Skip to content

Require AI-generated content disclosure in copilot instructions and skills #125842

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
stephentoub merged 3 commits into from
Mar 20, 2026
Merged

Require AI-generated content disclosure in copilot instructions and skills #125842

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1928baa
Require AI-generated content disclosure in copilot instructions and s…
stephentoub Mar 20, 2026
8811456
Tweak instructions
stephentoub Mar 20, 2026
8b8493a
Merge branch 'main' into ai-disclosure-copilot-instructions
stephentoub Mar 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions .github/copilot-instructions.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,15 @@ When NOT running under CCA, guidance for creating commits and pushing changes:
- Never push to an active PR without being explicitly asked, even in autopilot/yolo mode. Always wait for explicit instruction to push.
- Never chain commit and push in the same command. Always commit first, report what was committed, then wait for an explicit push instruction. This creates a mandatory decision point.
- Prefer creating a new commit rather than amending an existing one. Exceptions: (1) explicitly asked to amend, or (2) the existing commit is obviously broken with something minor (e.g., typo or comment fix) and hasn't been pushed yet.
- **Before posting to GitHub (PRs, issues, comments):** Include the AI-generated content disclosure (see below).

## AI-Generated Content Disclosure

When posting any content to GitHub under a user's credentials — opening PRs, creating issues, commenting on PRs or issues, posting review comments, or any other public-facing action — and the account is **not** a dedicated "copilot" or "bot" account/app, you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated.

This applies to all GitHub interactions: PR descriptions, issue bodies, comments, review comments, etc. Exceptions:
- The account is a recognized bot or Copilot app account (e.g., `github-actions[bot]`, `copilot`), where the AI origin is already apparent from the account identity.
- The user explicitly asks you to omit the disclosure.
Comment on lines +51 to +57
Copy link

Copilot AI Mar 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The disclosure section uses a level-2 heading (##), but later the document starts a major section with a level-1 heading (# Building & Testing...). This makes the heading hierarchy inconsistent (a # heading appears after a ## heading). Consider making the disclosure section a # heading too, or adjusting subsequent headings so the hierarchy stays consistent.

Copilot uses AI. Check for mistakes.

---

Expand Down
7 changes: 1 addition & 6 deletions .github/skills/api-proposal/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,12 +270,7 @@ Present the complete draft to the user for review. Iterate based on feedback bef

### Phase 5: Publish

> **Agent disclaimer:** When publishing to GitHub on behalf of a user account, prepend the following disclaimer to the proposal body:
>
> ```markdown
> > [!NOTE]
> > This proposal was drafted with the help of an AI agent. Please review for accuracy and remove this notice once you're satisfied with the content.
> ```
> **AI-generated content disclosure:** When posting any content to GitHub (issue body, PR body, comments) under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — prepend a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. This applies to the initial proposal, iteration updates, and any follow-up comments posted on the user's behalf. Skip this if the user explicitly asks you to omit it.

#### Step 1: Push and capture commit URL

Expand Down
2 changes: 2 additions & 0 deletions .github/skills/ci-analysis/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ Analyze CI build status and test failures in Azure DevOps and Helix for dotnet r

> 🚨 **NEVER** use `gh pr review --approve` or `--request-changes`. Only `--comment` is allowed. Approval and blocking are human-only actions.

> 📝 **AI-generated content disclosure:** When posting any content to GitHub (PR comments, retry commands, analysis summaries) under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.

**Workflow**: Gather PR context (Step 0) → run the script → read the human-readable output + `[CI_ANALYSIS_SUMMARY]` JSON → synthesize recommendations yourself. The script collects data; you generate the advice. For supplementary investigation beyond the script, MCP tools (AzDO, Helix, GitHub) provide structured access when available; the script and `gh` CLI work independently when they're not.

## When to Use This Skill
Expand Down
2 changes: 2 additions & 0 deletions .github/skills/code-review/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,8 @@ When the environment supports launching sub-agents with different models (e.g.,

When presenting the final review (whether as a PR comment or as output to the user), use the following structure. This ensures consistency across reviews and makes the output easy to scan.

> 📝 **AI-generated content disclosure:** When posting review content to GitHub (PR review comments, PR comments) under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.

### Structure

```
Expand Down
6 changes: 6 additions & 0 deletions .github/skills/issue-triage/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,6 +461,12 @@ Key points:
with these explicit instructions; the constraint above prevents *autonomous*
actions before the human decision, not user-directed actions after it.

When posting any content to GitHub (issue comments, label changes with explanations)
under a user's credentials -- i.e., the account is **not** a dedicated "copilot"
or "bot" account/app -- you **MUST** include a concise, visible note (e.g. a
`> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if
the user explicitly asks you to omit it.

- **NEVER** use `gh issue close`, `gh issue edit`, `gh issue comment`, or
`gh pr review --approve`/`--request-changes` **unless the user explicitly
asks you to** after picking an outcome.
Expand Down
2 changes: 2 additions & 0 deletions .github/skills/performance-benchmark/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,8 @@ public class Bench

Post a comment on the PR to trigger EgorBot with your benchmark. The general format is:

> 📝 **AI-generated content disclosure:** When posting benchmark comments to GitHub under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.

@EgorBot [targets] [options] [BenchmarkDotNet args]

Comment on lines 126 to 131
Copy link

Copilot AI Mar 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This disclosure requirement sits right before the @EgorBot ... example, but later the skill warns that any extra text between the EgorBot command line and the code block will be treated as additional command args. To prevent confusion, clarify where the disclosure note should be placed (e.g., before the @EgorBot line or in a separate comment) so users don’t accidentally put it between the command and the benchmark code block.

Suggested change
Post a comment on the PR to trigger EgorBot with your benchmark. The general format is:
> 📝 **AI-generated content disclosure:** When posting benchmark comments to GitHub under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.
@EgorBot [targets] [options] [BenchmarkDotNet args]
Post a comment on the PR to trigger EgorBot with your benchmark. Structure the comment as follows:
1. (Required when posting under a human user's credentials; optional for dedicated bot accounts) Add a visible AI-generated-content disclosure **before** the `@EgorBot` line in the comment. Do **not** place this disclosure between the `@EgorBot` command line and the benchmark code block. For example:
> 📝 **AI-generated content disclosure:** When posting benchmark comments to GitHub under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.
2. On a new line after the disclosure (or at the top of the comment if no disclosure is needed), add the EgorBot command:
@EgorBot [targets] [options] [BenchmarkDotNet args]
3. Immediately after the `@EgorBot` line, add your benchmark code block, with no intervening text:

Copilot uses AI. Check for mistakes.
```cs
Expand Down
2 changes: 2 additions & 0 deletions .github/skills/vmr-codeflow-status/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ Analyze the health of VMR codeflow PRs in both directions:

> 🚨 **NEVER** use `gh pr review --approve` or `--request-changes`. Only `--comment` is allowed. Approval and blocking are human-only actions.

> 📝 **AI-generated content disclosure:** When posting any content to GitHub (PR comments, analysis summaries) under a user's credentials — i.e., the account is **not** a dedicated "copilot" or "bot" account/app — you **MUST** include a concise, visible note (e.g. a `> [!NOTE]` alert) indicating the content was AI/Copilot-generated. Skip this if the user explicitly asks you to omit it.

**Workflow**: Run the script → read the human-readable output + `[CODEFLOW_SUMMARY]` JSON → synthesize recommendations yourself. The script collects data; you generate the advice.

## Prerequisites
Expand Down
Loading