Repository inventory

tkarakai/ai-agent-instruction-templates

Skills indexed from this repository, with install-style signals scoped to the repo.
1 skills0 GitHub stars0 weekly installsShellGitHubOwner profile

Overview

This skill loads an AI agent instruction template into the current project's .agents/ directory to give you a ready-made set of role-specific instructions. It automates downloading, placing agent instructions, recording version metadata, and pulling any declared dependencies. Use it to quickly add structured agent roles such as technical planners without manual setup.

How this skill works

You invoke the loader with the template name (and optional version). The loader script downloads the template from the remote repository, creates .agents/<template-name>/AGENTS.md containing the agent instructions, and writes version and provenance into .agents/.loaded-templates.yaml. If the template declares dependencies, the loader recursively pulls and installs them into .agents/.

When to use it

  • You need a vetted instruction set for a specific agent role (e.g., technical planner).
  • Setting up a project with repeatable, shareable agent roles and workflows.
  • Onboarding new team members who will run agents and need clear instructions.
  • Preparing commit or PR metadata that links which templates were used.
  • When you want to reuse community or organization templates with version traceability.

Best practices

  • Keep .agents/ in .gitignore to avoid committing generated or private instruction files.
  • Specify a version (e.g., @v1.0.0) to ensure reproducible agent behavior.
  • Open and review .agents/<template-name>/AGENTS.md before running agents to confirm required inputs.
  • Commit .agents/.loaded-templates.yaml when the template is authoritative for the project’s workflow.
  • Use /list-templates first to preview available templates and avoid unnecessary downloads.

Example use cases

  • Load a Software-Technical-Planner template to generate a step-by-step technical planning agent for project design.
  • Bootstrapping QA or review agents across multiple repositories using the same instruction standard.
  • Onboarding: add instruction templates so new contributors run consistent agent-driven tasks.
  • Auditability: record which template versions were used for later reproducibility and PR notes.

FAQ

Execute the provided curl command to run the loader: bash -c "$(curl -fsSL https://raw.githubusercontent.com/tkarakai/ai-agent-instruction-templates/main/load.sh)" -- <TemplateName[@version]>

Where are templates stored in the repo?

Templates are placed under .agents/<template-name>/ with an AGENTS.md for instructions and .agents/.loaded-templates.yaml for version records.

What if a template declares dependencies?

The loader automatically downloads and installs declared dependencies recursively into .agents/.

1 skills

More from this maintainer
Other repositories and skills published under the same GitHub owner.
Skills library
Jump back to the full directory or explore grouped topics.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational