AndreVianna/aid-methodology

AID — AI-Integrated Development: A complete methodology for human-AI collaborative software development. 12 phases, 5 stages, 11 feedback loops.

This repository also configures its own agents. See what aid-methodology tells them →

5Stars on the repository
128Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

aid-design-test

49

AndreVianna/aid-methodology

Skill Claude Code

Develop a test design as a DESIGN SEED in .aid/design/test.md -- the units under test, the cases, and the framework and fixtures. Use this skill when what a test should actually assert is still being worked out. Grounded in the Knowledge Base (.aid/knowledge/) and the project source. It WRITES NO production code and…

not rated 5 yesterday A 155 tokens copy · 86% MIT

AndreVianna/aid-methodology

Skill Claude Code

Develop the testing policy as a DESIGN SEED in .aid/design/testing-strategy.md -- test levels, coverage expectations, which gates block a merge, and who may waive one. Use this skill when how the project should be tested is still being decided, rather than which tests to write. Grounded in the Knowledge Base…

not rated 5 yesterday A 172 tokens original MIT

aid-design-theme

51

AndreVianna/aid-methodology

Skill Claude Code

Develop a visual theme design as a DESIGN SEED in .aid/design/theme.md -- the style-token set (color, type, spacing), its light/dark variants, and how components apply it. Use this skill when the visual language is still being decided, rather than applied. Grounded in the Knowledge Base (.aid/knowledge/) and the…

not rated 5 yesterday A 134 tokens original MIT

aid-design-ui

52

AndreVianna/aid-methodology

Skill Claude Code

Develop a UI design as a DESIGN SEED in .aid/design/ui.md -- the screen/flow structure, the interaction model, and accessibility notes. Use this skill when a screen's layout and behaviour are still being worked out and you want a design you intend to keep. Grounded in the Knowledge Base (.aid/knowledge/) and the…

not rated 5 yesterday A 164 tokens original MIT

aid-design

53

AndreVianna/aid-methodology

Skill Claude Code

Produce a design artifact you intend to keep -- a UX or interaction flow, a component or interface design, with accessibility notes -- meant to inform the real build. Use this skill when the subject has no dedicated design row of its own; when a dedicated /aid-design- row exists, use that row instead. It is grounded…

not rated 5 yesterday A 156 tokens original MIT

aid-detail

54

AndreVianna/aid-methodology

Skill Claude Code

Break deliverables into small, dependency-driven, typed tasks -- each one a reviewable unit. The ultimate breakdown. Use this skill when a delivery has been planned and the actual work items are needed before execution starts. It detects each task's type from the SPEC's own signals -- RESEARCH, DESIGN, IMPLEMENT…

not rated 5 yesterday A 104 tokens original MIT

aid-discover

55

AndreVianna/aid-methodology

Skill Claude Code needs its repo

Populate the Knowledge Base from a codebase that already exists. Use this skill when you are starting AID on a project with existing code, and its architecture, conventions, and patterns need to be written down before any later phase can rely on them. It reads all repository content -- code, configuration, and…

not rated 5 yesterday A SkillSpector: pass 118 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write an architecture write-up in one pass -- a system's components, boundaries, and interactions, as C4 or arc42 views with Mermaid diagrams. Use this skill when you already know the document you need is architecture write-up, and want it drafted now rather than planned. It is grounded in, and accuracy-checked…

not rated 5 yesterday A 144 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write a changelog in one pass -- release notes grouped as Added, Changed, Fixed, Removed and Security. Use this skill when you already know the document you need is changelog, and want it drafted now rather than planned. It is grounded in, and accuracy-checked against, the Knowledge Base (.aid/knowledge/) and the…

not rated 5 yesterday A 135 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write an ADR in one pass -- an architecture decision record: the context, the decision itself, the alternatives considered, and the consequences. Use this skill when you already know the document you need is ADR, and want it drafted now rather than planned. It is grounded in, and accuracy-checked against, the…

not rated 5 yesterday A 139 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write a guideline in one pass -- an advisory recommended practice, stating the principle, its rationale, and do/don't examples. Use this skill when you already know the document you need is guideline, and want it drafted now rather than planned. It is grounded in, and accuracy-checked against, the Knowledge Base…

not rated 5 yesterday A 138 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write a runbook in one pass -- an operational procedure, from trigger through diagnostic and remediation to escalation. Use this skill when you already know the document you need is runbook, and want it drafted now rather than planned. It is grounded in, and accuracy- checked against, the Knowledge Base…

not rated 5 yesterday A 134 tokens copy · 86% MIT

AndreVianna/aid-methodology

Skill Claude Code

Write a standard in one pass -- a mandatory rule, stating the rule, its scope, how compliance is enforced, and the exceptions. Use this skill when you already know the document you need is standard, and want it drafted now rather than planned. It is grounded in, and accuracy-checked against, the Knowledge Base…

not rated 5 yesterday A 138 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Write a tutorial in one pass -- a learning-oriented walkthrough, from prerequisites through worked steps to the outcome. Use this skill when you already know the document you need is tutorial, and want it drafted now rather than planned. It is grounded in, and accuracy-checked against, the Knowledge Base…

not rated 5 yesterday A 133 tokens copy · 86% MIT

aid-document

63

AndreVianna/aid-methodology

Skill Claude Code

Write a general document in one pass -- a Diataxis how-to, reference page or explanation, or a status or progress report. Use this skill when the document you need does not fall into one of the named genres and you want it drafted now. It is grounded in, and accuracy- checked against, the Knowledge Base…

not rated 5 yesterday A 157 tokens original MIT

aid-execute

64

AndreVianna/aid-methodology

Skill Claude Code needs its repo

Carry out one planned task and review the result. Use this skill when tasks have been detailed and you are ready for the work to actually be done. It runs the task according to its type -- RESEARCH, DESIGN, IMPLEMENT, TEST, DOCUMENT, MIGRATE, REFACTOR or CONFIGURE -- then loops through review and fixes until the…

not rated 5 yesterday A SkillSpector: pass 95 tokens original MIT

aid-experiment

65

AndreVianna/aid-methodology

Skill Claude Code

Design, run, and analyze a controlled experiment or A/B test. Use this skill when you already know what to experiment and want it scoped, specified, and broken into reviewable tasks in a single pass, with no requirements interview. You approve the resulting plan before anything is built: this skill plans and stops, so…

not rated 5 yesterday A 80 tokens copy · 83% MIT

aid-fix

66

AndreVianna/aid-methodology

Skill Claude Code

Diagnose and correct a defect, regression, incident, or vulnerability. Use this skill when you already know what to fix and want it scoped, specified, and broken into reviewable tasks in a single pass, with no requirements interview. You approve the resulting plan before anything is built: this skill plans and stops…

not rated 5 yesterday A 80 tokens copy · 80% MIT

aid-housekeep

67

AndreVianna/aid-methodology

Skill Claude Code needs its repo

Sweep the project back into a consistent state after work has landed. Use this skill when the Knowledge Base has drifted from the code, the generated summary is stale, or work-area artifacts have piled up. It runs three gated jobs in order: re-discovering KB docs that changed since the last approval, regenerating the…

not rated 5 yesterday A SkillSpector: pass 158 tokens original MIT

aid-migrate

68

AndreVianna/aid-methodology

Skill Claude Code

Migrate data, a dependency, framework, or platform, with a rollback plan (non-schema; schema migrations use create/update-data-model). Use this skill when you already know what to migrate and want it scoped, specified, and broken into reviewable tasks in a single pass, with no requirements interview. You approve the…

not rated 5 yesterday A 94 tokens copy · 80% MIT

aid-monitor

69

AndreVianna/aid-methodology

Skill Claude Code

Watch production, classify what you find, and route it to whoever should act. Use this skill after a deployment, on a schedule, or whenever something looks wrong in the field. It reads telemetry, detects anomalies, performs root-cause analysis on the ones that are bugs, and then routes: bugs to /aid-fix, change…

not rated 5 yesterday A SkillSpector: pass 86 tokens original MIT

aid-plan

70

AndreVianna/aid-methodology

Skill Claude Code

Sequence feature SPECs into deliverables -- each one a functional MVP that builds on the previous. Strategy, not tactics. Use when feature SPECs are complete and you need a delivery roadmap.

not rated 5 yesterday A 41 tokens original MIT

aid-prototype-ui

71

AndreVianna/aid-methodology

Skill Claude Code

Build a throwaway, low-fidelity UI wireframe and interaction flow to test whether a UX direction actually works. Use this skill when you want to see a screen before committing to building it. Isolated and disposable: it never touches production, and it reports what the mock shows rather than deciding anything for you.…

not rated 5 yesterday A 114 tokens original MIT

aid-prototype

72

AndreVianna/aid-methodology

Skill Claude Code

Build a throwaway, low-fidelity model to test whether a direction actually works, before anyone commits to building it properly. Use this skill when a decision hinges on something you can only learn by trying it. The model is isolated and disposable -- it lives in the work folder or an opt-in worktree and never…

not rated 5 yesterday A 141 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: