Agent skill

Maiden Skill

by Xircth in Xircth/VibeX

Project-wide engineering principles for VibeX. An agent skill from Xircth/VibeX.

Apache-2.0Auto-check passedDevelopment

Install Maiden Skill

skills CLI
$ npx skills add Xircth/VibeX --skill maiden-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Xircth/VibeX maiden-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Xircth/VibeX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/maiden-skill .claude/skills/maiden-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
maiden-skill
GitHub stars
136
Token cost
~597 tokens
SKILL.md length
305 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Project-wide engineering principles for VibeX. An agent skill from Xircth/VibeX.

  • Works in 6 steps: First principles and complete usability… → Fix the root cause — Trace a defect or… → Make code explain itself — Names express… → …
  • Tasks that involve Root cause analysis
  • SKILL.md covers Principles and Apply before acting
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Maiden Skill is an agent skill from Xircth/VibeX. Project-wide engineering principles for VibeX. Use this skill at the start of every task, before analysis, design, implementation, testing, or release, to keep solutions complete, root-cause-driven, clean, deployment-consistent, and free of redundant UI explanatory copy.

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Root cause analysis and Deployment. The repository describes itself as: IADE:A New Development Platform for the AI Era—An Integrated Agent Development Environment. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Root cause analysis
  • Tasks that involve Deployment

Example prompts

  • “/maiden-skill”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. First principles and complete usability — Start from the user-visible capability and its full path. Functional usability and completeness…
  2. Fix the root cause — Trace a defect or inconsistency to its origin and correct the design there. Do not paper over it with special cases…
  3. Make code explain itself — Names express what code does. Comments record why a decision exists or a business rule requires it; remove…
  4. Leave no residue — Do not retain backup files, obsolete code, stale documentation, commented-out experiments, or incorrect intermediate…
  5. Keep deployments identical — Treat local source and deployed source as the same artifact. Do not make untracked server-only changes…
  6. Keep UI concise — Every visible string must help the user act, decide, understand current state, recover from an error, or safely assess a…

What it can do on your machine

Read from SKILL.md and the folder at commit 4a2c06d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maiden Skill loads about 597 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 305 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~597

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Xircth/VibeX at commit 4a2c06d, republished under its Apache-2.0 licence (© Xircth). 305 words, ~597 tokens.

Download SKILL.mdSave it as .claude/skills/maiden-skill/SKILL.md (or your agent's skills folder).
name
maiden-skill
description
Project-wide engineering principles for VibeX. Use this skill at the start of every task, before analysis, design, implementation, testing, or release, to keep solutions complete, root-cause-driven, clean, deployment-consistent, and free of redundant UI explanatory copy.

Maiden Principles

Treat the work as if it were being created for the first time: one clear source of truth, a complete working outcome, and no accumulated workaround debt.

Principles

  1. First principles and complete usability — Start from the user-visible capability and its full path. Functional usability and completeness are the highest drivers; do not preserve an implementation, abstraction, or plan that prevents the feature from working end to end.
  2. Fix the root cause — Trace a defect or inconsistency to its origin and correct the design there. Do not paper over it with special cases, copied legacy logic, extra switches, or route-specific exceptions.
  3. Make code explain itself — Names express what code does. Comments record why a decision exists or a business rule requires it; remove comments that merely restate the code.
  4. Leave no residue — Do not retain backup files, obsolete code, stale documentation, commented-out experiments, or incorrect intermediate states. Correct or remove them.
  5. Keep deployments identical — Treat local source and deployed source as the same artifact. Do not make untracked server-only changes; verify integrity when the delivery process supports it.
  6. Keep UI concise — Every visible string must help the user act, decide, understand current state, recover from an error, or safely assess a consequence. Do not add implementation notes, redundant feature descriptions, or decorative hints (for example, do not explain that Settings is configured through settings.json).

Apply before acting

Before proposing or making changes, check:

  • Does this produce the complete usable capability, including the necessary paths and failure states?
  • Am I addressing the source of the problem rather than adding a workaround?
  • Can any code, documentation, or UI text be removed because it is redundant, stale, or implementation-facing?

When principles conflict, preserve correct, complete user functionality first; then choose the smallest clean design that keeps a single source of truth.

© Xircth, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/maiden-skill of Xircth/VibeX.

Open the folder on GitHubat commit 4a2c06d

Compare with similar skills

Maiden Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maiden Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maiden Skill this skillXircth/VibeX136—~597Automated safety check: PassApache-2.0
Convex Advisoropenclaw/clawhub9.5k—~1.1kAutomated safety check: PassMIT
Chatqna Troubleshootopen-edge-platform/edge-ai-libraries171—~2.6kAutomated safety check: PassApache-2.0
Deployment Rollback InterviewerPrepLabsAI/InterviewMentor112—~3.1kAutomated safety check: PassMIT
AWS Cloudformationaws/agent-toolkit-for-aws2.8k—~3.6kAutomated safety check: PassApache-2.0
Code Design Rationale Investigatorcursor/plugins11k9 repos~2.6kAutomated safety check: PassNone

Similar skills

  • Convex Advisor

    openclaw/clawhub

    Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

    9.5k GitHub stars~1.1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Chatqna Troubleshoot

    open-edge-platform/edge-ai-libraries

    Troubleshoot Chat Question-and-Answer Core end-to-end across Docker Compose and Helm deployments, including startup failures, health/API errors, runtime mismatches (OpenVINO vs Ollama), model/config…

    171 GitHub stars~2.6k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Deployment Rollback Interviewer

    PrepLabsAI/InterviewMentor

    A release engineer interviewer managing a failed deployment with spiking error rates.

    112 GitHub stars~3.1k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • AWS Cloudformation

    aws/agent-toolkit-for-aws

    Official

    Authors, validates, and troubleshoots AWS CloudFormation templates.

    2.8k GitHub stars~3.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    11k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Covers preparing, tagging and publishing a Cline desktop app release on the stable, beta or nightly channel through the desktop-publish GitHub workflow.

    70k GitHub stars~4.5k tokensUpdated today
    DevelopmentAuto-check passed

More from Xircth/VibeX

  • Build, migrate, test, link, debug, or package full-trust VibeX v4 product plugins with README summaries, contents, root config, dependencies, App surfaces, editable file tabs, Agent Skills…

    136 GitHub stars~1.7k tokensUpdated 11 days ago
    Auto-check passed
  • Launch the interactive web dashboard to visualize a codebase's knowledge graph

    136 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Understand

    Xircth/VibeX

    Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

    136 GitHub starsUsed in 2 repos~12k tokens
    Auto-check passed
  • Design, edit, validate, publish, inspect, and debug VibeX .vibex-workflow.json DAGs with the dedicated vibex-workflow-mcp.

    136 GitHub stars~737 tokensUpdated 11 days ago
    Auto-check passed
  • Implement Spec

    Xircth/VibeX

    Implement a specification in code.

    136 GitHub starsUsed in 1 repo~511 tokens
    Auto-check passed

Questions about Maiden Skill

What does Maiden Skill do?

Project-wide engineering principles for VibeX. An agent skill from Xircth/VibeX. Maiden Skill is an agent skill from Xircth/VibeX. Project-wide engineering principles for VibeX.

When should I use Maiden Skill?

Maiden Skill fits situations like: tasks that involve Root cause analysis; tasks that involve Deployment.

How do I install Maiden Skill in Claude Code?

Run `npx skills add Xircth/VibeX --skill maiden-skill -a claude-code`. Or copy the skill folder (.agents/skills/maiden-skill in Xircth/VibeX) into .claude/skills/maiden-skill in your project. Claude Code loads it when a task matches its description.

How do I install Maiden Skill in Codex?

Run `npx skills add Xircth/VibeX --skill maiden-skill -a codex`. Or copy the skill folder (.agents/skills/maiden-skill in Xircth/VibeX) into .agents/skills/maiden-skill in your project. Codex loads it when a task matches its description.

Can I use Maiden Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Xircth/VibeX --skill maiden-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maiden-skill, .gemini/skills/maiden-skill, .github/skills/maiden-skill and .opencode/skills/maiden-skill in your project.

What does Maiden Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Maiden Skill is instructions for the agent only.

Does Maiden Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Maiden Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maiden Skill use?

Maiden Skill is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maiden Skill use?

About 597 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Maiden Skill?

Skills that share tags, products or a category with Maiden Skill: Convex Advisor (openclaw/clawhub, 9.5k stars), Chatqna Troubleshoot (open-edge-platform/edge-ai-libraries, 171 stars), Deployment Rollback Interviewer (PrepLabsAI/InterviewMentor, 112 stars) and AWS Cloudformation (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maiden Skill?

Xircth (a GitHub user) maintains it in Xircth/VibeX, which has 136 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 29, 2026.

Source: Xircth/VibeX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.