Agent skill

Generate Entity Context

by rundeck in rundeck/rundeck

Generate standardized CONTEXT.md files for features. An agent skill from rundeck/rundeck.

Apache-2.0Auto-check passedDevelopment

Install Generate Entity Context

skills CLI
$ npx skills add rundeck/rundeck --skill generate-entity-context -a claude-code

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

GitHub CLI
$ gh skill install rundeck/rundeck generate-entity-context --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/rundeck/rundeck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/generate-entity-context .claude/skills/generate-entity-context && 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
generate-entity-context
GitHub stars
6.3k
Token cost
~2k tokens
SKILL.md length
359 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate standardized CONTEXT.md files for features. An agent skill from rundeck/rundeck.

  • Works in 4 steps: Identify Feature Location → Analyze Feature Structure → Create entity/ Directory → …
  • Documenting a new feature
  • SKILL.md covers Skill Overview, When to Use, Skill Execution Steps and Key Files, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Generate Entity Context is an agent skill from rundeck/rundeck. Generate standardized CONTEXT.md files for features. Use when documenting a new feature, creating entity-friendly technical documentation, or standardizing existing feature documentation.

Its SKILL.md is about 2k 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 Technical documentation. The repository describes itself as: Enable Self-Service Operations: Give specific users access to your existing tools, services, and scripts. The licence is Apache-2.0.

When your agent uses it

  • Documenting a new feature
  • Creating entity-friendly technical documentation
  • Standardizing existing feature documentation

Example prompts

  • “/generate-entity-context”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Shell, Write, StrReplace

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Identify Feature Location
  2. Analyze Feature Structure
  3. Create entity/ Directory
  4. Generate CONTEXT.md Using Template

What it can do on your machine

Read from SKILL.md and the folder at commit 664a7dd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Shell
    • Write
    • StrReplace

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and mermaid).

    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

Generate Entity Context loads about 2k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 359 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 rundeck/rundeck at commit 664a7dd, republished under its Apache-2.0 licence (© rundeck). 359 words, ~1,989 tokens.

Download SKILL.mdSave it as .claude/skills/generate-entity-context/SKILL.md (or your agent's skills folder).
name
generate-entity-context
description
Generate standardized CONTEXT.md files for features. Use when documenting a new feature, creating entity-friendly technical documentation, or standardizing existing feature documentation.
allowed-tools
Read, Grep, Glob, Shell, Write, StrReplace
disable-model-invocation
false
argument-hint
<feature-path>

Generate Entity Context Documentation

Skill Overview

This skill guides the creation of standardized CONTEXT.md files within feature modules. These files serve as technical briefings for AI entities, providing structured, scannable documentation about feature implementation.

When to Use

  • Creating new features that will require entity maintenance
  • Documenting existing features for entity consumption
  • Standardizing technical documentation across the codebase
  • User invokes: /generate-entity-context or similar command

Skill Execution Steps

1. Identify Feature Location

Ask the user which feature/module needs documentation, or accept it as a parameter.

2. Analyze Feature Structure

Scan the feature directory to identify:

  • Entry point files (main components, index files)
  • Services and API integration files
  • State management files (stores, composables)
  • Test files location
  • Key dependencies (imports analysis)
3. Create __entity__/ Directory

Create the standardized directory at the feature root:

[feature-path]/__entity__/CONTEXT.md
4. Generate CONTEXT.md Using Template

Use the following template structure:

markdown
# [Feature Name]

## Quick Facts
- **Purpose**: [one-line description of what this feature does]
- **Owner**: [team or person responsible]
- **Status**: [stable|experimental|deprecated]
- **Entry Point**: `path/to/main/file.ext`

## Architecture

```mermaid
graph LR
    A[Controller] --> B[Service]
    B --> C[Repository]
    B --> D[External API]

Key Files

FilePurposePattern Used
ExecutionController.javaHTTP endpoint handlerREST controller
ExecutionService.javaBusiness logic layerService layer pattern
ExecutionRepository.javaData access layerRepository pattern
ExecutionTypes.javaDomain modelsDTO/Entity definitions

Implementation Patterns

Data Access: [Pattern used - e.g., JPA repository with transaction management] API Integration: [How external APIs are called - e.g., Via HttpClient with retry logic] Error Handling: [Error handling approach - e.g., Custom exceptions with @ControllerAdvice] Testing: [Testing approach - e.g., Spock with Mockito in src/test/] Validation: [Validation approach - e.g., Bean Validation annotations]

Show full SKILL.md (139 more words)Show less

Critical Context

Important information entities must know before modifying this feature

  • [Gotcha #1: e.g., Execution requires active database transaction]
  • [Gotcha #2: e.g., Timeout is configurable via application.properties]
  • [Business Logic: e.g., Failed executions retry 3x with exponential backoff]
  • [Performance: e.g., Batch processing uses pagination - do not load all records]

Dependencies

mermaid
graph TD
    ExecutionService --> DatabaseConnection
    ExecutionService --> MessageQueue
    ExecutionService --> AuditLogger

Common Tasks

Add new [execution type]
  1. Update ExecutionType enum in ExecutionTypes.java
  2. Add handler method in ExecutionService.java
  3. Update ExecutionController.java endpoint mapping
  4. Add test in src/test/.../ExecutionServiceTest.java
Debug [failed execution]
  • Check database logs for transaction errors
  • Verify message queue connectivity in application logs
  • Review ExecutionAuditLog table for execution history
Modify [execution workflow]
  1. Update business logic in ExecutionService.java
  2. Modify validation rules if needed
  3. Update integration tests to cover new workflow

References

  • Conventions: [Relevant conventions] (see CLAUDE.md)
  • Architecture: [Relevant architecture] (see .claude/docs/architecture.md#section)
  • Testing: [Relevant testing approach] (see .claude/docs/testing-guidelines.md#section)

### 5. Populate Template Sections

#### Quick Facts
- Extract feature purpose from code analysis or ask user
- Determine status based on code maturity
- Identify entry point file

#### Architecture Diagram
- Analyze imports to understand component relationships
- Generate Mermaid diagram showing main data flow
- Aim for 4-7 nodes when the feature has meaningful relationships to show; for simple features, accuracy takes precedence — do not pad nodes artificially to hit a number

#### Key Files Table
- List 4-8 most important files
- Describe each file's purpose concisely
- Identify which pattern each file follows

#### Implementation Patterns
- Analyze code to identify:
  - Data access approach (JPA/JDBC/ORM patterns)
  - API integration pattern (service layer, direct calls, etc.)
  - Error handling mechanism
  - Testing strategy
  - Validation approach

#### Critical Context
- Ask user about non-obvious behavior
- Identify gotchas from code analysis (hardcoded values, timeouts, etc.)
- Note business logic requirements
- Document performance considerations

#### Dependencies Diagram
- Analyze imports to identify external dependencies
- Create Mermaid diagram showing dependency relationships
- Focus on significant dependencies only

#### Common Tasks
- Generate 2-4 common task procedures
- Base on typical operations for this feature type
- Provide concrete, step-by-step instructions

#### References
- Link to relevant sections in centralized docs
- Be specific (include anchor links)

### 6. Review and Validate
- Ensure all Mermaid diagrams are valid
- Verify file paths are correct
- Check that tables are properly formatted
- Confirm references to centralized docs are accurate

### 7. Self-Verification

Before presenting the CONTEXT.md to the user, complete the verification checklist in [VERIFICATION-CHECKLIST.md](VERIFICATION-CHECKLIST.md).

The checklist covers:
- **Content Completeness**: All required sections populated
- **Format Quality**: Proper markdown and structure
- **Technical Accuracy**: Code alignment verification
- **Entity Usability**: Scanability and actionability
- **Consistency**: Standards adherence

All 25 checklist items must pass before presenting to the user.

### 8. Present to User
Show the generated `CONTEXT.md` and:
- Highlight sections that need user input
- Ask user to validate critical context
- Offer to adjust any section

## Output Requirements

The generated `CONTEXT.md` must:
- Use proper Markdown formatting
- Include valid Mermaid diagrams
- Use tables for structured data
- Keep prose to minimum (bullet points preferred)
- Be approximately 50-150 lines depending on feature complexity
- Be scannable (entity should extract key info in <30 seconds)

## Example Invocation

**User**: `/generate-entity-context src/services/execution`

**Entity Response**:
1. Analyzes `src/services/execution/` directory
2. Identifies key files, patterns, dependencies
3. Asks clarifying questions about critical context
4. Generates `src/services/execution/__entity__/CONTEXT.md`
5. Presents result for user validation

## Quality Guidelines

**Do:**
- Keep diagrams simple and focused
- Use tables over paragraphs
- Provide actionable procedures
- Link to centralized docs for detailed patterns
- Focus on what entities need to know, not what humans need

**Don't:**
- Write essay-style documentation
- Include historical context (not an ADR)
- Over-explain obvious code
- Create complex diagrams with 10+ nodes
- Duplicate content from centralized docs

## Notes
- This format is optimized for entity consumption, not human reading
- The `README.md` in the feature directory should serve human developers
- `CONTEXT.md` is about operational facts, not decision rationale
- Update `CONTEXT.md` when significant changes occur to the feature

© rundeck, 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 .claude/skills/generate-entity-context of rundeck/rundeck.

Open the folder on GitHubat commit 664a7dd

Compare with similar skills

Generate Entity Context 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.

Generate Entity Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Generate Entity Context this skillrundeck/rundeck6.3k—~2kAutomated safety check: PassApache-2.0
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Simple Englishropensci/ckanr1043 repos~2kAutomated safety check: PassMIT
evlog Enricher Creatorevloghq/evlog1.9k—~1.7kAutomated safety check: PassMIT
Kitaru Docszenml-io/kitaru300—~936Automated safety check: PassApache-2.0
Verify New Sample PRpnp/sp-dev-fx-aces139—~2kAutomated safety check: PassMIT

Similar skills

  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Simple English

    ropensci/ckanr

    Write or rewrite text in plain, layman-readable English in the spirit of ASD-STE100 Simplified Technical English: short sentences, active voice, simple tenses, one word one meaning, condition before…

    104 GitHub starsUsed in 3 repos~2k tokens
    DevelopmentAuto-check passed
  • Guides adding a new built-in enricher to the evlog package, covering the source, tests, docs, README, a related skill and a changeset.

    1.9k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Kitaru Docs

    zenml-io/kitaru

    Kitaru documentation surfaces, link rules, and accuracy rules.

    300 GitHub stars~936 tokensUpdated today
    DevelopmentAuto-check passed
  • Verify New Sample PR

    pnp/sp-dev-fx-aces

    Verify a "new sample" PR in pnp/sp-dev-fx-aces builds successfully, then produce a deployment + testing checklist from the sample README so it can be manually deployed and tested before merging.

    139 GitHub stars~2k tokensUpdated 9 days ago
    DevelopmentAuto-check passed
  • Benchmark Readme Sync

    rstackjs/build-tools-performance

    Refresh README benchmark results from a successful GitHub Actions Benchmark run, preserving data provenance and separate development, build, and memory tables.

    115 GitHub stars~1.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from rundeck/rundeck

All 10 skills in this repo
  • Backport PR

    rundeck/rundeck

    Backport commits from an existing GitHub Pull Request to a target branch and open a new backport PR.

    6.3k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Cve Remediation

    rundeck/rundeck

    Verify if a CVE affects the project and remediate it. An agent skill from rundeck/rundeck.

    6.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • I18n Vue Template

    rundeck/rundeck

    Internationalize Vue component templates by replacing all hardcoded strings with $t() calls and adding translations to i18n.ts or enUS.js.

    6.3k GitHub stars~523 tokensUpdated today
    Auto-check: notes
  • Onboard Contributor

    rundeck/rundeck

    Guide a new contributor through the rundeck OSS repo. An agent skill from rundeck/rundeck.

    6.3k GitHub stars~848 tokensUpdated today
    Auto-check passed
  • Write Jest Tests

    rundeck/rundeck

    Write Vue component unit tests. An agent skill from rundeck/rundeck.

    6.3k GitHub stars~486 tokensUpdated today
    Auto-check: notes
  • Create API Endpoint

    rundeck/rundeck

    Create REST API endpoints with proper OpenAPI annotations, API versioning, and testing following Rundeck standards.

    6.3k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Generate Entity Context

What does Generate Entity Context do?

Generate standardized CONTEXT.md files for features. An agent skill from rundeck/rundeck. Generate Entity Context is an agent skill from rundeck/rundeck.md files for features.

When should I use Generate Entity Context?

Generate Entity Context fits situations like: documenting a new feature; creating entity-friendly technical documentation; standardizing existing feature documentation.

How do I install Generate Entity Context in Claude Code?

Run `npx skills add rundeck/rundeck --skill generate-entity-context -a claude-code`. Or copy the skill folder (.claude/skills/generate-entity-context in rundeck/rundeck) into .claude/skills/generate-entity-context in your project. Claude Code loads it when a task matches its description.

How do I install Generate Entity Context in Codex?

Run `npx skills add rundeck/rundeck --skill generate-entity-context -a codex`. Or copy the skill folder (.claude/skills/generate-entity-context in rundeck/rundeck) into .agents/skills/generate-entity-context in your project. Codex loads it when a task matches its description.

Can I use Generate Entity Context 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 rundeck/rundeck --skill generate-entity-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-entity-context, .gemini/skills/generate-entity-context, .github/skills/generate-entity-context and .opencode/skills/generate-entity-context in your project.

What does Generate Entity Context need to run?

SKILL.md names no scripts, command-line tools or credentials: Generate Entity Context is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Shell, Write, StrReplace.

Does Generate Entity Context 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 Generate Entity Context 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 Generate Entity Context use?

Generate Entity Context 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 Generate Entity Context use?

About 2k tokens (SKILL.md is roughly 8k 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 Generate Entity Context?

Skills that share tags, products or a category with Generate Entity Context: Simple English (moeru-ai/airi, 50k stars), Simple English (ropensci/ckanr, 104 stars), evlog Enricher Creator (evloghq/evlog, 1.9k stars) and Kitaru Docs (zenml-io/kitaru, 300 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generate Entity Context?

rundeck (a GitHub organization) maintains it in rundeck/rundeck, which has 6,327 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

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