Skip to content

docs: feature the biggest improvement cases on the landing page #44

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.

Sign up for GitHub

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
DCCA merged 1 commit into from
Jun 23, 2026
Merged

docs: feature the biggest improvement cases on the landing page #44

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions docs/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,6 +171,8 @@ <h2>skval vs. <code>skill-creator</code></h2>
<section id="benchmark">
<h2>Benchmark</h2>
<p class="lead">skval's deterministic structural scan over 10 widely-used skills — 8 ship as-is; the two flagged hit the size budget.
Plus runs over <a href="https://github.com/DCCA/skval/blob/main/docs/examples/skill-benchmark/wild-skills.md">75 installed skills</a>
and <a href="https://github.com/DCCA/skval/blob/main/docs/examples/skill-benchmark/from-the-web.md">69 from the web</a>.
<a href="https://github.com/DCCA/skval/tree/main/docs/examples/skill-benchmark">See the full benchmark →</a></p>
<table>
<tr><th>Skill</th><th>Type</th><th>Score</th><th>Findings</th></tr>
Expand All @@ -185,9 +187,13 @@ <h2>Benchmark</h2>
<tr><td>skill-creator</td><td>file_transform</td><td class="pill warn">96 / A</td><td>SKILL.md ~8246 tokens (&gt;5000)</td></tr>
<tr><td>docx</td><td>file_transform</td><td class="pill warn">92 / A</td><td>599 lines &amp; ~5142 tokens (over budget)</td></tr>
</table>
<div class="grid2" style="margin-top:18px">
<div class="card"><h3>docx · 92 → 100</h3><p style="color:var(--dim);margin:0">Applied skval's finding — moved the XML Reference section to <code>references/</code> (progressive disclosure). skval's own <code>compare.py</code>: <b class="A">+8</b>.</p></div>
<div class="card"><h3>bad-skill · 73 → 100</h3><p style="color:var(--dim);margin:0">Fixed four findings (kebab name, drop <code>&lt;&gt;</code>, broken ref, stray key). <code>compare.py</code>: <b class="A">+27</b>, Revise → Ship.</p></div>
<h3 style="color:var(--white);font-size:19px;margin:28px 0 4px">The upgrade: score → fix → re-score</h3>
<p class="lead" style="margin:0 0 14px">skval doesn't just grade — its ranked findings drive the fix. The biggest real-world turnarounds:</p>
<div class="grid2">
<div class="card"><h3>web skill · invalid frontmatter · <span class="warn">50</span> → <span class="A">100</span></h3>
<p style="color:var(--dim);margin:0">A real published skill whose unquoted colon broke its YAML — it used to <em>crash</em> skval, and now scores. One-line fix: quote the description. <code>compare.py</code>: <b class="A">+50</b>, Revise → Ship. <a href="https://github.com/DCCA/skval/blob/main/docs/examples/skill-benchmark/from-the-web.md">case study →</a></p></div>
<div class="card"><h3>bad-skill · <span class="warn">73</span> → <span class="A">100</span></h3>
<p style="color:var(--dim);margin:0">Four findings fixed one-for-one — kebab name, drop <code>&lt;&gt;</code>, broken ref, stray key. <code>compare.py</code>: <b class="A">+27</b>, Revise → Ship. <a href="https://github.com/DCCA/skval/tree/main/docs/examples/skill-benchmark/improved">case study →</a></p></div>
</div>
</section>

Expand Down
Loading