill when generating prompts for any Survivor's Guide to USMLE Step 1 chapter.

Use this skill when ready to compile a manuscript for journal submission, rebuilding after edits, or preparing a revision package. Triggers on "build upload package", "compile manuscript", "generate submission files", "rebuild manuscript", "prepare revision".

Use this skill when setting up or reviewing a manuscript project to ensure all numbers from data, figures, and tables are parameterized — never hardcoded in prose. Covers the Stats dataclass pattern, template placeholders, sync pipeline, and semantic validation. Triggers on "parameterize numbers", "stats dataclass", "hardcoded numbers", "sync sections", "data-driven manuscript", "validate prose", "manuscript numbers".

Use this skill when starting a new manuscript project, adding quartopress build pipeline to an existing project, converting a draft into a structured Quarto project, or setting up table/figure generation. Triggers on "scaffold manuscript", "set up manuscript", "new manuscript project", "quartopress init", "create manuscript structure".

Default prose style for all writing in this project. Traces how specific actors — corporations, regulators, physical systems, communities — make decisions that create consequences for the next actor in the chain. Applies chain-of-causation structure, named actors with active verbs, and the cascade reveal. Use for any section: capital flows, grid infrastructure, labor markets, utility regulation, material constraints, or environmental consequences. The style works for human actors and non-human constraints alike.

Use this skill when creating charts, applying the flowmpl design system, using concept frames, generating AI illustrations, working with palettes, or needing the full flowmpl API reference beyond flow diagrams. Triggers on "create a chart", "flowmpl chart", "design system", "concept frame", "AI illustration", "flowmpl palettes", "stacked bar", "waterfall chart", "annotated series", "flowmpl colors".

Use this skill when creating flow diagrams, causal chains, decision trees, process flows, or entity relationship diagrams using flowmpl's flow_diagram() function. Provides detailed API reference for nodes, edges, routing heuristics, and face overrides. Triggers on "flow diagram", "causal chain", "process flow", "decision tree", "entity diagram", "flow_diagram()", "node and edge".

FT Visual Vocabulary chart selection guide. Use when choosing chart types, evaluating whether a chart type matches the data relationship, proposing visualization alternatives, or when the user asks "what chart should I use", "is this the right chart", "what's a better way to show this", or describes a data relationship and needs a visualization recommendation.

Git-powered state awareness - track file changes, session context, decisions, and work history. Query what happened in previous sessions and during current session. Auto-activates for state queries and before duplicating work.

Delegate GitHub operations and research tasks to Copilot CLI to preserve Claude Code session limits. Automatically activates when detecting GitHub keywords (issue, PR, repo, commit) or research needs (compare, research, lookup, best practices). Offloads heavy operations to Copilot subprocess and returns compressed results only.

Expert-level git worktree troubleshooting, cleanup, and management. Use when users have worktree issues, conflicts, cleanup needs, or questions about git worktree commands. Activate for problems like stuck worktrees, locked files, orphaned branches, or worktree removal errors.

Help users discover Contextune capabilities and understand how to use natural language commands. Use when users ask about Contextune features, available commands, how to use the plugin, or what they can do. Activate for questions like "what can Contextune do?", "how do I use this?", "show me examples", "what commands are available?"

Expert guidance on parallel development workflows using git worktrees and multi-agent execution. Use when users mention parallel work, concurrent development, speeding up development, working on multiple features simultaneously, or scaling team productivity. Activate for questions about task decomposition, worktree management, or parallelization strategies.

Analyze and optimize parallel workflow performance. Use when users report slow parallel execution, want to improve speed, or need performance analysis. Activate for questions about bottlenecks, time savings, optimization opportunities, or benchmarking parallel workflows.

Efficiently research topics using parallel agents via Contextune's /ctx:research command. Use when users ask to research, investigate, find information about topics, compare options, or evaluate libraries/tools. Activate for questions like "research best X", "what's the best library for Y", or "investigate Z".

Systematic architecture analysis following Understand → Research → Specify → Decompose → Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".

Authoring jobsmith application Quarto artifacts: resume.qmd (single-page Typst PDF via awesomecv-typst extension), cover-letter-draft.md (markdown with click-to-copy code blocks), and index.qmd review pages (Quarto website with partials, callouts, and per-company SCSS themes). Use when editing or generating any of these three surfaces inside a jobsmith application directory.

Plan development work with a local-first interactive marimo notebook. Generates a YAML plan, populates slices and questions, runs dual-agent critique, opens the notebook for human review (approvals persist to .moplan/moplan.db), and finalizes the plan YAML as the deliverable. Use when asked to plan, create a development plan, or build a feature with design clarity first.

CRITICAL: Ijoka is installed. This skill defines the complete software development process for this project. Use this skill for ALL work - every coding session, every task, every feature. Ijoka tracks all activity, attributes work to features, and provides cross-session continuity. You MUST follow this process.

Create publication-quality figures for Plastic and Reconstructive Surgery journal using data-driven design principles and visual feedback. Apply professional medical styling, CMYK colors, 300+ DPI resolution, and ensure PRS compliance through iterative refinement. Use when user asks to create medical figures, statistical plots, before/after comparisons, validate figures, or prepare journal submissions. Keywords: PRS, medical visualization, journal figure, CMYK, 300 DPI, matplotlib, data visualization, publication ready, before/after, multi-panel, compliance.