agentic-coding-playbook

Query or contribute to syv.ai's shared company brain — the private 1brain GitHub repo (kunder, tilbud, teknik, strategi, wiki) — from any session, regardless of the current directory. Bootstraps a local clone when needed. Use when the user asks what syv.ai knows about a client or topic ("hvad ved vi om Krifa?", "har vi løst noget lignende før?"), wants something added to the brain ("tilføj til hjernen", mødenoter, læringer, nye dokumenter), or mentions 1brain or hjernen. All brain content is in Danish.

Write a syv.ai client proposal (tilbud, forslag, offer, PoC-beskrivelse, bud på udbud) in the company's fixed format and style, and render it as a branded PDF. Works from any session — bootstraps the private 1brain repo where the full proposal skill, templates and Typst PDF pipeline live. Trigger on opgavebeskrivelser, kravspecifikationer, SKI-udbud, RFPs and "lav et tilbud til …", also when the word "tilbud" isn't used directly.

Interviews the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Zooms out to give broader context or a higher-level perspective on a section of code. Use when you're unfamiliar with an area of code or need to understand how it fits into the bigger picture.

How to add or restyle a D3 diagram in the playbook docs (MkDocs Material). Use for any flowchart, diagram, chart, or graphic in docs/.

Use when a plan is multi-file, architecture-heavy, data-heavy, UI-heavy, ambiguous, or risky enough that the wrong direction would be expensive to undo. Renders the plan as a single self-contained HTML review surface — diagrams, file maps, annotated code, open questions — opened in the browser, with decisions captured in the terminal.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Lock down a repo and the working session for safe agent work. Installs deterministic PreToolUse hooks that hard-block destructive commands (destructive git, plus project-specific dangers), and establishes a ruthlessly-conservative posture that flags and demands explicit user approval before touching remote databases, internal systems, production, secrets, or customer data. Use when starting risky work, onboarding an agent to a sensitive codebase, or when the user runs /guardrails.

Set up a project's stack and dev-environment feedback loops — the agent's senses. For a new/empty repo, interview the user on the desired stack and scaffold it; for an existing project, detect the stack and wire up the dev env. Either way, install a format/lint/type/test gate that runs on every commit. Use when starting a project, onboarding to a repo, or when there's no automated quality gate yet.

Disciplined root-cause debugging for any bug, test failure, performance regression, or unexpected behavior. Build a feedback loop → reproduce → investigate → hypothesise → instrument → fix → regression-test. Use before proposing any fix, especially under time pressure or when a "quick fix" seems obvious.

Test-driven development with a disciplined red-green-refactor loop and tracer-bullet vertical slices. Tests verify behavior through public interfaces, not implementation. Use when implementing any feature or bugfix, when the user mentions TDD / red-green-refactor / test-first, or wants integration-style tests.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

One-command onboarding for the Syv.ai skills collection. Checks the environment (git, GitHub CLI auth), seeds a slim CLAUDE.md pointer if absent, confirms which skills resolved, and gives a short orientation. Use when a user has just installed the collection and runs /setup-syv-skills, or asks how to get set up to use the Syv skills.

Compacts the current conversation into a handoff document so another agent can pick up the work. Use when you want to hand off to a fresh session.

Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones — and present them as a visual HTML report. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Breaks a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when the user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turns the current conversation context into a PRD and publishes it as a GitHub issue (or a markdown file). Use when the user wants to create a PRD from the current context.

Create or edit agent skills with proper structure, a discoverable description, progressive disclosure, and bundled resources. Use when the user wants to write, create, build, or revise a skill, or asks how skills should be structured.

Use when you have a spec or requirements for a multi-step task, before touching code