## Summary When Claude responds using a skill from `.claude/skills/`, there's no indication to the user that a skill is being applied. It would be helpful to see which skill (if any) is guiding the response. ## Current Behavior - Skills are loaded silently from `.claude/skills/` - Responses that use skills look identical to responses inferred from context - No way to verify if a skill was actually used - `/skills` command doesn't exist to list loaded skills ## Desired Behavior Some indicati

Feature request: Indicate when a skill is being used

Status Fixed / completed

Maintainer reply None cached

Activity 6 comments · opened Dec 13, 2025 · closed Dec 15, 2025

Summary

When Claude responds using a skill from .claude/skills/, there's no indication to the user that a skill is being applied. It would be helpful to see which skill (if any) is guiding the response.

Current Behavior

Skills are loaded silently from .claude/skills/
Responses that use skills look identical to responses inferred from context
No way to verify if a skill was actually used
/skills command doesn't exist to list loaded skills

Desired Behavior

Some indication when a skill is active, e.g.:

> Reggie, how's my backlog?

⏺ Using skill: reggie-backlog-health

⏺ Bash(python reggie.py health --all)
...

Or a /skills command to list loaded skills and their trigger patterns.

Why This Matters

Debugging: Hard to tell if a skill isn't working or just not triggering
Trust: Users can't verify their skill customizations are being applied
Development: When building skills, feedback on activation helps iteration

Environment

Claude Code v2.0.69
macOS

View original on GitHub ↗

6 Comments

github-actions[bot] · 8 months ago

Found 3 possible duplicate issues:

This issue will be automatically closed as a duplicate in 3 days.

If your issue is a duplicate, please close it and 👍 the existing issue instead
To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

tonydehnke · 8 months ago

--- Commet removed --- wrong thread :)

wordify-nick · 8 months ago

Thanks for flagging #12140 @tonydehnke - they're related but tackling different problems.

#12140 is about discovery - "what skills do I have available?"

This issue is about runtime feedback - "which skill is actually being used right now?" Both would benefit from a /skills command, but the core ask here is visibility into skill activation during responses. When you're developing or debugging skills, you need to know if they're actually triggering - not just that they exist.

tonydehnke · 8 months ago

Oops, wrong thread, I 100% agree with your post, hope they implement this!

wordify-nick · 8 months ago

I don't know if this has just been released, but i'm seeing this working now:

> do you know how to do an agent james performance review? 

⏺ Yes! There's a performance-review skill for exactly this. Let me invoke it.

⏺ Skill(performance-review)