AndreVianna

128 mods across 1 repository, 6 stars between them.

aid-architect

01

AndreVianna/aid-methodology

Agent Claude Code

Transforms requirements, SPEC, and KB into design output — SPEC sections, typed dependency-ordered task breakdowns, feature decomposition, delivery sequencing, and DESIGN-typed task execution including UX and flow advice.

not rated 6 changed 5d ago A 44 tokens original MIT

aid-clerk

02

AndreVianna/aid-methodology

Agent Claude Code

INTERNAL UTILITY (sub-agent only — do NOT invoke from a skill). Performs one mechanical, schema-bounded operation per dispatch — file extraction, template placeholder-fill, or glob enumeration — returning a markdown table or file with path and line evidence.

not rated 6 changed 5d ago A 54 tokens original MIT

aid-developer

03

AndreVianna/aid-methodology

Agent Claude Code

The only agent that modifies production code. Implements TASK files following specs and KB conventions across all implementation task types (IMPLEMENT, TEST, REFACTOR, CONFIGURE, MIGRATE, FIX), with mandatory build verification and formal IMPEDIMENT.md escalation.

not rated 6 changed 5d ago A 54 tokens original MIT

aid-interviewer

04

AndreVianna/aid-methodology

Agent Claude Code

Conducts adaptive one-question-at-a-time dialogue with human stakeholders to gather requirements, clarify ambiguity, and produce REQUIREMENTS.md or Q&A entries.

not rated 6 changed 5d ago A 33 tokens original MIT

aid-operator

05

AndreVianna/aid-methodology

Agent Claude Code

Runs final release verification, packages artifacts, creates PRs and release notes, manages releases, and updates the KB on ship. Safety-first, verification-focused.

not rated 6 changed 5d ago A 35 tokens original MIT

aid-orchestrator

06

AndreVianna/aid-methodology

Agent Claude Code

Routes pipeline findings to the next phase or skill, enforces human gates, dispatches agents with context, and manages parallel execution.

not rated 6 changed 5d ago A 31 tokens copy · 88% MIT

aid-researcher

07

AndreVianna/aid-methodology

Agent Claude Code

Reads and analyzes code, docs, logs, APIs, and external web sources to produce structured Knowledge Base documents and analysis reports — covering existing-state cataloguing, dependency/integration/convention mapping, telemetry interpretation, security analysis, performance profiling, and web-sourced prior art. Web…

not rated 6 changed 5d ago A 70 tokens original MIT

aid-reviewer

08

AndreVianna/aid-methodology

Agent Claude Code

Adversarial quality evaluator. Reviews any artifact (code, tasks, specs, plans, KB docs) against its acceptance criteria, rubric, and KB conventions. Produces the 7-column issue ledger with source and severity tags. Does NOT fix anything; does NOT compute the grade.

not rated 6 changed 5d ago A 61 tokens original MIT

aid-tech-writer

09

AndreVianna/aid-methodology

Agent Claude Code

Authors user-facing documentation — API docs, changelogs, READMEs, release notes, user guides — and reviews existing docs for quality and accuracy.

not rated 6 changed 5d ago A 36 tokens original MIT

aid-ask

10

AndreVianna/aid-methodology

Skill Claude Code

Answer a question about this project, with citations. Use this skill when you want to know something -- how a part of the system works, what a document says, where a piece of work stands -- and you want a grounded answer rather than a guess. It reads three sources: the Knowledge Base, the live codebase, and any AID…

not rated 6 changed 5d ago A SkillSpector: warn 151 tokens original MIT

aid-brainstorm

11

AndreVianna/aid-methodology

Skill Claude Code

Diverge on a problem not yet formed into an answerable question, then converge it to a DESIGN SEED in .aid/design/ .md -- exploration, framings, and the candidate directions worth pursuing. Use this skill when a problem space is still open and you want to explore it, rather than answer one specific question. Grounded…

not rated 6 changed 5d ago A 165 tokens original MIT

aid-config

12

AndreVianna/aid-methodology

Skill Claude Code needs its repo

View or update AID pipeline settings. Use this skill when you need to see how the pipeline is configured, or change one setting such as the project name, its type, or the minimum grade. A bare invocation prints every value in a table and, on the first run, creates .aid/settings.yml from the template. Passing a key -…

not rated 6 changed 5d ago A 88 tokens original MIT

aid-create-api

13

AndreVianna/aid-methodology

Skill Claude Code

Create an API endpoint / middleware (contract, handler, validation). Use this skill when you already know what to create 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 6 changed 5d ago A 79 tokens original MIT

AndreVianna/aid-methodology

Skill Claude Code

Realize a ready architecture seed from .aid/design/architecture.md into the project's build-and-shape (C1) Knowledge Base document -- components and their responsibilities, boundaries, interactions, and the invariants a change must not break. Use this skill when an architecture seed is ready and the project has no…

not rated 6 changed 5d ago A 184 tokens original MIT

aid-create-backlog

15

AndreVianna/aid-methodology

Skill Claude Code

Realize a ready backlog seed into .aid/knowledge/backlog.md -- frontmatter, preamble, ## Contents index, ## Next Release, ## Prioritized, and ## Gotchas. Use this skill when a backlog seed is ready and the project needs its backlog document written for the first time. Moves accepted tech-debt.md items into backlog.md…

not rated 6 changed 5d ago A SkillSpector: pass 131 tokens original MIT

aid-create-cicd

16

AndreVianna/aid-methodology

Skill Claude Code

Realize a ready CI/CD seed from .aid/design/cicd.md into the project's shipping (C8) Knowledge Base document -- the pipeline stages and their order, the triggers, the environments and promotion between them, and the release flow. Use this skill when a CI/CD seed is ready and the project has no record of its delivery…

not rated 6 changed 5d ago A 205 tokens original MIT

aid-create-cli

17

AndreVianna/aid-methodology

Skill Claude Code

Create a CLI command. Use this skill when you already know what to create 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 run /aid-execute to carry the plan out.

not rated 6 changed 5d ago A 71 tokens copy · 86% MIT

aid-create-config

18

AndreVianna/aid-methodology

Skill Claude Code

Create a new configuration option or feature flag. Use this skill when you already know what to create 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 run…

not rated 6 changed 5d ago A 75 tokens copy · 92% MIT

AndreVianna/aid-methodology

Skill Claude Code

Build a durable dashboard / BI view, from its source through the visualization to how it is published and refreshed. Use this skill when you already know what to create and want it scoped, specified, and broken into reviewable tasks in a single pass, with no requirements interview. You approve the resulting plan…

not rated 6 changed 5d ago A 88 tokens copy · 91% MIT

AndreVianna/aid-methodology

Skill Claude Code

Create a new data model/entity with its schema migration. Use this skill when you already know what to create 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 run…

not rated 6 changed 5d ago A 78 tokens copy · 88% MIT

AndreVianna/aid-methodology

Skill Claude Code

Create a data pipeline (source, transform, sink, schedule). Use this skill when you already know what to create 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 run…

not rated 6 changed 5d ago A 81 tokens copy · 89% MIT

aid-create-diagram

22

AndreVianna/aid-methodology

Skill Claude Code

Create a diagram in one pass, choosing the diagram type that fits the subject -- flowchart, sequence, entity-relationship, C4, state, and so on, in Mermaid or Graphviz. Use this skill when a picture would explain something faster than prose and you do not want to pick the notation yourself. It is grounded in, and…

not rated 6 changed 5d ago A 155 tokens original MIT

aid-create-document

23

AndreVianna/aid-methodology

Skill Claude Code

Create a document in one pass, working out both its format and its structure from what you ask for -- a how-to, a reference page, an ADR, an architecture write-up, a runbook, a tutorial, a changelog, a diagram, a table. Use this skill when you need a document written now and do not want to decide its genre first. It…

not rated 6 changed 5d ago A 199 tokens original MIT

aid-create-infra

24

AndreVianna/aid-methodology

Skill Claude Code

Provision a new infrastructure resource. Use this skill when you already know what to create 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 run /aid-execute to…

not rated 6 changed 5d ago A 73 tokens copy · 84% 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: