dogkeeper886

dogkeeper886/testlink-mcp

Command Claude Code

Write tests after implementation, adapted to the project's existing test infrastructure.

dogkeeper886/testlink-mcp

Skill Claude CodeCodex

Integration test design principles for a connected end-to-end flow. Use when writing, reviewing, refactoring, or adding test cases under cicd/tests/ (the YAML flow and the runner). Enforces one self-contained, connected flow with no hardcoded or standalone tests. The principles are project-agnostic; the concrete…

dogkeeper886/testlink-mcp

Skill Claude CodeCodex

How to format text for TestLink fields. TestLink stores rich-text fields (summary, preconditions, step actions and expected results) as HTML, so field bodies must be written with HTML tags and escaped entities — not plain text or \n. Use whenever building or updating a TestLink test case or suite, and as the markup…

dogkeeper886/testlink-mcp

Skill Claude CodeCodex

Guidelines for writing or changing this project's MCP server code — adding or modifying TestLink tools.

dogkeeper886/testlink-mcp

Skill Claude CodeCodex

Reviews a TestLink change after the fact to confirm it achieved the user's goal — the right entities exist, fields are correct and well-formed, and the source document is faithfully represented. Use after testlink-sync or any manual create/update in TestLink, before calling the work done. The review gate paired with…

dogkeeper886/testlink-mcp

Skill Claude CodeCodex

Reads a source document — a spec, a GitHub issue, a markdown test-case file, a folder of them — and creates or updates the matching content in TestLink: requirements, test suites, test plans, builds, and test cases. Use when a QA engineer wants to import, sync, upload, or push content into TestLink from a document.…

dogkeeper886/testlink-mcp

Instructions file

Claude Code instructions for dogkeeper886/testlink-mcp, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

dogkeeper886/testlink-mcp

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

dogkeeper886/testlink-mcp

Agent

Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.

dogkeeper886/testlink-mcp

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

dogkeeper886/wpa-mcp

Command Claude Code

Push branch and open a pull request with issue linkage.

dogkeeper886/wpa-mcp

Command Claude Code

Start work on a GitHub Issue — create branch, implement, and track progress.

dogkeeper886/wpa-mcp

Command Claude Code

Merge an approved pull request and clean up.

dogkeeper886/wpa-mcp

Command Claude Code

Research a story and write the plan — the agreed approach — as ONE GitHub plan issue, then stop for human review.

dogkeeper886/wpa-mcp

Command Claude Code

Review the changes an issue was implemented with — do they deliver the issue, and do they stay surgical rather than sprawling beyond it?

dogkeeper886/wpa-mcp

Command Claude Code

Review a story for completeness and ensure it stays a goal document, not a spec.

dogkeeper886/wpa-mcp

Command Claude Code

Review the GitHub issues a story was broken into — do they cover the story, and does each stay a lean goal rather than a frozen spec?

dogkeeper886/wpa-mcp

Command Claude Code

Create a user story file from user input.

dogkeeper886/wpa-mcp

Command Claude Code

Break a reviewed plan (or a story) into GitHub task issues, each linked back to it.

dogkeeper886/wpa-mcp

Command Claude Code

Research best practices, study the project, and write its README — diagrams and all.

dogkeeper886/wpa-mcp

Command Claude Code

Check a README delivers for its reader, reads and looks right, and is true to the code.

dogkeeper886/wpa-mcp

Command Claude Code

Turn a reviewed test plan into readable test docs in docs/tests/ — reusing vetted steps where a reuse index is available, instead of re-inventing them.

dogkeeper886/wpa-mcp

Command Claude Code

Derive the scenarios that verify a story (or an on-request target) — the "what to test", before any test doc is written.

dogkeeper886/wpa-mcp

Command Claude Code

Check each test doc does one clear job, has observable steps, and traces back to its story — before it is bound and run.