Goodeye-LabsGoodeye-Labs/truesight-mcp-skills/skills/build-review-interface/SKILL.md

build-review-interface

Skill7 starsChanged 8 months agoMITView on GitHub

Build a custom web interface for trace annotation and review. Use when users need a bespoke review surface for their workflow.

2 other projects use a version of this.

Adopted by

Most recently taken up by

cerbos/skillstheir own version, first seen Oct 15, 2026
ai-evals-course/evals-skillstheir own version, first seen Aug 31, 2026

Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
ai-evals-course/evals-skills★ 1.4ksame name
cerbos/skills★ 5same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- bootstrap-template-evaluationSkill
- create-evaluationSkill
- error-analysisSkill
- eval-auditSkill
- evaluate-traceSkill
- generate-synthetic-dataSkill
- review-and-promote-tracesSkill
- truesight-workflowsSkill

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Use this skill to design and implement a stack-agnostic custom trace review web UI.
line 8
Very specific:
BEFORE the first scoping question, search for a structured question tool (e.g., AskUserQuestion or similar interactive widget) and load it.
line 13
Distinctive:
Start with custom web UI scoping questions.
line 16
Distinctive:
Ask one question at a time.
line 19
Distinctive:
Use the structured question tool for every question.
line 20
Distinctive:
Ask one follow-up when requirements are ambiguous.
line 21
Distinctive:
Add navigation and productivity controls:
line 48
Distinctive:
Keep technology guidance stack-agnostic unless the user asks for a specific stack.
line 68
Distinctive:
Keep sampling logic separate from UI implementation.
line 70

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Build Review Interface

Use this skill to design and implement a stack-agnostic custom trace review web UI.

Interactive Q&A protocol (mandatory)

<HARD-GATE>
BEFORE the first scoping question, search for a structured question tool (e.g., `AskUserQuestion` or similar interactive widget) and load it. Use that tool for EVERY scoping question. Fall back to plain-text lettered options ONLY if no such tool exists in the environment.
</HARD-GATE>

Start with custom web UI scoping questions.

Rules:

Ask one question at a time.
Use the structured question tool for every question. Structure each with a short header, 2-4 options with labels and descriptions, and place the recommended option first. Do not add "(Recommended)" or similar annotations to option labels.
Ask one follow-up when requirements are ambiguous.

Example question:

What should the primary annotation action set be in v1?
A) Pass / Fail only
B) Pass / Fail + free-text notes
C) Pass / Fail + notes + Defer
D) Custom label set

Custom UI workflow

Define annotation contract:
- pass/fail controls
- free-text notes
- defer action
- autosave behavior
Define data source and persistence:
- JSON/CSV input or API-backed source
- CSV/JSON/SQLite output for labels
Build trace review views:
- render markdown as markdown
- syntax highlight code
- pretty-print JSON
- collapse low-value verbose sections
Add navigation and productivity controls:
- next/previous
- position and progress counters
- keyboard shortcuts
Validate end to end:
- functional checks
- data persistence checks
- Playwright verification for core annotation loop

Design checklist

Consistent layout and terminology across traces
Pass/fail actions visually distinct
Full trace visible or expandable
Autosave on primary actions
Keyboard shortcuts for frequent actions
Trace-level annotation as default

Guardrails

Keep technology guidance stack-agnostic unless the user asks for a specific stack.
- Review the existing codebase to determine if any existing stack is available and offer that as an option.
Keep sampling logic separate from UI implementation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free