triple-review

Reviews a task using the TRIPLE protocol, as the review agent.

diegosouzapw/awesome-omni-skill·0installs61starsOther

SKILL.md

Full skill instructions

Review the project local TASK.md file and the working dir, in context with the git diff. Follow the triple.md protocol to review the impl agent's work, and provide feedback.

You are the review agent. Surface any concerns per the protocol, separate from findings.

$ARGUMENTS

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/diegosouzapw/awesome-omni-skill --skill triple-review

View on GitHub

skills/ai-agents/triple-review/SKILL.md

Categories

Other

remotion-best-practices
Best practices for Remotion - Video creation in React
563.7K installs
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
401.5K installs
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
353.1K installs
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
228K installs