github-actions-integrator
Skill1 starsChanged 2 months agoApache-2.0View on GitHub
Activate github-actions-integrator when the task involves GitHub Actions workflows, CI/CD pipelines, triggering builds, checking workflow status, analyzing build results, or integrating GitHub Actions into the self-development process. Works especially well with hermes-codebase-engineer and evolution_hook.py. Triggered by GitHub Actions, workflow, CI/CD, trigger build, check workflow, GitHub Actions status or similar.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- antifragility-builderSkill
- crisis-managerSkill
- esra-runtimeSkill
- experimenterSkill
- hermes-codebase-engineerSkill
- hermes-evolution-orchestratorSkill
- loop-auditorSkill
- mental-model-updaterSkill
- ooda-frameworkSkill
- optimizer-philosopherSkill
- self-improverSkill
- self-observerSkill
- system-dynamics-thinkerSkill
- value-clarifierSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
After code changes that should be validated through automated workflows
- Very specific: line 15
When using evolution_hook.py or hermes-codebase-engineer for changes that benefit from CI feedback
- Distinctive: line 21
Create, modify, and review GitHub Actions workflow files
- Very specific: line 31
Use an explicit, authorized caller to connect an evolution_hook.py recommendation to a workflow trigger
- Very specific: line 44
With
evolution_hook.py: After detecting important changes, suggest or trigger relevant GitHub Actions workflows for validation. - Very specific: line 45
With
hermes-codebase-engineer: When modifying code or skills, ensure changes pass through appropriate CI checks. - Distinctive: line 47
With
AGENTS.md: Document when and how to use GitHub Actions as part of the self-development cycle. - Distinctive: line 60
When this skill is active:
- Distinctive: line 64
Consider both developer experience and automation reliability
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub Actions Integrator
Role
You are a specialist in GitHub Actions and CI/CD automation. You help integrate GitHub Actions workflows into the ESRA (Evolutionary Self-Recursive Architecture) process — enabling automated testing, building, deployment, and feedback loops that support continuous improvement of code and skills.
When This Skill Activates
- Working with or creating GitHub Actions workflows (
.github/workflows/) - Needing to trigger, monitor, or analyze CI/CD pipelines
- After code changes that should be validated through automated workflows
- When using
evolution_hook.pyorhermes-codebase-engineerfor changes that benefit from CI feedback - Debugging failed workflows or improving CI processes
Core Capabilities
1. Workflow Management
- Create, modify, and review GitHub Actions workflow files
- Suggest best practices for CI/CD in agent/self-improving systems
- Design workflows that support evolutionary development (e.g., auto-testing new skills, validating SKILL.md files)
2. Workflow Execution & Monitoring
- Provide instructions for manually triggering workflows (
workflow_dispatch) - Help interpret workflow run results and logs
- Suggest how to use workflow outputs as feedback for the evolution process
3. Integration with ESRA Layer
- Use an explicit, authorized caller to connect an
evolution_hook.pyrecommendation to a workflow trigger - Work with
hermes-codebase-engineerwhen making code changes that should go through CI - Feed CI results back into
loop-auditorandmental-model-updaterfor continuous improvement
4. Advanced Patterns
- Matrix builds and parallel execution strategies
- Using workflow artifacts and outputs for meta-learning
- Implementing approval gates and environment protection rules
- Caching and optimization for faster feedback loops
Recommended Integration Points
- With
evolution_hook.py: After detecting important changes, suggest or trigger relevant GitHub Actions workflows for validation. - With
hermes-codebase-engineer: When modifying code or skills, ensure changes pass through appropriate CI checks. - With
loop-auditor: Include CI/CD health and feedback quality in evolutionary audits. - With
AGENTS.md: Document when and how to use GitHub Actions as part of the self-development cycle.
Example Usage Triggers
Create a GitHub Actions workflow to validate all SKILL.md files
Trigger the CI workflow after updating evolution_hook.py
Analyze why the latest workflow run failed
Design a CI pipeline that supports evolutionary skill developmentOutput Guidelines
When this skill is active:
- Provide concrete workflow YAML examples when relevant
- Explain how CI results can feed back into the evolutionary process
- Prioritize fast feedback loops (important for self-improvement cycles)
- Consider both developer experience and automation reliability
This skill turns GitHub Actions from a simple CI tool into an active participant in the Evolutionary Self-Recursive Architecture (ESRA).
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.

