jmagly/aiwg

color-accessibility

WCAG accessibility analysis for color palettes including contrast ratios, compliance checking, and remediation suggestions. Use when user needs to verify colors meet accessibility standards.

Idioma do texto original: inglês

color-palette

Generate, analyze, compare, export, and suggest color palettes using color theory. Use when user asks about colors, palettes, color schemes, or needs help choosing colors for a project.

Idioma do texto original: inglês

color-trends

Research current color trends from Pantone, architecture, film, and design. Use when user asks about trending colors, popular palettes, or wants research-backed color inspiration.

Idioma do texto original: inglês

star-prompt

Prompt users tastefully to star AIWG after a successful regenerate or intake workflow.

Idioma do texto original: inglês

theme-manager

Research, compare, sample, select, persist, adapt, rotate, and archive reusable visual themes and design templates

Idioma do texto original: inglês

research-query

Search the local research corpus, read matching findings, and synthesize an answer with inline citations to REF-XXX sources. The "query" operation for the research pipeline.

Idioma do texto original: inglês

agent-loop-ext

Crash-resilient external agent loop with state persistence and CI/CD integration

Idioma do texto original: inglês

agent-loop

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

Idioma do texto original: inglês

auto-test-execution

Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

Idioma do texto original: inglês

cross-task-learner

Enable agent loops to learn from similar past tasks and share patterns across loops

Idioma do texto original: inglês

debug-memory

Query and manage the executable feedback debug memory

Idioma do texto original: inglês

execute-feedback

Execute tests on generated code and iterate until passing

Idioma do texto original: inglês

infer-completion-criteria

Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly

Idioma do texto original: inglês

ralph-abort

Abort a running agent loop and optionally revert changes

Idioma do texto original: inglês

ralph-analytics

Show analytics and metrics from agent loop execution history

Idioma do texto original: inglês

ralph-attach

Attach to a running agent loop's live output stream

Idioma do texto original: inglês

ralph-config

View and configure agent loop settings — show, set, reset, and apply named presets

Idioma do texto original: inglês

ralph-external

Crash-resilient external loop with state persistence and CI/CD integration

Idioma do texto original: inglês

ralph-memory

Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations

Idioma do texto original: inglês

ralph-reflect

View and manage agent loop reflections and episodic memory

Idioma do texto original: inglês

ralph-resume

Resume an interrupted agent loop from last checkpoint

Idioma do texto original: inglês

ralph

Execute iterative task loop until completion criteria are met - iteration beats perfection

Idioma do texto original: inglês

ralph-status

Check status of current or previous agent loop

Idioma do texto original: inglês

reflection-injection

Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them

Idioma do texto original: inglês

agent-persistence

Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.

Idioma do texto original: inglês

dev-doctor

Run a development-focused health check on the AIWG repository structure

Idioma do texto original: inglês

dev-mode-init

Switch AIWG CLI to dev mode (local repo source), rebuild, deploy dev tools, and run a health check — all via the Steward agent

Idioma do texto original: inglês

devkit-create-addon

Create a new AIWG addon with AI-guided setup

Idioma do texto original: inglês

devkit-create-agent

Create a new agent with AI-guided expertise definition following the Agent Design Bible

Idioma do texto original: inglês

devkit-create-command

Create a new slash command with AI-guided behavior definition

Idioma do texto original: inglês

devkit-create-extension

Create a new AIWG extension (framework expansion pack) with AI-guided setup

Idioma do texto original: inglês

devkit-create-framework

Comma-separated phase names

Idioma do texto original: inglês

devkit-create-skill

Enable interactive design mode

Idioma do texto original: inglês

devkit-test

Auto-fix discoverable issues

Idioma do texto original: inglês

devkit-validate

Validate addon, framework, or extension structure and manifest

Idioma do texto original: inglês

link-check

Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix

Idioma do texto original: inglês

validate-addon

Validate an entire AIWG addon package for completeness and release readiness

Idioma do texto original: inglês

validate-component

Validate a single AIWG component (skill, agent, or command) for completeness and correctness

Idioma do texto original: inglês

flaky-detect

Identify flaky tests from CI history and test execution patterns. Use when debugging intermittent test failures, auditing test reliability, or improving CI stability.

Idioma do texto original: inglês

flaky-fix

Suggest and apply fixes for flaky tests based on detected patterns. Use after flaky-detect identifies unreliable tests that need repair.

Idioma do texto original: inglês