How do I install the Recap Validate skill?

Run npx skillmds@latest add aboudjem/recap-validate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Recap Validate safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Recap Validate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Recap Validate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Recap Validate?

aboudjem (@aboudjem) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Recap Validate by aboudjem — Agent Skill

Name: Recap Validate
Author: aboudjem

Recap Validate

Use when the user types /recap validate, asks Recap Studio to "score the page", "run validation", "qa the recap", or wants the multi-agent quality report regenerated. Dispatches the validation board and writes a structured report.

aboudjem 280d401 2.0 KB Updated Sep 17, 2026

File contents

/recap validate

You run the validation board and emit a structured quality report.

Inputs

A RecapPageContent JSON (loaded via packages/content-pipeline/src/load.ts).
The rendered Next.js page output (built tree under apps/recap-web/.next/) if available; otherwise reviewers work from the JSON only and downgrade performance & a11y confidence accordingly.

Reviewers (parallel, isolated)

fact-checker: every claim must reference a sourceMap id and the source must support the claim. Unsupported claims drop the score.
beginner-reviewer: read time ≤ 5 min for a smart 18-year-old.
accessibility-reviewer: chunking, motion, focus, density.
ux-design-reviewer: hierarchy, polish, storytelling, responsiveness.
performance-reviewer: bundle, lazy-load, static-first, CWV risk.
security-privacy-reviewer: secrets, PII, prompt-injection cues, side-effect surfaces, untrusted-source flags.
skeptical-reviewer: overclaim, marketing fluff, hidden complexity.

Scoring

Each reviewer emits { score: 1..10, findings: Finding[], blockers: string[] }.

Thresholds (must pass)

Facts	Beginner	A11y	UX	Perf	Sec	Simplicity
9	9	9	8	8	9	9

Output

Write artifacts/<slug>/validation.json and print a Markdown summary:

## Validation report: <slug>
| Dimension | Score | Target | Status | Top finding |
| --------- | ----- | ------ | ------ | ----------- |
...
Blockers:
- ...
Auto-patchable:
- ...

What you must never do

Never inflate a score to clear a threshold.
Never hide blockers.
If a reviewer cannot run (e.g. perf without a build), mark confidence: low and explain why.

---name: recap-validatedescription: Use when the user types /recap validate, asks Recap Studio to "score the page", "run validation", "qa the recap", or wants the multi-agent quality report regenerated. Dispatches the validation board and writes a structured report.---# /recap validateYou run the validation board and emit a structured quality report.## Inputs- A `RecapPageContent` JSON (loaded via `packages/content-pipeline/src/load.ts`).- The rendered Next.js page output (built tree under `apps/recap-web/.next/`) if available; otherwise reviewers work from the JSON only and downgrade performance & a11y confidence accordingly.## Reviewers (parallel, isolated)1. `fact-checker`: every claim must reference a `sourceMap` id and the source must support the claim. Unsupported claims drop the score.2. `beginner-reviewer`: read time ≤ 5 min for a smart 18-year-old.3. `accessibility-reviewer`: chunking, motion, focus, density.4. `ux-design-reviewer`: hierarchy, polish, storytelling, responsiveness.5. `performance-reviewer`: bundle, lazy-load, static-first, CWV risk.6. `security-privacy-reviewer`: secrets, PII, prompt-injection cues, side-effect surfaces, untrusted-source flags.7. `skeptical-reviewer`: overclaim, marketing fluff, hidden complexity.## ScoringEach reviewer emits `{ score: 1..10, findings: Finding[], blockers: string[] }`.## Thresholds (must pass)| Facts | Beginner | A11y | UX | Perf | Sec | Simplicity || ----- | -------- | ---- | -- | ---- | --- | ---------- || 9 | 9 | 9 | 8 | 8 | 9 | 9 |## OutputWrite `artifacts/<slug>/validation.json` and print a Markdown summary:```## Validation report: <slug>| Dimension | Score | Target | Status | Top finding || --------- | ----- | ------ | ------ | ----------- |...Blockers:- ...Auto-patchable:- ...```## What you must never do- Never inflate a score to clear a threshold.- Never hide blockers.- If a reviewer cannot run (e.g. perf without a build), mark `confidence: low` and explain why.

Frequently asked questions