refactor(skills): improve audit-website skill conciseness and structure#3
Open
popey wants to merge 1 commit intosquirrelscan:mainfrom
Open
refactor(skills): improve audit-website skill conciseness and structure#3popey wants to merge 1 commit intosquirrelscan:mainfrom
popey wants to merge 1 commit intosquirrelscan:mainfrom
Conversation
Improve skill quality scores from 85% to 100% content score
(description score maintained at 100%) by reducing verbosity
and applying progressive disclosure.
| Change | Before | After |
|--------|--------|-------|
| Description score | 100% | 100% |
| Content score | 85% | 100% |
| SKILL.md lines | ~470 | ~185 |
Changes:
- Fix typos in frontmatter description ("cateories" → "categories", "asses" → "assess")
- Consolidate intro, "What This Skill Does", and "Links" into a concise header
- Condense 21-category enumeration into a single-line summary
- Merge "When to Use" into one sentence (was repeating skill description)
- Consolidate "Basic Workflow", "Running Audits", and fix strategy into a single Workflow section
- Condense FIRST SCAN/SECOND SCAN prose into a 2-line scan strategy
- Remove inferrable agent guidance (asking for URLs, live vs local preference)
- Move detailed CLI option tables to references/CLI-OPTIONS.md
- Move score targets, issue categories, and fix approach to references/AUDIT-REFERENCE.md
- Remove "How It Works" section (inferrable from commands)
- Remove redundant "Output Formats" section (covered by Key Options + OUTPUT-FORMAT.md ref)
No behavioral changes — all original guidance is preserved, just reorganized
for better progressive disclosure via reference files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
1 participant
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.
👋 hullo @squirrelscan / @nc9
Improve skill quality scores from 85% to 100% content score (description score maintained at 100%) by reducing verbosity and applying progressive disclosure. Here's a summary of the results, with the actual changes listed below.
Changes:
No intended behavioral changes — all original guidance is preserved, just reorganized for better progressive disclosure via reference files.
These were pretty straightforward changes to bring the skill in line with what performs well against Anthropic's best practices. Full disclosure, I work at @tesslio where we build tooling around this. Not a pitch, just fixes that were straightforward to make, so I thought I'd offer them as a PR.
Of course, if you'd like to get them all to 100%, click here to trigger the evals and iterate some more, otherwise I'm happy to offer more improvements as I find them.
Thanks in advance!