ai-setup

Build, launch, and drive the mindwalk web UI end-to-end for verification.

Set up or troubleshoot Yassimba's curated agent skills, Pi packages, Herdr, and Herdr plugins through the ai-setup CLI. Use when the user asks to install this collection, configure Herdr, add one of its capabilities, update the setup, or diagnose installation problems.

Backlog management: use when the user mentions a backlog, asks what's next, wants work recorded before implementation, or wants queued ideas or specs prioritized, transitioned, completed, or removed; also use when another skill needs to record lifecycle changes.

Use when the user wants to brainstorm or explore an idea — a feature, product direction, or "what if" — before deciding whether it deserves a plan. Ideation only — ends in an idea brief, not a design.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (this repo's documented coding standards) and Spec (what the originating issue/PRD asked for). Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Use when creating a git commit — the user asks to commit, or a unit of work is complete and ready to commit.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Manual end-to-end walkthrough — drive the live app first-hand (CLI, API, web UI) and query the datastore directly. Trigger on "e2e", "smoke test", "manually test".

Adversarial UX test — drive the live web UI as the product's most tech-hostile persona to hunt friction, then filter the rant into RED/YELLOW/WHITE/GREEN verdicts. Trigger on "ux test", "friction test", "asshole user test".

Generate a visual architecture walkthrough for a feature in the current codebase. Use when the user asks how a feature works at a high level — "explain X", "how does X work", "trace the X flow".

A relentless interview to sharpen a plan or design.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Example-map a ticket or spec - grill the user for rules and concrete examples, write them into the ticket, ready to become the test list for the TDD loop.

Implement a piece of work based on a spec or set of tickets.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Grill me about specs for the workflows I want to build, within this workspace.

Pre-push quality gate + pull/merge request creation. Use when the user wants to ship, release, push a branch, or open a PR/MR — runs the project's own lint, type-check, and test gates first, then commits, pushes, and opens the request on the project's forge (gh or glab).

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in a local file, or native blocking links on a real tracker.

Add or update docstrings, doc comments, and inline comments in source code — any language. Use when the user wants docstrings written or fixed, a conversion to a doc style (NumPy, TSDoc, rustdoc), or a comment cleanup. Source files only — README/ADR/prose docs belong to write-documentation / write-readme.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.

Blueprint a change before building it — Mermaid diagrams of the design, held for approval before any code. Use before implementing non-trivial work — proactively or when the user asks to see the design first — or when another skill needs a design-approval gate.

Core agent-browser usage guide — read before running any agent-browser command. Use when the user asks to interact with, test, or automate a website — clicking, filling forms, extracting data, taking screenshots, logging in.

CNAP canon for Enexis infrastructure. Use when work involves CNAP, PAX, Enexis cloud landing zones or golden paths, `*.cnap.enexis.nl`, or when `terraform-engineer` or `pax-specialist` is active in an Enexis repo.

Generate draw.io diagrams — .drawio XML exported to PNG/SVG/PDF/JPG via the desktop CLI. Use when the user asks for draw.io specifically, or a requested diagram needs what Mermaid's auto-layout can't give — custom styling, swimlanes, or a rich shape vocabulary (network topology, ML/DL model figures). Default and proactive diagramming belongs to mermaid-skill.

Design infographics — structured visual summaries of a topic, dataset, or content. Use when the user asks for an infographic or infographic blueprint, or shares content and wants it presented visually ("can you make this visual?").

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", or issue key patterns.

Create Marp presentation slides — themed decks authored in Markdown. Use when the user asks for a Marp document or wants slides written in Markdown rather than .pptx.

Review-first git merge — preview incoming changes, merge --no-commit --no-ff, resolve conflicts with the user, commit only after review.

Generate Mermaid diagrams as code (.mmd) and export to PNG/SVG/PDF with mmdc. Use when the user wants a diagram — flowchart, sequence, class, ER, state, gantt, git graph, architecture, timeline, mindmap — proactively when explaining a system with 3+ components, a runtime flow, a schema, or a lifecycle, and when another skill (e.g. blueprint) needs a diagram authored or exported to an image.

Create, edit, or read .pptx files — decks, templates, layouts, speaker notes, comments, including extracting a file's text for use elsewhere. Use whenever a .pptx file is the input or output, and when the user asks for a deck, slides, or a presentation without naming another format (Marp/Markdown slides belong to marp-slide).

Use when writing Python 3.12+ — typed application code, async programming, CLI tools (cyclopts, rich), or pandas data manipulation.

Configure this repo for the engineering skills — issue tracker, domain doc layout, ai-docs gitignore. Run once per repo before first use of the other engineering skills.

Terraform infrastructure as code across AWS, Azure, or GCP. Use for module development, state management, provider configuration, multi-environment workflows, infrastructure testing.

Write software documentation structured by Diátaxis. Use when the user wants a tutorial, how-to guide, reference page, explanation doc, or user guide — "write docs", "document this", "we need a guide for X". Not for READMEs (write-readme) or docstrings (update-docstrings).

Use when writing prose humans will read—documentation, commit messages, error messages, reports, UI text—or when the user wants existing text to sound human rather than AI-written ("humanize this", "reads like ChatGPT").

Make the agent restate its last message in plain language.

Zoom out — map the modules and callers around unfamiliar code at a higher layer of abstraction.

Run a two-proposer deep-research workflow with an aggregating referee and an evidence-graded report.