extension-detector

Solid

Detects when a new project-level skill / rule / command would reduce friction. Asks the user for confirmation before creating anything. NEVER writes plugin-level files — only `.claude/skills/`, `.claude/rules/`, `.claude/commands/` in the user's project.

AI & Automation 24 stars 3 forks Updated today MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
47
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # Extension Detector **STATUS — v3.7.0-alpha.3.** Self-extending capability with hard gates against plugin pollution. ## Core principle The Aura Frog plugin ships a fixed set of skills, rules, and commands. Project-specific patterns belong **in the project**, not in the plugin. This skill watches for the moment a user's project would benefit from its own extensions and proposes them — but **never creates them autonomously**. **Hard rule:** anything this skill creates lands in the user's project under `.claude/`, never in `aura-frog/`. ## Detection signals (in order of strength) | Strength | Signal | Action | |---|---|---| | **Strong** | User explicitly says "we should have a skill/rule/command for X", "add a rule that…", "make this a skill" | Surface immediately | | **Medium** | User repeats the same correction 3+ times across recent turns ("don't do X" / "always do Y") | Surface as candidate rule | | **Medium** | Same multi-step procedure invoked manually 3+ times in this project | Surface as candidate skill | | **Weak** | Project README/CONTRIBUTING references a workflow Aura Frog doesn't have a command for | Surface as candidate command | Weak signals require 2+ in combination bef...

Details

Author
nguyenthienthanh
Repository
nguyenthienthanh/aura-frog
Created
8 months ago
Last Updated
today
Language
JavaScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

getff

Use when treating any codebase rule (architectural, naming, dependency, test-quality, contract, SLO) as an executable test that fails the build when violated, or when the user asks about enforcing code quality, fighting AI-generated code drift, setting up linters/tests/CI/pre-commit hooks, designing review processes, mutation testing, contract testing, fitness functions, observability-driven development, SLO-as-code, or any version of "how do I make my codebase resistant to AI agents breaking my conventions". Also trigger on any mention of ArchUnit, Stryker, Pact, dependency-cruiser, AI Factory (aif), Husky, lint-staged, ESLint flat config, Zod validation strategy, or shift-left/shift-right testing. Strongly trigger when the user mentions Claude Code, Cursor, or Copilot writing code that "looks fine but is wrong" — that is the core problem this skill addresses.

0 Updated today
artyhoo
AI & Automation Listed

pre-decision-analysis

当用户提出需要人类拍板但必须先做结构化分析的问题(评估、对比、讨论、值不值得、该不该、拆不拆、要不要起 ADR)时触发。本文件是该 skill 在 Claude Code 下的执行器;通用入口在 `../../SKILL.md`,规则权威源在 skill 顶层 `process/` 与 `standards/`(symlink 到 docs/dev/)。关键词:决策分析、多方案对比、argue subagent、codex review、PR diff review、AskUserQuestion、scratch 协作。

1 Updated today
moesin-lab
Web & Frontend Solid

skill-builder

Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design tree decision-by-decision — entity fit, use cases, name, description, workflow steps, tools, and progressive-disclosure layout — then reviews the finished skill against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new skill or slash command. Does not build an agent or subagent — use agent-builder. Does not serve, vendor, or refresh the authoring guidance itself — use guidance.

128 Updated today
testdouble