dawid-dahl-umain

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

Plugin marketplace listing 5 plugins: aaid-tdd, aaid-bdd, implan, testing, code-quality.

dawid-dahl-umain/augmented-ai-development

Cursor rule Cursor

AAID (Augmented AI Development) - TDD workflow with disciplined RED/GREEN/REFACTOR cycles.

dawid-dahl-umain/augmented-ai-development

Cursor rule

Acceptance Testing Mode overrides standard AAID instructions for acceptance-testing-blueprint.

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

AAID (Augmented AI Development) - BDD/ATDD workflow using the Three-Layer Model for acceptance testing with developer-maintained architectural control.

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

AAID (Augmented AI Development) - BDD/ATDD acceptance testing workflow using the Three-Layer Model where the developer maintains architectural control and reviews all AI-generated code. Use when the user initiates acceptance testing or references AAID BDD. Trigger phrases include: "start BDD", "begin ATDD"…

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Validate acceptance tests against AAID BDD quality criteria. Scans for proper three-layer architecture, isolation patterns, state management, and stubbing practices. Produces pass/warn/fail table with specific findings. Do NOT activate for writing new tests, running tests, or general testing questions.

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

AAID (Augmented AI Development) - TDD workflow enforcing disciplined RED/GREEN/REFACTOR cycles with developer-maintained architectural control.

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

AAID (Augmented AI Development) - TDD workflow enforcing disciplined RED/GREEN/REFACTOR cycles where the developer maintains architectural control and reviews all AI-generated code. Use when the user initiates TDD or references AAID. Trigger phrases include: "start TDD", "begin AAID", "use test list", "RED phase"…

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

Code-quality skills for Claude Code. Currently a read-only dead code sweep: run the project's own static analyzer, triage what it flags against the ways code stays reachable without a visible caller, and report what is genuinely safe to remove.

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Find dead code in any codebase and report it. Never edits, deletes, or commits anything in the repository. Detects the project's toolchain, runs its static analyzer (knip, vulture, staticcheck, cargo-udeps, deadcode), triages candidates against the ways code stays reachable without a visible caller, and reports what…

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

Align on substantial work before execution, then record the plan in durable files a fresh agent can pick up cold. Includes optional Implan spike and retro skills.

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Manually invoked structured planning workflow for substantial work. Produces a self-contained Plan Directory holding a main plan, a mental model, a verification strategy, and a notes scratchpad, so a fresh agent or the user can pick the work up cold and execute it well. Also use these conventions when working inside…

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Capture a concise retrospective of completed work and persist it alongside an Implan, so future agents can learn from the outcome. Use when the user invokes "/implan:retro" or explicitly asks to record learnings from completed work alongside an Implan. Do not activate for team retrospective facilitation or general…

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Run a bounded experiment or temporary prototype that tests an important assumption before the real work begins. Works with an existing Implan wherever it lives, and works standalone otherwise. Produces a durable spike report for the user or a future agent. Use when the user invokes "/implan:spike" or explicitly asks…

dawid-dahl-umain/augmented-ai-development

Plugin Claude Code

Test-quality skills for Claude Code. AI-driven mutation testing, where Claude acts as the mutation engine to find weak tests, and agentic testing, where Claude drives the running app in a real browser to judge whether it is fit to release.

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

Use the running app in a real browser the way a person would and judge whether it is fit to release: functionality, responsiveness, accessibility, robustness, and anything else that would stop you shipping it. Use when the user says "browser test", "test in the browser", "test with the browser tool", "check it in…

dawid-dahl-umain/augmented-ai-development

Skill Claude CodeCodex

AI-driven mutation testing — Claude acts as the mutation engine. Analyzes source code, generates and applies mutations, runs tests, tracks killed vs survived mutants, analyzes test gaps, and recommends test improvements. No external mutation testing libraries. Use when user says "mutate", "mutation testing", "mutation…

dawid-dahl-umain/augmented-ai-development

Cursor rule

AAID (Augmented AI Development) - TDD workflow with disciplined RED/GREEN/REFACTOR cycles.