runbook-generator
Skill0 starsChanged 10 months agoMITView on GitHub
Creates structured runbooks to document reproducible scenarios for APIs, UX flows, and technical procedures
- Reads credentials
9 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- OneWave-AI/claude-skillstheir own version, first seen Sep 21, 2026
- Hassaan146/claude-skillstheir own version, first seen Jul 25, 2026
- mahiunfiltered/claude-code-skillstheir own version, first seen Jul 8, 2026
- stevancris/sre-ai-agenttheir own version, first seen Jun 14, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- OneWave-AI/claude-skills★ 378same name
- Hassaan146/claude-skills★ 18same name
- csiddhant796-blip/claude-skills-collection★ 2same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- kazemcodes/skill-tree★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- Arnav-0/claude-code-setup★ 0same name
- darkweb19/skills★ 0same name
- stevancris/sre-ai-agent★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- coaching-reporter/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- astro-mcp-integrationSkill
- coaching-reporterSkill
- commit-messageSkill
- feature-notesSkill
- pr-creatorSkill
- project-roadmapSkill
- runbook-executorSkill
- scoped-commitsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 9 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Default runbook location: ./runbooks/<task-name>/STEPS.md
- Distinctive: line 46
When asked to create a runbook:
- Very specific: line 48
Run the creation script: ./runbook-generator/scripts/create-runbook.sh <runbook-path>
- Distinctive: line 50
Ensure all sections are complete and actionable
- Distinctive: line 51
Verify the runbook is reproducible
- Distinctive: line 53
When asked to update a runbook:
- Distinctive: line 56
Update the relevant sections
- Distinctive: line 61
Create a runbook for user login flow:
- Distinctive: line 66
Create a runbook for API endpoint testing:
- Distinctive: line 73
When a runbook contains HTTP requests that can be executed locally, create scripts using httpie to automate the requests and save responses.
- Very specific: line 113
Create a .env file for secrets (copy from .env.example):
- Very specific: line 131
Use script-http instead of http directly
- Distinctive: line 132
Use environment variables for secrets and configuration
- Very specific: line 160
When documenting HTTP steps in STEPS.md, reference the activation and scripts:
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
This skill helps create standardized runbooks that document reproducible scenarios in a clear, step-by-step format. Runbooks are ideal for documenting API workflows, user interface flows, deployment procedures, and any technical process that needs to be executed consistently.
A runbook is a living document that describes an ideal, reproducible scenario - not a log of past executions. It should be executable multiple times with the same expected results.
Configuration
Default runbook location: ./runbooks/<task-name>/STEPS.md
You can customize the runbook path when creating a new runbook.
Runbook Structure
Each runbook must include:
- Overview: Brief description of what this runbook accomplishes
- Technical Requirements: Environment setup needed before execution
- Git branch/commit to checkout
- Database state requirements
- Required credentials or configurations
- Environment context (local, dev, staging, prod)
- Any pre-execution setup (delete records, modify configs, etc.)
- Steps to Reproduce: Clear, actionable steps
- Exact commands to run
- UI elements to click
- API calls to make (with curl examples)
- Expected responses at each step
- Validations: How to verify successful completion
- Database queries to run
- UI states to check
- API responses to validate
- Success criteria
Instructions
When asked to create a runbook:
- Run the creation script:
./runbook-generator/scripts/create-runbook.sh <runbook-path> - Edit the generated template with specific details
- Ensure all sections are complete and actionable
- Verify the runbook is reproducible
When asked to update a runbook:
- Locate the existing STEPS.md file
- Update the relevant sections
- Maintain the standard structure
Examples
Create a runbook for user login flow:
./runbook-generator/scripts/create-runbook.sh runbooks/user-login-flowCreate a runbook for API endpoint testing:
./runbook-generator/scripts/create-runbook.sh runbooks/api-payment-flowHTTP Request Scripts
When a runbook contains HTTP requests that can be executed locally, create scripts using httpie to automate the requests and save responses.
Important: All scripts must be executed under supervision. Review each script before execution and verify the target endpoints are correct for your environment.
Structure for HTTP Scripts
<runbook-path>/
├── STEPS.md
├── scripts/
│ ├── activation.sh # Environment setup and aliases
│ ├── .env # Secrets (git-ignored)
│ ├── .env.example # Example configuration
│ ├── login.httpie.sh
│ ├── get-user.httpie.sh
│ └── responses/
│ ├── 1738500000-login.httpie.http
│ └── 1738500100-get-user.httpie.http
└── evidence/Activation Script
The activation.sh script sets up the environment for HTTP scripts:
- Loads environment variables from
.envfile (for secrets) - Creates the
script-httpfunction that wraps httpie and saves responses automatically
Usage
# First, activate the environment
source ./scripts/activation.sh
# Then run your scripts
./scripts/login.httpie.shConfiguration with .env
Create a .env file for secrets (copy from .env.example):
cp .env.example .envExample .env:
API_BASE_URL=https://api.example.com
API_USERNAME=your-username
API_PASSWORD=your-password
API_TOKEN=your-bearer-tokenScript Requirements
Each httpie script should:
- Use
script-httpinstead ofhttpdirectly - Use environment variables for secrets and configuration
- Include a comment indicating to run
source ./activation.shfirst
Naming Convention
Response files follow this pattern:
<unix-timestamp>-<endpoint-name>.httpie.httpExample httpie Script
#!/bin/bash
# Login API request using httpie
# Usage: source ./activation.sh && ./login.httpie.sh
set -e
BASE_URL="${API_BASE_URL:-https://api.example.com}"
script-http POST "$BASE_URL/login" \
username="${API_USERNAME:-test@example.com}" \
password="${API_PASSWORD:-secret123}"STEPS.md Integration
When documenting HTTP steps in STEPS.md, reference the activation and scripts:
## Step 1: Activate environment
\`\`\`bash
source ./scripts/activation.sh
\`\`\`
## Step 2: Authenticate with API
Execute the login script to authenticate:
\`\`\`bash
./scripts/login.httpie.sh
\`\`\`
Expected response: HTTP 200 with JWT token in response body.
Response saved to: `scripts/responses/<timestamp>-login.httpie.http`Resources
- Template:
assets/runbook-template.md - Creation script:
scripts/create-runbook.sh
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

