Repository navigation
Add per-agent Skills management and spawn load state #2525
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.
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
Merged
Changes from all commits
Commits
Show all changes
19 commits
Select commit
Hold shift + click to select a range
60716e1
Add per-agent skills management and spawn load state
lilyshen0722 ae31304
Mount Skills in agent Settings and verify runtime report
lilyshen0722 9ec5ecb
Search full skill catalog and scope load names to installed skills
lilyshen0722 b62e659
Report actual skill inclusion for Claude and Codex
lilyshen0722 9cac625
Keep skill reports on an installed pod and use design tokens
lilyshen0722 05c63df
Report skill frontmatter names from wrapper spawns
lilyshen0722 3aef685
Deliver installed catalog skills to next wrapper spawn
lilyshen0722 8995266
Cover server skill prompt budget
lilyshen0722 3581c6a
Record skill load only after completed spawn
lilyshen0722 7125ac7
Keep run loop mock aligned with skill feed
lilyshen0722 c793318
Harden skill queries and limit installed skills reads
lilyshen0722 07af8a0
Normalize skill keys without edge regex
lilyshen0722 0c3c84d
Keep agent turns running when skill delivery fails
lilyshen0722 f5dc4c5
test(skills): align route fixtures with ObjectId validation
lilyshen0722 ebe84d0
Use accessible installation pod for agent skills
lilyshen0722 7a4abe7
Show selected pod in agent Skills section
lilyshen0722 0345f34
Keep Wake and Pods before Skills in agent settings
lilyshen0722 a226f8a
Rebase agent Skills and bump CLI to 0.1.135
lilyshen0722 8ec0749
Keep Policy and Skills together in agent Settings
lilyshen0722 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
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
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
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
🔎 Supported by static analysis
🏁 Script executed:
Repository: Team-Commonly/commonly
Length of output: 10746
🏁 Script executed:
Repository: Team-Commonly/commonly
Length of output: 10899
Stop truncating agent-scoped skill content before storage.
upsertImportedSkillAssetstorestruncate(markdown || '', 8000)for every import. The agent skills feed returns that stored value, so an agent skill longer than 8000 characters reaches the runtime cut off mid-instruction. The wrapper still counts the cut skill as mounted, and the skill-load report records it as loaded. The stored metadata does not keep the full text.Keep the full markdown for agent-scoped imports. The wrapper's 64 KB budget then decides whether each skill fits. A skill that does not fit is reported as conflicted, not loaded.
🐛 Suggested fix
Existing agent skills stay truncated until they are imported again. Add a test that imports an agent-scoped skill longer than 8000 characters. Assert that the stored
contentequals the full markdown and thatGET /pods/:podId/skillsreturns the full text.🤖 Prompt for AI Agents