Load relevant universal engineering standards (decision-making and ADRs, architecture, testing, security, type design, documentation, etc.) and apply them to the current task. ALWAYS invoke before ANY technical decision, design, documentation or code change — including before writing or revising a decision record, choosing a tool, runtime, platform or data shape, or running a spike.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add ooloth/dotfiles --skill uphold-standards --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Uphold Standards?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ooloth-uphold-standards)More formats (shields.io, HTML) on the badges page.
---
name: uphold-standards
description: Load relevant universal engineering standards (decision-making and ADRs, architecture, testing, security, type design, documentation, etc.) and apply them to the current task. ALWAYS invoke before ANY technical decision, design, documentation or code change — including before writing or revising a decision record, choosing a tool, runtime, platform or data shape, or running a spike.
---
## Your task
1. Read `~/.agents/standards/README.md` to understand the framing and tier definitions
2. List `~/.agents/standards/` to see all available standards files
3. Load all files with a theme relevant to the current task. Include any language-specific file
(e.g. `rust.md`, `python.md`) that matches the language(s) used in the current repository
4. If you notice a gap in the available guidance, feel free to mention what should be added (if no
gap, say nothing)
5. Proactively apply the standards
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', ...