Search eval sweep

Name: Search eval sweep
Author: @slashclone

@slashclone/search-eval-sweep

Measure search quality with a fixed set of real queries: hits, misses, and false positives at the current cutoff and across a sweep of cutoffs, so ranking and threshold changes are chosen from data instead of guesses. Works for keyword, semantic, or hybrid search.

SkillDatav0.1.0 (latest)

Use in Claude Save Like Clone Comment

Activity: New: be the first to try it
Installs: 0 installs
Likes: 0 likes
Clones: 0 clones

0.1.0
5 Nov 2026
Scan passedNo tests

Use in Claude

Claude Code

/kit add @slashclone/search-eval-sweep

CLI

slashclone add @slashclone/search-eval-sweep

Codex

slashclone add @slashclone/search-eval-sweep --agent codex

Not enforced. Codex does not enforce the permissions this kit declares.

Cursor

slashclone add @slashclone/search-eval-sweep --agent cursor

Not enforced. Cursor does not enforce the permissions this kit declares.

claude.ai and the desktop app

Download for Claude

Not enforced. claude.ai and the Claude desktop app do not enforce the permissions this kit declares. How to upload it

As a file

Download .kit

One file with everything in it. slashclone add ./file.kit checks it against this page before installing.

Review before installing

Set up SlashClone in Claude

Health

No keep-alive checks yet

Checks run weekly once someone keeps the kit installed.

Run reports are off

Safety

Scan passed
Not reviewed yet
No tests

This kit reads **/*.ts, **/*.json and writes to scripts/search-eval*. Install it?

Full scan and review

Similar kits

Playtest feedback
@gameforge
Turn messy playtest notes into a ranked list of what to fix next. Tags each note (bug, confusion, frustration, boredom, delight, idea), tallies them with a script, ranks issues by how many testers hit them and how badly, and lists the moments players loved so you protect them.
Customer health score
@usagemetrics
Score customer health from usage, support, and billing signals with weights you can read and edit. Bands every account green, yellow, or red, names the top drivers, tracks change since the last score, and flags at-risk accounts renewing soon. Works from one CSV.
Agent cost dashboard
@agentcosts
Turn LLM usage logs into one self-contained HTML cost dashboard for an agentic product: cost per customer, per task, per successful outcome, model mix, cache hit rate, and gross margin when you add revenue by customer. Prices blank costs from an editable price table.
Usage pricing simulator
@agentcosts
Test pricing models for an AI product on your real usage before you change a price: per seat, per task, credits, and hybrid (platform fee plus included credits plus overage). Shows revenue, gross margin after LLM cost, and which customers' bills would jump or drop under each model.

Link

https://slashclone.dev/@slashclone/search-eval-sweep

README badge

[![Install with SlashClone](https://slashclone.dev/badge/slashclone/search-eval-sweep.svg)](https://slashclone.dev/@slashclone/search-eval-sweep)

Embed

<iframe src="https://slashclone.dev/embed/slashclone/search-eval-sweep" width="480" height="200" title="@slashclone/search-eval-sweep" loading="lazy"></iframe>

Share card image

More from @slashclone

Product rename checklist
Rename a product across code, copy, CLI, plugins, and docs without breaking anything: one name constant, a careful sweep, and a list of strings that must keep the old name (signing labels, key-derivation labels, OAuth client ids, stored rule ids, migrations). Shows the plan and asks before it edits.
Two theme brand colors
Find brand colors that work in both light and dark mode: for each hue, the shade with the best WCAG contrast against all your light and dark backgrounds at once, so a logo or accent can keep one color in both themes. Prints a table and saves the results as JSON.
Canvas frame capture
Check a canvas or WebGL animation frame by frame when the browser cannot take screenshots (a hidden pane, a background tab, a headless run). Captures timed frames from the page itself and saves them as small images you can look at. Writes only to a frames folder you choose.
Release on green
Set up a release pipeline with no manual gates: when CI passes on main, migrate the database, deploy, run a smoke test, and roll back on its own if the smoke test fails. Writes the GitHub Actions workflow for you to review; never deploys or stores secrets itself.

See all of @slashclone's kits

Report this kit