gemini-cli - ✅(Solved) Fix Execute skills directly via slash commands [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
google-gemini/gemini-cli#25318Fetched 2026-04-14 05:55:58
View on GitHub
Comments
0
Participants
1
Timeline
7
Reactions
1
Author
Participants
Timeline (top)
labeled ×3connected ×1cross-referenced ×1issue_type_added ×1

Fix Action

Fixed

PR fix notes

PR #25327: feat(cli): provide default post-submit prompt for skill command

Description (problem / solution / changelog)

Summary

Provide a default post-submit prompt "Use the skill [name]" for skill commands if no extra arguments are provided.

Details

This ensures that when a user runs a skill command (e.g., /pr-creator), the agent is immediately prompted to use the skill, reducing the need for an extra user turn to manually type "use the skill pr-creator".

Related Issues

Related to #25318

How to Validate

Run the relevant test: npm test -w @google/gemini-cli -- src/services/SkillCommandLoader.test.ts

Pre-Merge Checklist

  • Updated relevant documentation and README (if needed)
  • Added/updated tests (if needed)
  • Noted breaking changes (if any)
  • Validated on required platforms/methods:
    • MacOS
      • npm run

Changed files

  • packages/cli/src/services/SkillCommandLoader.test.ts (modified, +1/-1)
  • packages/cli/src/services/SkillCommandLoader.ts (modified, +4/-1)
RAW_BUFFERClick to expand / collapse

What would you like to be added?

Ensure that invoking a skill via a slash command (e.g., /code-reviewer) executes the skill immediately and returns the results, rather than just loading the skill into the context.

Why is this needed?

Currently, running /code-reviewer appears to load the skill rather than actually execute it. The user expectation is that a slash command representing a skill should act as a direct command to execute and return output (e.g., start reviewing current code).

Additional context

As skills can replace a lot of custom commands, users should not need to first activate skill and then prompt the llm to run it

extent analysis

TL;DR

Modify the slash command invocation to directly execute the skill and return results, rather than just loading it into the context.

Guidance

  • Investigate the current implementation of slash command handling to identify why it only loads the skill instead of executing it.
  • Consider adding a parameter or flag to the slash command that indicates whether the skill should be executed immediately or just loaded.
  • Review the user expectation and skill functionality to ensure that direct execution of a skill via a slash command aligns with the intended user experience.
  • Examine the skill activation and execution logic to determine if there are any existing mechanisms that can be leveraged to achieve the desired behavior.

Example

No code snippet is provided as the issue lacks specific technical details about the implementation.

Notes

The solution may depend on the specific architecture and implementation of the skill system, slash command handling, and user interaction logic.

Recommendation

Apply a workaround to modify the slash command handling to execute the skill immediately, as the current behavior does not meet user expectations.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

gemini-cli - ✅(Solved) Fix Execute skills directly via slash commands [1 pull requests, 1 participants]