Canonical Copilot Collections is a repository for organizing and distributing GitHub Copilot instructions, prompts, agents, and skills across Canonical repositories. Teams configure repositories to subscribe to shared collections, such as Python, documentation, or Juju development guidance, and keep those assets synchronized.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add canonical/copilot-collections --skill generate-promptgit clone --depth 1 https://github.com/canonical/copilot-collectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/canonical/copilot-collections/generate-prompt)<a href="https://agentmods.dev/skills/canonical/copilot-collections/generate-prompt"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-prompt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/canonical/copilot-collections/generate-prompt"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.02549 |
| Opus 5 | $0.00044 | $0.01274 |
| Sonnet 5 | $0.00018 | $0.00510 |
| Haiku 4.5 | $0.00009 | $0.00255 |
Grade A, and why
generate-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Template Generator (Template Engineer)
Overview
This skill generates Prompt Template files that are pure text templates optimized for:
- Repeatability: Same task, different inputs
- Efficiency: Manual trigger, snapshot of current editor
- Simplicity: No scripts, no thinking processes, just templates
Key distinction:
- Prompts (this skill) = Quick reusable snippets with variables
- Skills = Complex workflows with scripts/references
- Agents = Persistent roles with tool constraints
- Instructions = Always-on rules
Example prompts:
- "Explain this code" (variable: selected code)
- "Fix this bug" (variables: error message, code context)
- "Add unit tests" (variables: function code, framework)
- "Document this API" (variables: endpoint code, method)
Workflow
Step 1: Intent Validation
Confirm the user wants a Prompt Template (not a skill, agent, or instruction).
Decision tree:
- User wants a quick, repeatable snippet? → Continue to Step 2
- Examples: "Explain code", "Fix bug", "Add tests"
- User wants a complex workflow with scripts?
- → STOP. Redirect to
generate-agent-skillsinstead - Explain: Skills have workflows, scripts, progressive disclosure
- → STOP. Redirect to
- User wants a persistent role/perspective?
- → STOP. Redirect to
generate-agentinstead - Explain: Agents have identity, tool constraints, thinking processes
- → STOP. Redirect to
- User wants always-on rules?
- → STOP. Redirect to
generate-path-instructionsorgenerate-repo-instructions - Explain: Instructions provide continuous guidance
- → STOP. Redirect to
Proceed only if creating a simple, reusable prompt template.
Step 2: Task Analysis
Goal: Understand what the prompt does and when it's used.
Load the task analysis checklist:
cat references/task_analysis_checklist.md
Work through the checklist to define:
- Task Description - What does this prompt do?
- Trigger Conditions - When would someone use this?
- Input Requirements - What data does it need?
- Output Format - What should it produce?
- Constraints - Any rules or limitations?
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 379 lines · 89 tokens per session scan A 61c6082b9236
generate-prompt is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 6d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,549 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
hve-builder
Create, improve, refactor, replace, review, or validate prompts, instructions, agents, subagents, and skills, and build or extend HVE workflows. Use when authoring or cleaning up Copilot customizations, deciding which instructions to keep or retire, or connecting an HVE workflow to project-specific knowledge, tools…