ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

Ashan Skill Creator

Skill by ashanzzz

skill-install β€” Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/ashanzzz/ashan-skill-creator
Or

name: ashan-skill-creator description: Install: clawhub install skill-creator Create, edit, improve, or audit OpenClaw AgentSkills. Triggered when users say "create a skill", "write a skill", "author a skill", "improve this skill", "review the skill", "tidy up the skill", "audit the skill", or "build a new skill". Also used for: restructuring skill directories, moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec.

Skill Creator πŸ› οΈ

Complete guide to creating high-quality OpenClaw AgentSkills.

When to Use This Skill

  • User asks to create a new skill from scratch
  • User asks to improve an existing skill (add structure, examples, remove bloat)
  • User asks to audit a skill (check spec compliance, security, completeness)
  • User asks to organize a skill (restructure, add references/, add constraints)
  • User asks for guidance on skill publishing options

1. What Are Skills?

Skills are modular, self-contained packages that extend an Agent's capabilities with specialized knowledge, workflows, and tool integrations.

Each Skill is a folder containing at minimum:

skill-name/
β”œβ”€β”€ SKILL.md          ← Required (capability definition + instructions)
β”œβ”€β”€ scripts/          ← Optional (executable scripts)
β”œβ”€β”€ references/       ← Optional (on-demand reference docs)
└── assets/          ← Optional (templates, images for output)

2. Core Principles

Principle 1: Concise is Key

Context Window is a shared resource. The Agent needs room for: system prompt, conversation history, other Skills' metadata, and the current request.

Default assumption: the Agent is already very smart. Only add what the Agent genuinely doesn't know. Challenge every piece: "Does this justify its token cost?"

Prefer concise examples over verbose explanations.

Principle 2: Progressive Disclosure

Three-level loading structure for efficient context use:

LevelContentWhen LoadedSize Limit
1stname + descriptionAlways in context~100 words
2ndSKILL.md bodyAfter skill triggers<500 lines
3rdreferences/ / scripts/As neededUnlimited

Key rule: If SKILL.md exceeds 500 lines, split content into references/ files.

Principle 3: Match Freedom to Task Fragility

FreedomFormBest For
HighFree-text instructionsMultiple valid approaches, context-dependent decisions
MediumPseudocode / parameterized scriptsPreferred pattern exists, some variation OK
LowFixed scripts, few paramsBrittle operations, consistency critical

Principle 4: Examples Beat Explanations

Real-world data: Examples chapters deliver the largest quality improvement. Good/bad comparison examples outperform any amount of prose.


3. SKILL.md Standard Structure

3.1 Frontmatter (Required)

Metadata

Author@ashanzzz
Stars4473
Views1
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build β€” we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-ashanzzz-ashan-skill-creator": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

sure-api

Use the we-promise/sure REST API with X-Api-Key auth. Covers accounts, transactions, categories, tags, merchants, imports, holdings, trades, valuations, chats, official docs URLs, self-update workflow from upstream OpenAPI, and ClawHub publish readiness.

ashanzzz 4473

vikunja-task-api

Install: clawhub install ashanzzz-vikunja-task-api Full Vikunja v2 API integration β€” projects, tasks, labels, teams, views, comments, attachments, bulk operations, and more.

ashanzzz 4473

Verified Research

Skill by ashanzzz

ashanzzz 4473

unraid-xml-generator

Generate Unraid DockerMan user template XML files from structured input. Use when: the user asks to "η”Ÿζˆ Unraid XML 樑板", "εˆ›ε»Ί Docker 樑板", "δΈΊ XXX 写 Unraid 樑板", or "η”Ÿζˆ DockerMan XML" for any container. Key technique learned (2026-04-02): Unraid DockerMan templates support <ExtraParams>--entrypoint /bin/sh</ExtraParams> + <PostArgs> to bypass the container image's ENTRYPOINT. This allows overriding any image's startup command from the template. Config variables use: <Config Name="..." Target="ENV_VAR" Default="..." Type="..." Display="..." Required="..." Mask="..."> These become environment variables passed into the container. The skill generates a complete, valid XML and optionally deploys it to /boot/config/plugins/dockerMan/templates-user/my-<name>.xml (requires user confirmation before writing).

ashanzzz 4473

unraid-xml-generator

Generate Unraid DockerMan user template XML files from structured input. Use when: the user asks to "η”Ÿζˆ Unraid XML 樑板", "εˆ›ε»Ί Docker 樑板", "δΈΊ XXX 写 Unraid 樑板", or "η”Ÿζˆ DockerMan XML" for any container. Key technique learned (2026-04-02): Unraid DockerMan templates support <ExtraParams>--entrypoint /bin/sh</ExtraParams> + <PostArgs> to bypass the container image's ENTRYPOINT. This allows overriding any image's startup command from the template. Config variables use: <Config Name="..." Target="ENV_VAR" Default="..." Type="..." Display="..." Required="..." Mask="..."> These become environment variables passed into the container. The skill generates a complete, valid XML and optionally deploys it to /boot/config/plugins/dockerMan/templates-user/my-<name>.xml (requires user confirmation before writing).

ashanzzz 4126