0 Fork 0

mirror of https://github.com/kevinveenbirkenbach/computer-playbook.git synced 2026-11-09 20:26:33 +00:00

Files

T

kevinveenbirkenbach da140094a1 docs(agents): split iteration loops and refactor Playwright SPOT

Split docs/agents/action/iteration.md into role.md, playwright.md,
workflow.md, and a scope-focused README. Move Certificate Authority
and Inspect rules into role.md. Rewrite playwright.md as a machine-
oriented state machine with explicit preconditions, procedure, exit
gates, and escape path.

Extract Playwright spec content MUSTs into the new contrib SPOT
docs/contributing/artefact/files/role/playwright.specs.js.md. Reduce
the agent-side spec and env.j2 pages to procedure only. Align the
framework SPOT and the test-e2e-playwright role README with the
central templates/package.json.j2 + files/playwright.config.js model
and images.playwright.version as single source of truth.

Sweep em dashes and sentence-case role headings across all touched
docs per documentation.md and readme_md.md rules.

2026-04-19 22:04:24 +02:00

8.0 KiB

Raw Blame History

Cheatsheet 📋

Copy-paste prompt templates the operator can hand to an agent to kick off a workflow. Each prompt routes the agent to its authoritative procedure file; this page is a navigational aid only and MUST NOT be treated as source of truth.

Replace every <placeholder> before sending.

Every prompt below instructs the agent to first clarify all open requirements through active listening, then act autonomously through to completion with as few follow-up questions as possible.

Selection Matrix 🧭

Situation	Use
Building a new feature, app, or larger change	Development
Fixing or evolving a single web app role with the deploy/test loop	Web Development Iteration
Running or validating tests for a specific scope	Testing
Writing or updating a Playwright spec for a `web-*` role	Playwright Tests
Cleaning up code, docs, or roles after a change	Refactor and Optimize
A GitHub Actions / CI run failed and needs triage	Pipeline Debugging
A local deploy is failing on the host	Local Deploy Debugging
Operator placed a `.log` or `job-logs.txt` file in the workdir for ad-hoc inspection	Log File Inspection
Staged changes are ready to be committed	Commit
A branch is ready to be opened as a pull request	Pull Request Creation
A branch needs to be pushed, validated via manual CI, and transitioned through the draft → ready-for-review cycle	Push, Trigger, Pull
A new requirement needs to be written	Requirement Creation
An existing requirement file needs to be implemented end to end	Requirement Implementation

Development 🧱

For any change with a documented acceptance scope, Requirement Implementation is the preferred entry point; use this prompt only when no requirement file exists or applies.

Follow the instructions from AGENTS.md, develop <feature-or-app> by following the procedure in docs/agents/action/develop.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: develop.md

Web Development Iteration 🔁

For any change with a documented acceptance scope, Requirement Implementation is the preferred entry point; use this prompt only when no requirement file exists or applies.

Follow the instructions from AGENTS.md, iterate on web app role <role> by following the procedure in docs/agents/action/iteration/role.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: Role Loop

Testing ✅

Follow the instructions from AGENTS.md, run and validate tests for <scope> by following the procedure in docs/agents/action/testing.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: testing.md

Playwright Tests 🎭

Follow the instructions from AGENTS.md, write or update the Playwright test for role <role> by following the procedure in docs/agents/action/iteration/playwright.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Ask upfront whether to scope changes to the Playwright files only or also to any other files that cause the tests to fail. Use mode /caveman ultra.

SPOT: playwright.md

Refactor and Optimize ♻️

Follow the instructions from AGENTS.md, refactor and optimize the affected files by following the procedure in docs/agents/action/refactor.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: refactor.md

Pipeline Debugging 🛠️

Follow the instructions from AGENTS.md, triage the failing CI run at <github-actions-run-url> by following the procedure in docs/agents/action/debug/pipeline.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: pipeline.md

Local Deploy Debugging 🧰

Follow the instructions from AGENTS.md, debug the failing local deploy of role <role> by following the procedure in docs/agents/action/debug/local.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: local.md

Log File Inspection 🔍

Follow the instructions from AGENTS.md, inspect the log file <path-to-log> by following the procedure in docs/agents/action/debug/log.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: log.md

Commit 💾

Follow the instructions from AGENTS.md, commit the staged changes by following the procedure in docs/agents/action/commit.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: commit.md

Pull Request Creation 📤

Follow the instructions from AGENTS.md, open a pull request for the current branch by following the procedure in docs/agents/action/pull-request.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: pull-request.md

Push, Trigger, Pull 📡

Follow the instructions from AGENTS.md, push branch <branch>, run it through the manual-CI draft cycle, and transition the PR to ready-for-review by following the procedure in docs/agents/action/push-trigger-pull.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: push-trigger-pull.md

Requirement Creation ✍️

Follow the instructions from AGENTS.md, create a new requirement for <topic> by following the procedure in docs/contributing/requirements.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.

SPOT: requirements.md

Requirement Implementation 🚀

If no requirement file exists yet for the work, run Requirement Creation first to produce one.

Follow the instructions from AGENTS.md, implement requirement docs/requirements/<NNN-topic>.md by following the procedure in docs/agents/action/requirements.md. Begin by clarifying every open requirement through active listening, then act autonomously through to completion with as few follow-up questions as possible. Use mode /caveman ultra.