Not in the top 1,000 by GitHub stars
elisaterumi-ai/agent-skills-in-practice
Learn what AI skills are and how to design, structure, and use them in real-world agent systems.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
examples/ai-news-radar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/clinical-anonymization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/commit-message-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/content-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/copywriting-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/data-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/data-visualizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/document-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/financial-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/linkedin-post-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/pdf-processor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/pr-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/product-roadmap-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/prompt-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/radar-ia-br/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/spreadsheet-analyst/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/web-researcher/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
examples/workflow-automator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
281cc8163762 → 281cc8163762
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 281cc8163762
No earlier version was observed for comparison.
Heat
1.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- ai-news-radar
examples/ai-news-radar - clinical-anonymization
examples/clinical-anonymization - commit-message-generator
examples/commit-message-generator - content-summarizer
examples/content-summarizer - copywriting-assistant
examples/copywriting-assistant - data-analyzer
examples/data-analyzer - data-visualizer
examples/data-visualizer - document-generator
examples/document-generator - financial-analyzer
examples/financial-analyzer - linkedin-post-generator
examples/linkedin-post-generator - pdf-processor
examples/pdf-processor - pr-review
examples/pr-review - product-roadmap-builder
examples/product-roadmap-builder - prompt-optimizer
examples/prompt-optimizer - radar-ia-br
examples/radar-ia-br - spreadsheet-analyst
examples/spreadsheet-analyst - web-researcher
examples/web-researcher - workflow-automator
examples/workflow-automator
How it works
ai-news-radar
When your agent uses it
Searches and summarizes the latest AI news in English from selected sources. Removes duplicates and categorizes the topics.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
772 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Objective
- Usage
- Preferred sources
- Instructions
- Selection criteria
- Duplicate removal
- Possible categories
- Output format
Files
.gitignoreasset1 bytesSKILL.mdcore3,514 bytesSKILL.mdcore3,514 bytes
Read SKILL.md
# AI News Radar
## Objective
Searches and summarizes the main recent Artificial Intelligence news from curated sources.
The skill:
- searches recent news
- removes duplicates
- categorizes the topics
- translates/summarizes in English
- returns:
- titleView the complete source on GitHubclinical-anonymization
When your agent uses it
Removes sensitive data from clinical text while preserving meaning. Use for healthcare data.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
93 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
Files
SKILL.mdcore383 bytes
Read SKILL.md
## Instructions
1. Identify sensitive data:
- Names
- Dates
- Locations
- IDs
2. Replace with placeholders:
- [NAME]
- [DATE]
- [LOCATION]
- [ID]
View the complete source on GitHubcommit-message-generator
When your agent uses it
Generates standardized and meaningful commit messages following best practices. Use when writing or improving commit messages.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Examples
Files
SKILL.mdcore670 bytes
Read SKILL.md
## Instructions
When generating a commit message:
1. Understand the purpose of the changes
2. Identify the main impact
3. Use concise and clear language
4. Prefer imperative tone (e.g., "Add", "Fix", "Update")
5. Optionally include additional details
## Output Format
type(scope): short description
View the complete source on GitHubcontent-summarizer
When your agent uses it
Summarizes long-form content into key insights. Use when reducing large texts.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
77 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Summary
- Key Points
Files
SKILL.mdcore318 bytes
Read SKILL.md
## Instructions
1. Identify main ideas
2. Remove redundant information
3. Preserve key insights
4. Keep concise
## Output Format
## Summary
Short summary
## Key Points
- Point 1View the complete source on GitHubcopywriting-assistant
When your agent uses it
Writes persuasive content for marketing and ads. Use when creating copy.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
68 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Headline
- Body
- Call to Action
Files
SKILL.mdcore308 bytes
Read SKILL.md
## Instructions
1. Identify target audience
2. Define value proposition
3. Use persuasive language
4. Include call to action
## Output Format
## Headline
## Body
## Call to ActionView the complete source on GitHubdata-analyzer
When your agent uses it
Extracts insights from structured data. Use when analyzing datasets.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
74 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Insights
- Observations
Files
SKILL.mdcore322 bytes
Read SKILL.md
## Instructions
1. Identify key variables
2. Analyze patterns and trends
3. Highlight anomalies
4. Generate insights
## Output Format
## Insights
- Insight 1
- Insight 2
## ObservationsView the complete source on GitHubdata-visualizer
When your agent uses it
Generates charts and visual representations from data. Use when visualizing data.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
80 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Chart Suggestion
- Insights
- Notes
Files
SKILL.mdcore368 bytes
Read SKILL.md
## Instructions
1. Identify key variables
2. Choose appropriate chart type
3. Highlight important patterns
4. Keep visualization clear
## Output Format
## Chart Suggestion
Type of chart
## Insights
- Key patternsView the complete source on GitHubdocument-generator
When your agent uses it
Generates structured documents such as reports, summaries, and formal texts. Use when creating documents.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
86 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Title
- Introduction
- Body
- Conclusion
Files
SKILL.mdcore399 bytes
Read SKILL.md
## Instructions
1. Understand the purpose of the document
2. Identify key sections
3. Organize content logically
4. Use clear and professional language
## Output Format
## Title
## Introduction
## BodyView the complete source on GitHubfinancial-analyzer
When your agent uses it
Analyzes financial data and generates insights. Use when working with financial reports.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
91 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Summary
- Key Metrics
- Insights
- Recommendations
Files
SKILL.mdcore389 bytes
Read SKILL.md
## Instructions
1. Identify key metrics (revenue, costs, profit)
2. Analyze trends
3. Highlight risks or opportunities
4. Provide insights
## Output Format
## Summary
## Key Metrics
- Metric 1
View the complete source on GitHublinkedin-post-generator
When your agent uses it
Creates professional and engaging LinkedIn posts. Use when writing content for LinkedIn.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
97 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
Files
SKILL.mdcore432 bytes
Read SKILL.md
## Instructions
1. Identify the main topic or insight
2. Structure the post with a strong hook
3. Use short paragraphs for readability
4. Add a clear takeaway
5. Optionally include a call to action
## Output Format
- Hook (first line)
- Body (short paragraphs)
- Closing (insight or CTA)View the complete source on GitHubpdf-processor
When your agent uses it
Extracts and summarizes content from PDF documents. Use when working with PDF files.
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
86 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Summary
- Key Sections
Files
SKILL.mdcore378 bytes
Read SKILL.md
## Instructions
1. Extract text from the document
2. Identify key sections or themes
3. Summarize relevant information
4. Preserve important structure
## Output Format
## Summary
Main points of the document
## Key Sections
- Section 1View the complete source on GitHubpr-review
When your agent uses it
Reviews pull requests for code quality, readability, security, and best practices. Use when analyzing code changes or reviewing a PR.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
147 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Summary
- Issues
- Suggestions
- Positives
- Risk Level
Files
SKILL.mdcore699 bytes
Read SKILL.md
## Instructions
When reviewing a pull request:
1. Analyze the code changes (diff)
2. Identify potential bugs or edge cases
3. Check readability and structure
4. Evaluate performance implications
5. Look for security issues (if applicable)
6. Suggest improvements and alternatives
## Output Format
## SummaryView the complete source on GitHubproduct-roadmap-builder
When your agent uses it
Structures product plans and feature roadmaps. Use when planning products.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
84 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Goals
- Roadmap
- Priorities
Files
SKILL.mdcore335 bytes
Read SKILL.md
## Instructions
1. Define product goals
2. Identify key features
3. Prioritize based on impact
4. Organize timeline
## Output Format
## Goals
## Roadmap
- Phase 1
- Phase 2View the complete source on GitHubprompt-optimizer
When your agent uses it
Improves prompts for better LLM performance. Use when refining prompts.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
78 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Original Prompt
- Improved Prompt
- Improvements
Files
SKILL.mdcore373 bytes
Read SKILL.md
## Instructions
1. Analyze the original prompt
2. Identify ambiguities or weaknesses
3. Improve clarity and structure
4. Add constraints if needed
## Output Format
## Original Prompt
...
## Improved Prompt
...View the complete source on GitHubradar-ia-br
When your agent uses it
Busca e resume as últimas notícias de IA em português a partir de fontes selecionadas. Remove duplicatas e categoriza os tópicos.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Objetivo
- Uso
- Fontes preferenciais
- Instruções
- Critérios de seleção
- Remoção de duplicadas
- Categorias possíveis
- Formato de saída
Files
.gitignoreasset1 bytesSKILL.mdcore3,613 bytes
Read SKILL.md
# Radar Notícias IA BR
## Objetivo
Busca e resume as principais notícias recentes de Inteligência Artificial a partir de fontes curadas.
A skill:
- busca notícias recentes
- remove duplicatas
- categoriza os tópicos
- traduz/resume em português
- retorna:
- título
- linkView the complete source on GitHubspreadsheet-analyst
When your agent uses it
Analyzes and manipulates spreadsheet data (Excel/CSV). Use when working with tabular data.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
87 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Summary
- Analysis
- Recommendations
Files
SKILL.mdcore409 bytes
Read SKILL.md
## Instructions
1. Understand dataset structure
2. Identify key columns and metrics
3. Perform calculations or transformations
4. Extract insights
## Output Format
## Summary
Overview of the dataset
## Analysis
- Key findingsView the complete source on GitHubweb-researcher
When your agent uses it
Performs structured research and synthesizes information. Use when researching topics.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
81 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Topic
- Key Insights
- Sources
Files
SKILL.mdcore338 bytes
Read SKILL.md
## Instructions
1. Define research goal
2. Identify relevant sources
3. Extract key insights
4. Summarize findings
## Output Format
## Topic
## Key Insights
- Insight 1
- Insight 2View the complete source on GitHubworkflow-automator
When your agent uses it
Designs structured workflows for tasks and automation. Use when organizing processes.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
82 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
- Output Format
- Workflow Steps
- Automation Opportunities
Files
SKILL.mdcore366 bytes
Read SKILL.md
## Instructions
1. Understand the task or process
2. Break into steps
3. Identify dependencies
4. Suggest automation opportunities
## Output Format
## Workflow Steps
1. Step 1
2. Step 2
## Automation OpportunitiesView the complete source on GitHubSkills included
- ai-news-radar
- clinical-anonymization
- commit-message-generator
- content-summarizer
- copywriting-assistant
- data-analyzer
- data-visualizer
- document-generator
- financial-analyzer
- linkedin-post-generator
- pdf-processor
- pr-review
- product-roadmap-builder
- prompt-optimizer
- radar-ia-br
- spreadsheet-analyst
- web-researcher
- workflow-automator
Repository facts
- License
- Apache-2.0
- Created
- Apr 27, 2026
- Last pushed
- May 16, 2026
- Forks
- 33
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
examples/ai-news-radar/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Frontmatter field user-invocable in examples/ai-news-radar/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md examples/ai-news-radar/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md examples/ai-news-radar/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md examples/ai-news-radar/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md examples/ai-news-radar/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md examples/ai-news-radar/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.