-
Notifications
You must be signed in to change notification settings - Fork 36
adjust primary skill.md framing with triggers and examples #456
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
Open
paulirish
wants to merge
21
commits into
main
Choose a base branch
from
skill-framing-upgrades
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
21 commits
Select commit
Hold shift + click to select a range
0b3f5ae
Apply pushy frontmatter description and Theory of Mind to SKILL.md (l…
paulirish 269abad
Merge remote-tracking branch 'origin/main' into skill-framing-upgrades
paulirish 242385e
guides: optimize modern-web skill description trigger semantics
paulirish 38f46c7
manual edits
paulirish da6a07b
skills: optimize modern-web frontmatter for triggering efficiency
paulirish dbdc4bf
serving: add prompt triggering and embedding validation test script
paulirish 2812614
serving: expand empirical test with full TPR/FPR dispatching suite
paulirish ab37534
guides: apply optimal GOAL+TRIGGER+BYPASS prompt sequencing format
paulirish 5669693
serving: upgrade empirical test script with high-load selection stres…
paulirish 1865bce
deps: move @google/genai to devDependencies at root
paulirish 02c4622
serving: add RAG similarity-floor calibration sweeps tool
paulirish a46149d
guides: integrate strict exclusions to prevent simple task over-trigg…
paulirish c3bd54e
guides: modernize skill metadata using structured Goal-Trigger-Exclus…
paulirish b8bc253
guides: optimize modern-web skill description using agentskills.io pr…
paulirish 10bed3c
serving: extract tokenizer logging into modular getTokenCountString h…
paulirish bec6a85
serving: drop redundant try-catch block from getTokenCountString
paulirish 41d29d5
serving: restrict tokenizer logging strictly to parsed frontmatter de…
paulirish 4b5742b
serving: expand empirical stress test with Softball Near-Miss evaluat…
paulirish 0db72f5
serving: encapsulate frontmatter parsing inside getDescriptionTokenCo…
paulirish 3df9721
guides: refine modern-web exclusions stanza with explicit trivial-gat…
paulirish 0a0b187
drop these
paulirish 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
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.
Result of description from AGY analysis:
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.
This looks great, but isn't it too long? (1875 chars).
At least Claude's cap is no longer 250 characters (!) but it's still 1500.
Though given that the last list is when not to trigger, I guess the truncation doesn't lose us much.
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.
Ah, great point. Most of the other frontier models have a hard limit at 1024 characters, I believe. Here is a much more concise version (991 characters):
This was tested against the same dataset had the same results (0% False Positive rate, 86.7% trigger accuracy).
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.
#804