Skills - EnConvo Documentation

Overview

Use Agent Skills to extend EnConvo with task-specific capabilities. A skill packages instructions, resources, and optional scripts so EnConvo can follow a workflow reliably. You can share skills across teams or with the community.

Skills use progressive disclosure to manage context efficiently: EnConvo starts with each skill’s metadata (name, description, file path). Full instructions are loaded only when a skill is activated.

Skill Structure

A skill is a directory with a SKILL.md file plus optional scripts and references.

my-skill/
├── SKILL.md          # Required: instructions + metadata
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
└── assets/           # Optional: templates, resources

SKILL.md Format

The SKILL.md file must include a frontmatter block with name and description:

---
name: my-skill
description: Explain exactly when this skill should and should not trigger.
---

Step-by-step instructions for EnConvo to follow.

Because implicit matching depends on the description field, write descriptions with clear scope and boundaries. Be specific about when and when not to use the skill.

How Skills Are Activated

EnConvo can activate skills in two ways:

Explicit Invocation

Mention the skill directly in your prompt using the / prefix. Use this when you know exactly which skill you need.

Implicit Invocation

EnConvo automatically selects a skill when your task matches its description. No manual selection needed.

Explicit Invocation

Type / followed by the skill name in SmartBar or chat to invoke it directly:

/code-reviewer Review this function for security issues
/meeting-notes Format these raw notes into a structured summary
/api-checker Check the health of api.example.com

This is the most reliable way to invoke a skill — you get exactly the one you want.

Implicit Invocation

When you do not specify a skill, EnConvo automatically matches your request to the most relevant skill based on the description field:

You type: “Summarize these meeting notes into action items”
EnConvo scans all available skill descriptions
The meeting-notes skill matches (“…format raw meeting transcripts into structured notes with action items…”)
The skill is activated and its instructions guide the response

How to Write Descriptions That Match Well

Good implicit matching depends entirely on well-written description fields:

Quality	Example
Too vague	”Helps with code”
Too broad	”Does anything related to programming”
Good	”Review code for bugs, security issues, and best practices. Use when the user asks for a code review or wants to improve code quality. Do not use for code generation or writing new code.”

The key elements:

What it does: “Review code for bugs, security issues, and best practices”
When to trigger: “Use when the user asks for a code review”
When NOT to trigger: “Do not use for code generation or writing new code”

Skill Locations

EnConvo reads skills from multiple locations, with different scopes:

Scope	Location	Use Case
Project	`$PROJECT/.agents/skills/`	Skills specific to a project or workspace
User	`~/.agents/skills/`	Personal skills that apply across all projects
System	Bundled with EnConvo	Built-in skills available to everyone

If two skills share the same name in different locations, both remain available — EnConvo does not merge them.

Project Skills

Project-scoped skills are stored inside your project directory. They are available only when that project is active:

my-project/
├── .agents/
│   └── skills/
│       ├── deploy-checklist/
│       │   └── SKILL.md
│       └── pr-template/
│           └── SKILL.md
├── src/
└── package.json

This is ideal for skills that depend on project-specific conventions, file structures, or tools.

User Skills

User-scoped skills in ~/.agents/skills/ are available across all projects. Use this for personal productivity skills that are not project-specific:

~/.agents/skills/
├── email-composer/
│   └── SKILL.md
├── meeting-notes/
│   └── SKILL.md
└── code-reviewer/
    └── SKILL.md

Creating a Skill

Using the Skill Creator

The fastest way to create a skill is with the built-in creator:

/skill-creator

The creator walks you through:

What the skill does
When it should trigger
Whether it should be instruction-only or include scripts

Instruction-only is the default and recommended approach. Use scripts only when you need deterministic behavior or external tooling.

Manual Creation

Create a folder with a SKILL.md file:

Create the skill directory

mkdir -p ~/.agents/skills/my-skill

Write SKILL.md

cat > ~/.agents/skills/my-skill/SKILL.md << 'EOF'
---
name: my-skill
description: Summarize selected text into bullet points. Use when the user asks for a summary or key takeaways. Do not use for translation or rewriting tasks.
---

## Instructions

1. Read the selected text from the user's input.
2. Identify the 3-5 most important points.
3. Return a bullet-point summary.
4. Keep each bullet under 20 words.
EOF

Verify

EnConvo detects skill changes automatically. If the new skill doesn’t appear, restart EnConvo.

Writing Effective Instructions

The body of SKILL.md (below the frontmatter) contains the instructions the AI follows. Write them as clear, imperative steps:

---
name: changelog-generator
description: Generate a changelog from git commits. Use when the user asks to create a changelog, release notes, or commit summary. Do not use for general git operations.
---

## Instructions

1. Read the git log for the specified date range or number of commits.
2. Group commits by category:
   - **Features**: New functionality (commits starting with "feat:")
   - **Fixes**: Bug fixes (commits starting with "fix:")
   - **Breaking Changes**: Changes that break backward compatibility
   - **Other**: Everything else
3. For each commit, write a user-facing description (not the raw commit message).
4. Format as markdown with version header, date, and categorized bullet points.
5. Highlight breaking changes with a warning callout.

## Output Format

v1.2.0 (2024-01-15)

Features

Added dark mode support for all pages
New export to PDF option in reports

Fixes

Fixed login timeout on slow connections
Resolved duplicate notification issue

Breaking Changes

⚠️ API endpoint /v1/users now requires authentication

Be specific about inputs

State exactly where the input comes from: “Read the selected text”, “Parse the attached file”, “Use the URL from the user’s message”.

Define the output format

Include a concrete example of what the output should look like. This prevents ambiguity and ensures consistency.

Handle edge cases

Add instructions for common edge cases: “If no commits are found, report that the range is empty” or “If the input is not valid JSON, ask the user to check the format”.

Keep it focused

One skill should do one thing well. If you find yourself writing a skill with 10+ steps covering multiple tasks, split it into separate skills.

Adding Scripts

For skills that need executable logic, add a scripts/ directory:

my-skill/
├── SKILL.md
└── scripts/
    └── fetch_data.sh

Reference scripts in your SKILL.md:

---
name: api-checker
description: Check API endpoint health and response times.
---

## Instructions

1. Run the health check script:
   ```bash
   bash scripts/fetch_data.sh $URL

Parse the JSON output.
Report status, response time, and any errors.

### When to Use Scripts

| Use Scripts When | Use Instructions Only When |
|-----------------|---------------------------|
| You need deterministic output (exact formats, calculations) | The task is primarily about reasoning and language |
| You interact with external APIs or databases | The task uses only the AI's built-in capabilities |
| You need to process or transform data programmatically | The task is about writing, summarizing, or analyzing |
| You require authentication or credential handling | The instructions alone are sufficient |

## Adding References

Include documentation or context files that the skill can consult:

my-skill/ ├── SKILL.md ├── references/ │ ├── api-docs.md │ └── examples.md └── scripts/ └── run.sh

Reference them in instructions:

```markdown
Consult `references/api-docs.md` for the API schema before making requests.

References are useful for:

API documentation the skill needs to follow
Style guides or brand guidelines
Code examples and templates
Domain-specific knowledge

Installing Skills

EnConvo supports two methods to install skills using /skill-installer:

From EnConvo Skills Store

Search and install skills by name from the built-in skills store:

/skill-installer pdf

This searches the EnConvo skills store and installs the matching skill. EnConvo detects newly installed skills automatically.

From GitHub

Install skills directly from a GitHub repository URL — including subdirectories:

/skill-installer https://github.com/anthropics/skills/tree/main/skills/pptx

GitHub installation supports subdirectory paths, so you can point to a specific skill folder within a larger repository. No need to clone the entire repo.

Browsing the Skills Store

The Skills Store provides a curated collection of community-built skills:

Open Settings
Navigate to Skills Store
Browse categories or search by keyword
Click Install on any skill
The skill is downloaded and ready to use immediately

Popular skill categories:

Development: Code review, documentation generation, testing
Writing: Email composition, blog posts, technical writing
Data: Analysis, visualization, reporting
Productivity: Meeting notes, task management, scheduling

Managing Skills

Viewing Installed Skills

See all your installed skills in Settings -> Skills:

System skills (built-in)
User skills (from ~/.agents/skills/)
Project skills (from current project)
Store-installed skills

Updating Skills

Store skills: Check for updates in the Skills Store
GitHub skills: Re-run the installer with the same URL
Custom skills: Edit the SKILL.md file directly — changes are detected automatically

Disabling Skills

You can disable a skill without deleting it:

Go to Settings -> Skills
Find the skill
Toggle it off

Disabled skills will not be available for implicit or explicit invocation until re-enabled.

Best Practices

Keep each skill focused

One skill = one job. A skill that does too many things is harder to trigger correctly and harder to maintain.

Prefer instructions over scripts

Use plain-language instructions unless you need deterministic behavior or external tooling. Instructions are easier to write, debug, and iterate on.

Write imperative steps

Be explicit about inputs, steps, and expected outputs. Vague instructions lead to inconsistent results.

Test your trigger descriptions

Try various prompts against your skill’s description field to confirm it triggers (and doesn’t trigger) correctly.

Use clear boundaries

In the description, state both what the skill should handle and what it should not handle.

Version your skills

For team-shared skills, keep them in version control (git). This makes it easy to track changes, roll back, and collaborate.

Example Skills

Code Reviewer

---
name: code-reviewer
description: Review code for bugs, security issues, and best practices. Use when the user asks for a code review or wants to improve code quality. Do not use for code generation or writing new code.
---

## Instructions

1. Read the provided code carefully.
2. Check for:
   - Logic errors and edge cases
   - Security vulnerabilities (injection, XSS, etc.)
   - Performance issues
   - Code style and readability
3. Provide feedback as a numbered list.
4. For each issue, include:
   - Severity (Critical / Warning / Suggestion)
   - Line reference
   - Explanation and fix

Meeting Notes

---
name: meeting-notes
description: Format raw meeting transcripts into structured notes with action items. Use when the user provides meeting notes, transcripts, or asks to organize meeting content. Do not use for scheduling or calendar tasks.
---

## Instructions

1. Parse the meeting transcript or raw notes.
2. Extract and organize into sections:
   - **Attendees**: List all participants
   - **Key Decisions**: Bullet-point decisions made
   - **Discussion Summary**: 3-5 sentence overview
   - **Action Items**: Table with Owner, Task, Deadline
3. Use markdown formatting for readability.

Git Commit Message

---
name: commit-message
description: Generate conventional commit messages from staged changes. Use when the user asks for a commit message or wants to commit changes. Do not use for general git operations like branching or merging.
---

## Instructions

1. Read the staged diff (use `git diff --staged`).
2. Identify the type of change:
   - feat: New feature
   - fix: Bug fix
   - docs: Documentation
   - refactor: Code restructuring
   - test: Adding tests
   - chore: Maintenance
3. Write a commit message following Conventional Commits format:

type(scope): concise description

Detail 1
Detail 2

4. Keep the subject line under 72 characters.
5. Include a body only if the change needs explanation.

API Documentation Generator

---
name: api-docs
description: Generate API documentation from source code. Use when the user asks to document an API, endpoint, or function. Do not use for general code documentation or README files.
---

## Instructions

1. Read the source code file(s) provided.
2. For each endpoint or public function, document:
   - **Method & Path** (for HTTP) or **Signature** (for functions)
   - **Description**: What it does in one sentence
   - **Parameters**: Name, type, required/optional, description
   - **Response**: Structure and example
   - **Errors**: Possible error codes and meanings
3. Format as markdown with code examples.
4. Include a curl example for each HTTP endpoint.

## Output Format

### `POST /api/users`

Create a new user account.

**Parameters:**

| Name | Type | Required | Description |
|------|------|----------|-------------|
| email | string | Yes | User's email address |
| name | string | Yes | Display name |

**Response (201):**
```json
{ "id": "usr_123", "email": "user@example.com", "name": "John" }

## Resources

<CardGroup cols={2}>
  <Card title="EnConvo GitHub" icon="github" href="https://github.com/enconvo">
    Browse open-source extensions and skills
  </Card>
  <Card title="Community Discord" icon="discord" href="https://discord.gg/jYsdVRRK2k">
    Share skills and get help from the community
  </Card>
  <Card title="Skills Store" icon="store" href="https://www.enconvo.com">
    Browse and install community skills
  </Card>
  <Card title="MCP Integration" icon="plug" href="/features/mcp">
    Combine skills with MCP tools
  </Card>
</CardGroup>

Documentation Index

​Overview

​Skill Structure

​SKILL.md Format

​How Skills Are Activated

Explicit Invocation

Implicit Invocation

​Explicit Invocation

​Implicit Invocation

​How to Write Descriptions That Match Well

​Skill Locations

​Project Skills

​User Skills

​Creating a Skill

​Using the Skill Creator

​Manual Creation

​Writing Effective Instructions

​v1.2.0 (2024-01-15)

​Features

​Fixes

​Breaking Changes

​Adding Scripts

​Installing Skills

​From EnConvo Skills Store

​From GitHub

​Browsing the Skills Store

​Managing Skills

​Viewing Installed Skills

​Updating Skills

​Disabling Skills

​Best Practices

​Example Skills

​Code Reviewer

​Meeting Notes

​Git Commit Message

​API Documentation Generator

Overview

Skill Structure

SKILL.md Format

How Skills Are Activated

Explicit Invocation

Implicit Invocation

How to Write Descriptions That Match Well

Skill Locations

Project Skills

User Skills

Creating a Skill

Using the Skill Creator

Manual Creation

Writing Effective Instructions

v1.2.0 (2024-01-15)

Features

Fixes

Breaking Changes

Adding Scripts

Installing Skills

From EnConvo Skills Store

From GitHub

Browsing the Skills Store

Managing Skills

Viewing Installed Skills

Updating Skills

Disabling Skills

Best Practices

Example Skills

Code Reviewer

Meeting Notes

Git Commit Message

API Documentation Generator