An example skill for testing diff-skill evaluation.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add serpro69/claude-toolbox --skill before --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Before?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/serpro69-before-09d6ffd6)More formats (shields.io, HTML) on the badges page.
---
name: example-skill
description: An example skill for testing diff-skill evaluation.
---
<!-- codex: tool-name mapping applied. See .codex/scripts/session-start.sh -->
# Example Skill
**Goal: Validate input data and produce a conformance report.**
## Conventions
Read shared conventions at [shared-conventions.md](shared-conventions.md).
## Required Outputs
- [ ] Conformance report written to `docs/reports/`
- [ ] Inline summary presented to the user
- [ ] Failures indexed under `kk:review-findings`
## Workflow
**Mandatory order — load instructions before acting.** The phases below are strictly sequential. You MUST read all referenced process files before examining any input data. Do not skip verification steps.
See [example-process.md](example-process.md) for the detailed steps.
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', ...
