[bot] Document userPromptSubmitted LLM bypass and multi-skill invocation (v1.0.44)#1656
Merged
aaronpowell merged 1 commit intostagedfrom May 11, 2026
Merged
Conversation
…-skill invocation (v1.0.44)
- automating-with-hooks.md: update userPromptSubmitted event table entry to
mention new ability to handle requests directly (v1.0.44+); add 'Handling
Requests Directly with userPromptSubmitted' example section showing the
{"response":"..."} JSON pattern; update FAQ answer to describe the bypass
capability
- creating-effective-skills.md: update skill invocation Q&A to document
mid-input slash commands and multiple skills in a single message (v1.0.44+);
update 'Can agents chain multiple skills?' FAQ with user-facing details
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
aaronpowell
approved these changes
May 11, 2026
Contributor
Author
|
🟡 Contributor Reputation Check: MEDIUM risk
Maintainers: please review this contributor before merging. |
github-actions
Bot
added
the
needs-review:MEDIUM
Contributor
There was a problem hiding this comment.
Pull request overview
Updates Learning Hub documentation to reflect GitHub Copilot CLI v1.0.44 behavior changes around (1) userPromptSubmitted hooks being able to return direct responses (skipping the LLM) and (2) mid-input slash commands + multi-skill invocation.
Changes:
- Documented
userPromptSubmitted“LLM bypass” behavior and added a new example section showing the{"response":"..."}pattern. - Expanded skill invocation guidance to cover mid-input slash commands and invoking multiple skills in one message.
- Bumped
lastUpdatedmetadata on both pages to 2026-05-08.
Show a summary per file
| File | Description |
|---|---|
| website/src/content/docs/learning-hub/creating-effective-skills.md | Updates the Q&A to describe mid-input slash commands and multiple skill invocations per message (v1.0.44). |
| website/src/content/docs/learning-hub/automating-with-hooks.md | Documents userPromptSubmitted direct-response capability (LLM bypass) and adds an example configuration + script. |
Copilot's findings
- Files reviewed: 2/2 changed files
- Comments generated: 2
| INPUT=$(cat) | ||
| PROMPT=$(echo "$INPUT" | jq -r '.prompt // empty' | tr '[:upper:]' '[:lower:]') | ||
|
|
||
| if echo "$PROMPT" | grep -q "^/help\b"; then |
| "userPromptSubmitted": [ | ||
| { | ||
| "type": "command", | ||
| "bash": "./scripts/prompt-router.sh", |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What's new in v1.0.44
The v1.0.44 release (2026-05-08) shipped two notable user-facing features that weren't yet documented in the Learning Hub:
1.
userPromptSubmittedhooks can bypass the LLMHooks on the
userPromptSubmittedevent can now handle a request directly by writing{"response": "..."}to stdout. The CLI delivers that text to the user and skips the model call entirely. Previously the event was documented only as useful for auditing/logging.Use cases: inline FAQ bots, policy enforcement with clear rejection messages, prompt redirect patterns.
2. Multiple skills per message & mid-input slash commands
Slash commands no longer have to appear at the start of a message — they can appear mid-input. Users can also invoke multiple skills in a single message (e.g.,
/generate-tests and then /conventional-commit).What was updated
website/src/content/docs/learning-hub/automating-with-hooks.mduserPromptSubmittedevent table row to mention the new LLM-bypass capability{"response": "..."}patternlastUpdatedto 2026-05-08website/src/content/docs/learning-hub/creating-effective-skills.mdlastUpdatedto 2026-05-08Source announcements