Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso, rules-distill. Never ship without evidence (gstack screenshots, metrics). Use on any build/suggest/lead task.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add frankxai/Starlight-Intelligence-System --skill excellence-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Excellence Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/frankxai-excellence-review)More formats (shields.io, HTML) on the badges page.
---
name: excellence-review
description: Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso, rules-distill. Never ship without evidence (gstack screenshots, metrics). Use on any build/suggest/lead task.
---
# Excellence Review Skill — Grok Harness
## God 99 Mandate
1. repo-mastery (read all rules files first, map cross-repo)
2. CEO/Eng/Design plan reviews (subagent or delegate to claude)
3. Adversarial: verification-loop + santa-method (2 independent pass required)
4. gstack: qa (tiers quick/standard/exhaustive), browse, design-review, benchmark, canary
5. Security: cso / security-auditor + supply chain
6. Polish: rules-distill, skill-comply, document-release
Output format: report + before/after + artifacts. Iterate atomically.
Tools: gstack (headless browser ~100ms), terminal (tests), subagents.
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', ...
