skill-writer

name	skill-writer
description	Create, revise, and validate effective skills. Use when adding a new skill or changing an existing skill's SKILL.md, bundled scripts, references, assets, scaffold templates, or validation tooling.
author	alexgorbatchev
metadata	{"created_on":"2026-04-14 12:00","last_modified":"2026-07-22 08:47","status":"current"}

Skill Writer

This skill provides guidance for creating and revising effective skills.

About Skills

Skills are modular, self-contained packages that extend the agent's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform the agent from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

What Skills Provide

1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks

Core Principles

Concise is Key

The context window is a public good. Skills share the context window with everything else the agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

Default assumption: the agent is already very smart. Only add context the agent doesn't already have. Challenge each piece of information: "Does the agent really need this explanation?" and "Does this paragraph justify its token cost?"

Prefer concise examples over verbose explanations.

Treat the frontmatter description as routing metadata, not as a mini playbook. It should help the agent decide whether to load the skill, not try to enforce workflow rules before the skill body is read.

Eliminate Prompt Debt and Redundancy

To keep skills highly efficient and avoid wasting tokens on useless meta-commentary:

• No Markdown Title/Headers: Do not start SKILL.md with # Skill Name or similar. The model already knows the skill name from the metadata.
• No Overviews or Meta-Commentary: Do not add ## Overview or explanatory sentences like "This skill acts as a proxy..." or "Below are the guidelines...". Jump straight into the action, rules, or decision logic.
• Minimalist Descriptions: Strip the frontmatter description to the absolute bare minimum needed to trigger. For example, use Use when asked to commit changes in a Git repository. instead of verbose sentences detailing every scenario.
• Remove Implied Steps: Do not write out steps that are completely obvious or implied. For example, if working with a review agent, do not instruct to "address issues" as that is the definition of pairing with a review agent.

Set Appropriate Degrees of Freedom

Match the level of specificity to the task's fragility and variability:

High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.

Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.

Low freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.

Think of the agent as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

Portability (No Local References)

Skills must be portable and reusable across different environments, machines, and projects.

Never include local references or hardcoded absolute paths in your skill files (SKILL.md, scripts, references, etc.).

• Avoid paths like /Users/alex/development/... or C:\Users\....
• Use relative paths, or environment variables, or parameterize paths so they are evaluated at runtime by the agent.
• When referring to other files within the skill itself, always use paths relative to the skill directory (e.g., scripts/my_script.ts or references/docs.md).

Anatomy of a Skill

Every skill consists of a required SKILL.md file and optional bundled resources:

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   ├── description: (required)
│   │   └── author: alexgorbatchev (repo convention)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Bun/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

SKILL.md (required)

Every SKILL.md consists of:

• Frontmatter (YAML): name, description, and author (e.g., author: alexgorbatchev) are required triggering and attribution fields. Additionally, in this repository, you MUST include a metadata dictionary containing created_on and last_modified (using strict YYYY-MM-DD HH:MM format) plus status: current to keep track of the skill's history and metadata lifecycle. Keep frontmatter minimal, and place these historical attributes exclusively within the nested metadata block.
• Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).

Bundled Resources (optional)

Scripts (scripts/)

Executable code (Bun/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.

• When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed
• Example: scripts/rotate_pdf.py for PDF rotation tasks
• Benefits: Token efficient, deterministic, may be executed without loading into context
• Note: Scripts may still need to be read by the agent for patching or environment-specific adjustments

References (references/)

Documentation and reference material intended to be loaded as needed into context to inform the agent's process and thinking.

Rule of thumb: If you're writing detailed configuration, setup steps, or reference material that exceeds ~50 lines, put it in references/filename.md and link to it from SKILL.md. Keep SKILL.md focused on workflows and decision guidance.

• When to include: For documentation that the agent should reference while working
• Examples: references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specifications
• Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
• Service setup: Installation, configuration, and infrastructure setup details must be written to references/setup.md - this keeps SKILL.md focused on workflows while preserving setup documentation for reference
• Benefits: Keeps SKILL.md lean, loaded only when the agent determines it's needed
• Best practice: If files are large (>10k words), include grep search patterns in SKILL.md
• Avoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.

Assets (assets/)

Files not intended to be loaded into context, but rather used within the output the agent produces.

• When to include: When the skill needs files that will be used in the final output
• Examples: assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typography
• Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
• Benefits: Separates output resources from documentation, enables the agent to use files without loading them into context

What to Not Include in a Skill

A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:

• README.md
• INSTALLATION_GUIDE.md
• QUICK_REFERENCE.md
• CHANGELOG.md
• etc.

The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.

Progressive Disclosure Design Principle

Skills use a three-level loading system to manage context efficiently:

1. Metadata (name + description) - Always in context (~100 words)
2. SKILL.md body - When skill triggers (~5k words)
3. Bundled resources - As needed by the agent (Unlimited because scripts can be executed without reading into context window)

Progressive Disclosure Patterns

Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.

Key principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.

Pattern 1: High-level guide with references

# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]

## Advanced features

- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns

The agent loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.

Pattern 2: Domain-specific organization

For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:

bigquery-skill/
├── SKILL.md (overview and navigation)
└── reference/
    ├── finance.md (revenue, billing metrics)
    ├── sales.md (opportunities, pipeline)
    ├── product.md (API usage, features)
    └── marketing.md (campaigns, attribution)

When a user asks about sales metrics, the agent only reads sales.md.

Similarly, for skills supporting multiple frameworks or variants, organize by variant:

cloud-deploy/
├── SKILL.md (workflow + provider selection)
└── references/
    ├── aws.md (AWS deployment patterns)
    ├── gcp.md (GCP deployment patterns)
    └── azure.md (Azure deployment patterns)

When the user chooses AWS, the agent only reads aws.md.

Pattern 3: Conditional details

Show basic content, link to advanced content:

# DOCX Processing

## Creating documents

Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).

## Editing documents

For simple edits, modify the XML directly.

**For tracked changes**: See [REDLINING.md](REDLINING.md)
**For OOXML details**: See [OOXML.md](OOXML.md)

The agent reads REDLINING.md or OOXML.md only when the user needs those features.

Important guidelines:

• Avoid deeply nested references - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
• Structure longer reference files - For files longer than 100 lines, include a table of contents at the top so the agent can see the full scope when previewing.

Skill Writing Process

Skill writing and maintenance involve these steps:

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (create the folder and SKILL.md manually, or use bun run skills:add for vendoring)
4. Edit the skill (implement resources and write SKILL.md)
5. Validate the skill's formatting and frontmatter against project requirements
6. Iterate based on real usage

Follow these steps in order, skipping only if there is a clear reason why they are not applicable.

Step 1: Understanding the Skill with Concrete Examples

Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.

To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.

For example, when building an image-editor skill, relevant questions include:

• "What functionality should the image-editor skill support? Editing, rotating, anything else?"
• "Can you give some examples of how this skill would be used?"
• "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
• "What would a user say that should trigger this skill?"

To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.

Conclude this step when there is a clear sense of the functionality the skill should support.

Step 2: Planning the Reusable Skill Contents

To turn concrete examples into an effective skill, analyze each example by:

1. Considering how to execute on the example from scratch
2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly

Example: When building a pdf-editor skill to handle queries like "Help me rotate this PDF," the analysis shows:

1. Rotating a PDF requires re-writing the same code each time
2. A scripts/rotate_pdf.py script would be helpful to store in the skill

Example: When designing a frontend-webapp-builder skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:

1. Writing a frontend webapp requires the same boilerplate HTML/React each time
2. An assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skill

Example: When building a big-query skill to handle queries like "How many users have logged in today?" the analysis shows:

1. Querying BigQuery requires re-discovering the table schemas and relationships each time
2. A references/schema.md file documenting the table schemas would be helpful to store in the skill

To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.

Step 3: Initializing the Skill

When creating a new skill from scratch, create the directory under the appropriate skills folder and create a SKILL.md file.

• For a global/registry skill: Create skills/<skill-name>/SKILL.md.
• For project-local skills: Typically placed under .agents/skills/<skill-name>/SKILL.md.

Ensure the directory contains:

• SKILL.md (required, with valid YAML frontmatter)
• Optional scripts/, references/, or assets/ directories if the skill contains reusable, portable code, resources, or files.

Step 4: Edit the Skill

When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of the agent to use. Include information that would be beneficial and non-obvious to the agent. Consider what procedural knowledge, domain-specific details, or reusable assets would help another agent execute these tasks more effectively.

Start with Reusable Skill Contents

To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.

Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.

Update SKILL.md

Writing Guidelines: Always use imperative/infinitive form.

Self-review to 10/10

Do not stop at the first draft that seems acceptable. Self-review the skill against an explicit quality bar, correct weaknesses, and repeat until the result would reasonably score 10/10 against the rubric below.

Mandatory Watertightness Audit: Before finalizing any skill's instructions, you MUST consult the prompt-writer skill to perform a formal Watertightness Audit (using the $W = 10 \times P \times (1 - L) \times C$ formula). If $W < 9.0$, you must identify the logical loopholes, lack of semantic precision, or weak behavioral coupling, and write surgically precise negative guardrails (e.g. "Do not use X", "Prohibited justifications") to close them until $W \ge 9.0$.

Use a bounded review loop:

1. Draft the smallest correct version of the skill.
2. Review it critically against the rubric.
3. Fix the highest-impact problems first.
4. Repeat until every rubric item passes cleanly or an external constraint prevents further improvement.

Treat 10/10 as meaning the skill is clear, correctly scoped, concise, internally consistent, and ready for another agent to use without avoidable confusion. Do not chase perfection through meaningless rewrites; stop only when additional edits no longer improve correctness, clarity, triggering, or usability.

Review rubric:

• Triggering quality: Does the description clearly say what the skill does, when to use it, and nearby cases that should not trigger it?
• Workflow quality: Are the steps concrete, ordered, and actionable instead of vague advice?
• Resource quality: Are scripts, references, and assets present only when they materially improve reliability or reuse?
• Conciseness: Is every section earning its token cost, with bulky details moved into references when appropriate?
• Consistency: Do frontmatter, body instructions, scripts, and examples agree with each other?
• Usability: Could another agent execute the skill successfully without guessing missing context?

Frontmatter

Write the YAML frontmatter with name, description, and author:

• name: The skill name

• description: The description is the ONLY stable routing mechanism. To achieve near-100% mathematical certainty that an agent will trigger the skill, you must override its pre-trained complacency. If the model thinks it already knows how to do a task, it will skip the skill unless the description hacks its attention mechanism.

  The "Near-100% Certainty" Trigger Formula: Descriptions must act as security tripwires using these 5 watertight elements:

  1. Hard Conditional Imperatives: Override passive language ("helps with", "guidelines for"). Use "MUST USE", "ALWAYS TRIGGER", "REQUIRED".
  2. Exact Lexical Anchors: Agents route via token matching. Match the user's exact tokens by explicitly listing file extensions (e.g., .tsx, .go), directory names, CLI commands, and framework names. Do not rely on synonyms.
  3. Action-Verb Mapping: Map exact user intents. Use words like "create", "debug", "refactor", "migrate", "deploy".
  4. Anti-Hallucination Clause: Break the model's pre-trained confidence. Explicitly state that its default training is insufficient or outdated for this specific project.
  5. Negative Boundaries (Anti-Dilution): Explicitly define where the skill stops to prevent probability splitting between similar skills (e.g., "Do NOT use for React").

  The Formula Template:

  [REQUIRED/ALWAYS USE] when [List exact Verbs: creating, debugging] [List exact Nouns/Frameworks]. Applies to [List exact file extensions / directories]. Your default training knowledge is insufficient; you [MUST READ] this to get the project-specific rules. Do NOT use for [Negative Boundary].

  Examples:

  • Weak (70% hit rate): "Apply Go coding rules, design principles, and project conventions for maintainable Go code."

  • Bulletproof (99.9% hit rate): "ALWAYS USE when writing, refactoring, or reviewing Go code (.go files). You MUST read this to get our specific standard library rules and memory conventions before writing any code. Do NOT use for TypeScript."

  • Weak (70% hit rate): "Use this skill to deploy the application to AWS."

Example YAML Frontmatter:

---
name: skill-name
description: REQUIRED when creating...
author: alexgorbatchev
metadata:
  created_on: 2026-07-22 08:30
  last_modified: 2026-07-22 08:47
  status: current
---

Default to name, description, author, and metadata. The allowed extra keys beyond those in this toolchain are license and allowed-tools.

Body

Write instructions for using the skill and its bundled resources.

For a project-local <base-skill>-addendum, keep the body focused on the project-specific delta from the base skill. State clearly that project-specific guidance in the addendum supersedes conflicting guidance from the base skill for that project, and avoid repeating unchanged parts of the base skill.

Step 5: Validating a Skill

Once development of the skill is complete, self-validate its structure and frontmatter:

• Format: Ensure valid YAML frontmatter with name, description, author, and metadata keys.
• Metadata: Verify created_on and last_modified are present and in strict YYYY-MM-DD HH:MM format, and status is set correctly.
• Constraints: Verify that descriptions contain no < or > tags, are strings, and stay below the 1024-character maximum.
• Rules: Check that all principles and critical rules are clear, imperative, and actionable.

Step 6: Iterate

After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.

Iteration workflow:

1. Use the skill on real tasks
2. Notice struggles or inefficiencies
3. Identify how SKILL.md or bundled resources should be updated
4. Implement changes and test again