Rebuild and validate Skillz Forge catalog truth, evidence contracts, and provenance without credentials.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add OKHP3/skillz --skill catalog-integrity --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Catalog Integrity?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/okhp3-catalog-integrity)More formats (shields.io, HTML) on the badges page.
---
name: catalog-integrity
description: Rebuild and validate Skillz Forge catalog truth, evidence contracts, and provenance without credentials.
---
# Catalog integrity
## Use when
Run after changing a skill contract, family metadata, evidence artifacts,
catalog derivation, or generated catalog assets.
## Callable command
```bash
node .agents/skills/catalog-integrity/run.mjs
```
The command runs the existing `artifacts/forge/scripts/build-catalog.js` and
`test-catalog.mjs` from their migrated workspace locations. It sets the local
development escape hatch for a shallow checkout only; CI still fails closed.
## Inputs and outputs
- Input: the current checkout's root distribution families and generated
`artifacts/forge/public/data/` assets.
- Output: concise pass/fail lines and a non-zero exit on invalid counts,
metadata, evidence vocabulary, payload split, or provenance.
Never paste credentials into the command. A local shallow-history warning is
not a release pass; a CI shallow-history failure blocks publishing.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...