code-yeongyu/oh-my-openagent / packages/shared-skills/skills/ulw-research
ulw-research
UnverifiedRuns maximum-saturation research with a cooperating team, claim-graph gating, and a cited, QA'd deliverable. Use when the user explicitly asks for research or a deep investigation, including any 'ulw' research wording.
scripts/tests/fixtures/fidelity/report-good.html
View on GitHub<!doctype html>
<html lang="en">
<head><meta charset="utf-8"><title>Bridge report</title></head>
<body>
<h1>Bridge report</h1>
<h2>Findings</h2>
<p>The span is <data class="fact" value="320" data-fact="F1" data-unit="m" data-lineage="MEASURED">up to 320 m</data> long [S4].</p>
<p>In millimetres the span is <data class="fact" value="320000" data-fact="F8" data-unit="mm" data-lineage="DERIVED">320,000 mm (320 m)</data> [S4].</p>
<p>Units sold reached <data class="fact" value="1237" data-fact="F2" data-lineage="MEASURED">1,237</data> [S4].</p>
<p>The operator wrote <q data-fact="Q1" data-quote-sel="full">we estimate completion no earlier than 2027</q> [S4].</p>
<p>The schedule note opens with <q data-fact="Q1" data-quote-sel="lead=4">we estimate completion no…</q> [S4].</p>
<p>The opening date is <q data-fact="Q1" data-quote-sel="from=no earlier;to=2027">…no earlier than 2027</q> [S4].</p>
<p>The test suite ran with <data class="fact" value="42" data-fact="F7" data-claim-kind="verified" data-lineage="MEASURED">42 passed</data> [S5].</p>
<p data-kind="opinion">This looks like a sound plan.</p>
<p data-claim="C1">The design follows the published standard.</p>
<figure data-chart-source="assets/share.csv">
<svg viewBox="0 0 200 100" role="img"><g class="ticks" data-tick-step="10" data-tick-min="0" data-tick-max="30"><text x="0" y="90">0</text><text x="0" y="60">10</text><text x="0" y="30">20</text><text x="0" y="5">30</text></g><text x="40" y="50">12%</text><text x="120" y="20">27%</text></svg>
<figcaption>Market share by segment, in percent [S4].</figcaption>
</figure>
<table>
<thead><tr><th>Metric</th><th>Value</th></tr></thead>
<tbody>
<tr><td>Span</td><td><data class="fact" value="320" data-fact="F1" data-unit="m" data-lineage="MEASURED">320 m</data></td></tr>
<tr><td>Units sold</td><td><data class="fact" value="1237" data-fact="F2" data-lineage="MEASURED">1,237</data></td></tr>
</tbody>
</table>
<h2>Appendix</h2>
<p>Units sold in the base year were <data class="fact" value="1237" data-fact="F2" data-lineage="MEASURED">1,237</data> [S4].</p>
<h2>Gaps and contradictions</h2>
<p data-claim="C3">An early schedule claim was refuted.</p>
<h2>How this report was made</h2>
<p>Collected from the cited public page and one recorded test run [S4] [S5].</p>
<h2>Sources</h2>
<ol>
<li id="s4">[S4] Bridge authority page, retrieved 2026-10-01.</li>
<li id="s5">[S5] Test run output, recorded 2026-10-01.</li>
</ol>
</body>
</html>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |