promptlings
Copilot instructions1 starsChanged 11 days agoApache-2.0View on GitHub
Do not create or add scripts unless the user explicitly requests scripts. Do not create or add tests unless the user explicitly requests tests. This repository delivers agents and skills through Markdown instructions. Requests to improve a flow, fix a problem, verify behavior, or review a change are not permission to add scripts, test suites, test fixtures, or CI testing infrastructure. Do not turn a prompt-based workflow into a maintained execution framework. Preserve useful procedures, measured settings, failure handling and…
In this repository24 other files it gives its agents.
- ab-testingSkill
- artifact-inspectionSkill
- comparative-evaluationSkill
- cue-synced-demoSkill
- design-analysisSkill
- design-writingSkill
- evidence-verificationSkill
- intent-alignmentSkill
- interactive-experienceSkill
- narrative-transitionsSkill
- pr-description-writingSkill
- presenter-scriptSkill
- promptlings-memory-captureSkill
- pr-videoSkill
- reasoning-first-narrationSkill
- reasoning-first-writingSkill
- review-comment-writingSkill
- review-ensembleSkill
- spec-deliverySkill
- technical-demo-productionSkill
- technical-illustrationSkill
- technical-investigationSkill
- test-analysisSkill
- tts-setupSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
2 rules. About 1 is common, 1 is distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use these alternatives instead:
- Common: line 22
Every em dash in output is a lint failure.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 Copilot instructions 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
Copilot Instructions
No Scripts or Tests Without an Explicit Request
Do not create or add scripts unless the user explicitly requests scripts. Do not create or add tests unless the user explicitly requests tests.
This repository delivers agents and skills through Markdown instructions. Requests to improve a flow, fix a problem, verify behavior, or review a change are not permission to add scripts, test suites, test fixtures, or CI testing infrastructure. Do not turn a prompt-based workflow into a maintained execution framework.
Preserve useful procedures, measured settings, failure handling and verification guidance in the relevant agent or skill. Use existing tools for execution. Task-specific production code belongs to the producing agent's authorized workspace, not automatically in this repository.
Em Dash Ban
Never use em dashes in any generated content. This is a hard, non-negotiable rule.
Use these alternatives instead:
- Colons for explanations or elaboration
- Commas for parenthetical asides
- Periods for emphasis (start a new sentence)
- Parentheses for supplementary information
- Semicolons for joining related independent clauses
Every em dash in output is a lint failure. No exceptions.
The only context where an em dash character may appear is inside agent instruction files (.agent.md) when the purpose of that text is to explicitly ban agents from using em dashes. Even in that narrow case, prefer spelling out "em dash" rather than using the character itself where possible.
Agent Authoring
All .agent.md files in this repository must include an explicit em dash ban in their instructions. If an agent file does not contain a rule prohibiting em dashes in its output, it is incomplete. The ban should be stated clearly and unambiguously, for example:
Em dashes are banned from all output. Use commas, colons, semicolons, periods, or parentheses instead.
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.

