Files
Obsidian-CLI-skill/eval/eval_review.html
T
pablo-mano a882e74591 Apply optimized description from run_loop eval; add v2 eval set
Description rewritten to emphasize vault action intent over CLI syntax,
with explicit "without this skill Claude has no vault access" framing.
Adds v2 eval set (20 queries built around natural-language vault requests).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-04 00:37:19 +01:00

220 lines
10 KiB
HTML

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Eval Set Review - obsidian-cli v2</title>
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
<style>
* { box-sizing: border-box; margin: 0; padding: 0; }
body { font-family: 'Lora', Georgia, serif; background: #faf9f5; padding: 2rem; color: #141413; }
h1 { font-family: 'Poppins', sans-serif; margin-bottom: 0.5rem; font-size: 1.5rem; }
.description { color: #b0aea5; margin-bottom: 1.5rem; font-style: italic; max-width: 900px; }
.controls { margin-bottom: 1rem; display: flex; gap: 0.5rem; }
.btn { font-family: 'Poppins', sans-serif; padding: 0.5rem 1rem; border: none; border-radius: 6px; cursor: pointer; font-size: 0.875rem; font-weight: 500; }
.btn-add { background: #6a9bcc; color: white; }
.btn-add:hover { background: #5889b8; }
.btn-export { background: #d97757; color: white; }
.btn-export:hover { background: #c4613f; }
table { width: 100%; max-width: 1100px; border-collapse: collapse; background: white; border-radius: 6px; overflow: hidden; box-shadow: 0 1px 3px rgba(0,0,0,0.08); }
th { font-family: 'Poppins', sans-serif; background: #141413; color: #faf9f5; padding: 0.75rem 1rem; text-align: left; font-size: 0.875rem; }
td { padding: 0.75rem 1rem; border-bottom: 1px solid #e8e6dc; vertical-align: top; }
tr:nth-child(even) td { background: #faf9f5; }
tr:hover td { background: #f3f1ea; }
.section-header td { background: #e8e6dc; font-family: 'Poppins', sans-serif; font-weight: 500; font-size: 0.8rem; color: #141413; text-transform: uppercase; letter-spacing: 0.05em; }
.query-input { width: 100%; padding: 0.4rem; border: 1px solid #e8e6dc; border-radius: 4px; font-size: 0.875rem; font-family: 'Lora', Georgia, serif; resize: vertical; min-height: 60px; }
.query-input:focus { outline: none; border-color: #d97757; box-shadow: 0 0 0 2px rgba(217,119,87,0.15); }
.toggle { position: relative; display: inline-block; width: 44px; height: 24px; }
.toggle input { opacity: 0; width: 0; height: 0; }
.toggle .slider { position: absolute; inset: 0; background: #b0aea5; border-radius: 24px; cursor: pointer; transition: 0.2s; }
.toggle .slider::before { content: ""; position: absolute; width: 18px; height: 18px; left: 3px; bottom: 3px; background: white; border-radius: 50%; transition: 0.2s; }
.toggle input:checked + .slider { background: #d97757; }
.toggle input:checked + .slider::before { transform: translateX(20px); }
.btn-delete { background: #c44; color: white; padding: 0.3rem 0.6rem; border: none; border-radius: 4px; cursor: pointer; font-size: 0.75rem; font-family: 'Poppins', sans-serif; }
.btn-delete:hover { background: #a33; }
.summary { margin-top: 1rem; color: #b0aea5; font-size: 0.875rem; }
</style>
</head>
<body>
<h1>Eval Set Review: <span id="skill-name">obsidian-cli</span></h1>
<p class="description">Current description: <span id="skill-desc">Use this skill whenever the user wants Claude to interact with their Obsidian vault — reading notes, creating or appending content, searching, managing tasks, tags, properties, daily notes, bookmarks, templates, sync, plugins, or links. The underlying mechanism is the official Obsidian CLI (v1.12+), but trigger even when the user doesn't mention the CLI — phrases like "add this to my daily note", "search my vault", "create a note from template", or "what tasks do I have open?" all apply. Also trigger for explicit CLI usage: running obsidian subcommands from a shell, scripting or automating vault operations, scheduling via cron, debugging IPC/headless Linux setups, or building programmatic wrappers. Skip only for pure GUI questions (Obsidian settings navigation, theme/plugin installation via UI) or iCloud sync configuration that has nothing to do with vault content.</span></p>
<div class="controls">
<button class="btn btn-add" onclick="addRow()">+ Add Query</button>
<button class="btn btn-export" onclick="exportEvalSet()">Export Eval Set</button>
</div>
<table>
<thead>
<tr>
<th style="width:65%">Query</th>
<th style="width:18%">Should Trigger</th>
<th style="width:10%">Actions</th>
</tr>
</thead>
<tbody id="eval-body"></tbody>
</table>
<p class="summary" id="summary"></p>
<script>
const EVAL_DATA = [
{
"query": "add this to my daily note: 'reviewed the Q1 roadmap with sarah, she wants the mockups by friday'",
"should_trigger": true
},
{
"query": "search my vault for everything i've written about the Henderson project, i need to prep for a call",
"should_trigger": true
},
{
"query": "what open tasks do i have in obsidian? just the incomplete ones",
"should_trigger": true
},
{
"query": "create a new note from my meeting-notes template and call it 'Standup 2026-03-04'",
"should_trigger": true
},
{
"query": "append '- [ ] follow up with the design team about the nav bar' to my projects/mobile-redesign.md",
"should_trigger": true
},
{
"query": "how many notes are in my vault right now? also which ones have no links pointing to them?",
"should_trigger": true
},
{
"query": "read me today's daily note",
"should_trigger": true
},
{
"query": "set the status property on projects/q2-launch.md to 'in-review'",
"should_trigger": true
},
{
"query": "i want to write a script that pulls all notes tagged #meeting from the past week and summarizes them",
"should_trigger": true
},
{
"query": "move everything in my Inbox/ folder to Archive/2026/ and update the daily note with a log entry",
"should_trigger": true
},
{
"query": "how do i change the accent color in obsidian? i want something more muted than the default purple",
"should_trigger": false
},
{
"query": "i can't figure out how to enable community plugins in obsidian — the toggle is greyed out in safe mode",
"should_trigger": false
},
{
"query": "does obsidian have a built-in kanban view or do i need a plugin for that?",
"should_trigger": false
},
{
"query": "my icloud sync for obsidian keeps conflicting with files on my ipad — how do i resolve this without losing data?",
"should_trigger": false
},
{
"query": "how do i set up the obsidian git plugin to auto-commit my vault every hour?",
"should_trigger": false
},
{
"query": "i use notion for my notes but i'm thinking of switching to obsidian — what's the best way to export from notion and import into obsidian?",
"should_trigger": false
},
{
"query": "in the dataview plugin, how do i write a query that shows all notes with a due-date property before today?",
"should_trigger": false
},
{
"query": "i want to customize the obsidian theme with css — how do i target the sidebar background color specifically?",
"should_trigger": false
},
{
"query": "what's the keyboard shortcut to open the command palette in obsidian on mac?",
"should_trigger": false
},
{
"query": "i'm writing a python script to parse markdown files from my notes folder and extract all the headings into a CSV — what's the best library for this?",
"should_trigger": false
}
];
let evalItems = [...EVAL_DATA];
function render() {
const tbody = document.getElementById('eval-body');
tbody.innerHTML = '';
const sorted = evalItems
.map((item, origIdx) => ({ ...item, origIdx }))
.sort((a, b) => (b.should_trigger ? 1 : 0) - (a.should_trigger ? 1 : 0));
let lastGroup = null;
sorted.forEach(item => {
const group = item.should_trigger ? 'trigger' : 'no-trigger';
if (group !== lastGroup) {
const headerRow = document.createElement('tr');
headerRow.className = 'section-header';
headerRow.innerHTML = `<td colspan="3">${item.should_trigger ? 'Should Trigger' : 'Should NOT Trigger'}</td>`;
tbody.appendChild(headerRow);
lastGroup = group;
}
const idx = item.origIdx;
const tr = document.createElement('tr');
tr.innerHTML = `
<td><textarea class="query-input" onchange="updateQuery(${idx}, this.value)">${escapeHtml(item.query)}</textarea></td>
<td>
<label class="toggle">
<input type="checkbox" ${item.should_trigger ? 'checked' : ''} onchange="updateTrigger(${idx}, this.checked)">
<span class="slider"></span>
</label>
<span style="margin-left:8px;font-size:0.8rem;color:#b0aea5">${item.should_trigger ? 'Yes' : 'No'}</span>
</td>
<td><button class="btn-delete" onclick="deleteRow(${idx})">Delete</button></td>
`;
tbody.appendChild(tr);
});
updateSummary();
}
function escapeHtml(text) {
const div = document.createElement('div');
div.textContent = text;
return div.innerHTML;
}
function updateQuery(idx, value) { evalItems[idx].query = value; updateSummary(); }
function updateTrigger(idx, value) { evalItems[idx].should_trigger = value; render(); }
function deleteRow(idx) { evalItems.splice(idx, 1); render(); }
function addRow() {
evalItems.push({ query: '', should_trigger: true });
render();
const inputs = document.querySelectorAll('.query-input');
inputs[inputs.length - 1].focus();
}
function updateSummary() {
const trigger = evalItems.filter(i => i.should_trigger).length;
const noTrigger = evalItems.filter(i => !i.should_trigger).length;
document.getElementById('summary').textContent =
`${evalItems.length} queries total: ${trigger} should trigger, ${noTrigger} should not trigger`;
}
function exportEvalSet() {
const valid = evalItems.filter(i => i.query.trim() !== '');
const data = valid.map(i => ({ query: i.query.trim(), should_trigger: i.should_trigger }));
const blob = new Blob([JSON.stringify(data, null, 2)], { type: 'application/json' });
const url = URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = 'eval_set.json';
document.body.appendChild(a);
a.click();
document.body.removeChild(a);
URL.revokeObjectURL(url);
}
render();
</script>
</body>
</html>