Analyze gaps in user-facing features and desirable characteristics, developer-facing tooling and desirable characteristics, and other opportunities not currently tracked in the project's backlog. Use when the user asks you to help identify opportunities to improve the system.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ooloth/dotfiles --skill scan-gaps --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Scan Gaps?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ooloth-scan-gaps)More formats (shields.io, HTML) on the badges page.
---
name: scan-gaps
description: Analyze gaps in user-facing features and desirable characteristics, developer-facing tooling and desirable characteristics, and other opportunities not currently tracked in the project's backlog. Use when the user asks you to help identify opportunities to improve the system.
effort: high
---
## Your task
1. Use up to 50 subagents to explore the current codebase (or subsection if the user specified a smaller scope)
2. Identify opportunities to improve user- or developer-facing characteristics and address fundamental flaws
3. Study the user's `trekker`, Jira, Monday, GitHub issues or other backlog (if any) to see what opportunities are already tracked
4. Report the top untracked user-facing and developer-facing opportunities
5. Generate a self-contained HTML slide deck of the findings:
- `mkdir -p .outputs/<yyyy-mm-dd>`
- Write the report to `.outputs/<yyyy-mm-dd>/scan-gaps.html` — clean minimal styling, one slide per opportunity plus a summary/title slide, keyboard arrow-key and click navigation between slides
- `open .outputs/<yyyy-mm-dd>/scan-gaps.html`
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', ...
